Jason Eisner

Also published as: Jason M. Eisner


2023

pdf
The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding
Hao Fang | Anusha Balakrishnan | Harsh Jhamtani | John Bufe | Jean Crawford | Jayant Krishnamurthy | Adam Pauls | Jason Eisner | Jacob Andreas | Dan Klein
Findings of the Association for Computational Linguistics: ACL 2023

In a real-world dialogue system, generated text must be truthful and informative while remaining fluent and adhering to a prescribed style. Satisfying these constraints simultaneously isdifficult for the two predominant paradigms in language generation: neural language modeling and rule-based generation. We describe a hybrid architecture for dialogue response generation that combines the strengths of both paradigms. The first component of this architecture is a rule-based content selection model defined using a new formal framework called dataflow transduction, which uses declarative rules to transduce a dialogue agent’s actions and their results (represented as dataflow graphs) into context-free grammars representing the space of contextually acceptable responses. The second component is a constrained decoding procedure that uses these grammars to constrain the output of a neural language model, which selects fluent utterances. Our experiments show that this system outperforms both rule-based and learned approaches in human evaluations of fluency, relevance, and truthfulness.

pdf
Non-Programmers Can Label Programs Indirectly via Active Examples: A Case Study with Text-to-SQL
Ruiqi Zhong | Charlie Snell | Dan Klein | Jason Eisner
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Can non-programmers annotate natural language utterances with complex programs that represent their meaning? We introduce APEL, a framework in which non-programmers select among candidate programs generated by a seed semantic parser (e.g., Codex). Since they cannot understand the candidate programs, we ask them to select indirectly by examining the programs’ input-ouput examples. For each utterance, APEL actively searches for a simple input on which the candidate programs tend to produce different outputs. It then asks the non-programmers only to choose the appropriate output, thus allowing us to infer which program is correct and could be used to fine-tune the parser. As a first case study, we recruited human non-programmers to use APEL to re-annotate SPIDER, a text-to-SQL dataset. Our approach achieved the same annotation accuracy as the original expert annotators (75%) and exposed many subtle errors in the original annotations.

pdf
On the Intersection of Context-Free and Regular Languages
Clemente Pasti | Andreas Opedal | Tiago Pimentel | Tim Vieira | Jason Eisner | Ryan Cotterell
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics

The Bar-Hillel construction is a classic result in formal language theory. It shows, by a simple construction, that the intersection of a context-free language and a regular language is itself context-free. In the construction, the regular language is specified by a finite-state automaton. However, neither the original construction (Bar-Hillel et al., 1961) nor its weighted extension (Nederhof and Satta, 2003) can handle finite-state automata with ε-arcs. While it is possible to remove ε-arcs from a finite-state automaton efficiently without modifying the language, such an operation modifies the automaton’s set of paths. We give a construction that generalizes the Bar- Hillel in the case the desired automaton has ε-arcs, and further prove that our generalized construction leads to a grammar that encodes the structure of both the input automaton and grammar while retaining the asymptotic size of the original construction.

pdf
Time-and-Space-Efficient Weighted Deduction
Jason Eisner
Transactions of the Association for Computational Linguistics, Volume 11

Many NLP algorithms have been described in terms of deduction systems. Unweighted deduction allows a generic forward-chaining execution strategy. For weighted deduction, however, efficient execution should propagate the weight of each item only after it has converged. This means visiting the items in topologically sorted order (as in dynamic programming). Toposorting is fast on a materialized graph; unfortunately, materializing the graph would take extra space. Is there a generic weighted deduction strategy which, for every acyclic deduction system and every input, uses only a constant factor more time and space than generic unweighted deduction? After reviewing past strategies, we answer this question in the affirmative by combining ideas of Goodman (1999) and Kahn (1962). We also give an extension to cyclic deduction systems, based on Tarjan (1972).

pdf
Efficient Semiring-Weighted Earley Parsing
Andreas Opedal | Ran Zmigrod | Tim Vieira | Ryan Cotterell | Jason Eisner
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

We present Earley’s (1970) context-free parsing algorithm as a deduction system, incorporating various known and new speed-ups. In particular, our presentation supports a known worst-case runtime improvement from Earley’s (1970) O(N3|G||R|), which is unworkable for the large grammars that arise in natural language processing, to O(N3|G|), which matches the complexity of CKY on a binarized version of the grammar G. Here N is the length of the sentence, |R| is the number of productions in G, and |G| is the total length of those productions. We also provide a version that achieves runtime of O(N3|M|) with |M| ≤ |G| when the grammar is represented compactly as a single finite-state automaton M (this is partly novel). We carefully treat the generalization to semiring-weighted deduction, preprocessing the grammar like Stolcke (1995) to eliminate the possibility of deduction cycles, and further generalize Stolcke’s method to compute the weights of sentence prefixes. We also provide implementation details for efficient execution, ensuring that on a preprocessed grammar, the semiring-weighted versions of our methods have the same asymptotic runtime and space requirements as the unweighted methods, including sub-cubic runtime on some grammars.

pdf
Privacy-Preserving Domain Adaptation of Semantic Parsers
Fatemehsadat Mireshghallah | Yu Su | Tatsunori Hashimoto | Jason Eisner | Richard Shin
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Task-oriented dialogue systems often assist users with personal or confidential matters. For this reason, the developers of such a system are generally prohibited from observing actual usage. So how can they know where the system is failing and needs more training data or new functionality? In this work, we study ways in which realistic user utterances can be generated synthetically, to help increase the linguistic and functional coverage of the system, without compromising the privacy of actual users. To this end, we propose a two-stage Differentially Private (DP) generation method which first generates latent semantic parses, and then generates utterances based on the parses. Our proposed approach improves MAUVE by 2.5X and parse tree function-type overlap by 1.3X relative to current approaches for private synthetic data generation, improving both on fluency and semantic coverage. We further validate our approach on a realistic domain adaptation task of adding new functionality from private user data to a semantic parser, and show overall gains of 8.5% points on its accuracy with the new feature.

pdf
A Measure-Theoretic Characterization of Tight Language Models
Li Du | Lucas Torroba Hennigen | Tiago Pimentel | Clara Meister | Jason Eisner | Ryan Cotterell
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Language modeling, a central task in natural language processing, involves estimating a probability distribution over strings. In most cases, the estimated distribution sums to 1 over all finite strings. However, in some pathological cases, probability mass can “leak” onto the set of infinite sequences. In order to characterize the notion of leakage more precisely, this paper offers a measure-theoretic treatment of language modeling. We prove that many popular language model families are in fact tight, meaning that they will not leak in this sense. We also generalize characterizations of tightness proposed in previous works.

pdf
Contrastive Decoding: Open-ended Text Generation as Optimization
Xiang Lisa Li | Ari Holtzman | Daniel Fried | Percy Liang | Jason Eisner | Tatsunori Hashimoto | Luke Zettlemoyer | Mike Lewis
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Given a language model (LM), maximum probability is a poor decoding objective for open-ended generation, because it produces short and repetitive text. On the other hand, sampling can often produce incoherent text that drifts from the original topics. We propose contrastive decoding (CD), a reliable decoding approach that optimizes a contrastive objective subject to a plausibility constraint. The contrastive objective returns the difference between the likelihood under a large LM (called the expert, e.g. OPT-13B) and a small LM (called the amateur, e.g. OPT-125M), and the constraint ensures that the outputs are plausible. CD is inspired by the fact that the failures of larger LMs (e.g., repetition, inco- herence) are even more prevalent in smaller LMs, and that this difference signals which texts should be preferred. CD requires zero additional training, and produces higher quality text than decoding from the larger LM alone. It also works across model scales (OPT-13B and GPT2-1.5B) and significantly outperforms four strong decoding algorithms (e.g., nucleus, top-k) in automatic and human evaluations across wikipedia, news and story domains.

pdf
Toward Interactive Dictation
Belinda Z. Li | Jason Eisner | Adam Pauls | Sam Thomson
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Voice dictation is an increasingly important text input modality. Existing systems that allow both dictation and editing-by-voice restrict their command language to flat templates invoked by trigger words. In this work, we study the feasibility of allowing users to interrupt their dictation with spoken editing commands in open-ended natural language. We introduce a new task and dataset, TERTiUS, to experiment with such systems. To support this flexibility in real-time, a system must incrementally segment and classify spans of speech as either dictation or command, and interpret the spans that are commands. We experiment with using large pre-trained language models to predict the edited text, or alternatively, to predict a small text-editing program. Experiments show a natural trade-off between model accuracy and latency: a smaller model achieves 30% end-state accuracy with 1.3 seconds of latency, while a larger model achieves 55% end-state accuracy with 7 seconds of latency.

2022

pdf
Online Semantic Parsing for Latency Reduction in Task-Oriented Dialogue
Jiawei Zhou | Jason Eisner | Michael Newman | Emmanouil Antonios Platanios | Sam Thomson
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Standard conversational semantic parsing maps a complete user utterance into an executable program, after which the program is executed to respond to the user. This could be slow when the program contains expensive function calls. We investigate the opportunity to reduce latency by predicting and executing function calls while the user is still speaking. We introduce the task of online semantic parsing for this purpose, with a formal latency reduction metric inspired by simultaneous machine translation. We propose a general framework with first a learned prefix-to-program prediction module, and then a simple yet effective thresholding heuristic for subprogram selection for early execution. Experiments on the SMCalFlow and TreeDST datasets show our approach achieves large latency reduction with good parsing quality, with a 30%–65% latency reduction depending on function execution time and allowed cost.

pdf
Algorithms for Acyclic Weighted Finite-State Automata with Failure Arcs
Anej Svete | Benjamin Dayan | Ryan Cotterell | Tim Vieira | Jason Eisner
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Weighted finite-state automata (WSFAs) arecommonly used in NLP. Failure transitions area useful extension for compactly representingbackoffs or interpolation in n-gram modelsand CRFs, which are special cases of WFSAs.Unfortunately, applying standard algorithmsfor computing the pathsum requires expand-ing these compact failure transitions. As aresult, na ̈ıve computation of the pathsum inacyclic WFSAs with failure transitions runs inO(|Q|2|Σ|) (O(|Q||Σ|) for deterministic WF-SAs) while the equivalent algorithm in normalWFSAs runs in O(|E|), where E representsthe set of transitions, Q the set of states, andΣ the alphabet. In this work, we present moreefficient algorithms for computing the pathsumin sparse acyclic WFSAs, i.e., WFSAs with av-erage out symbol fraction s ≪ 1. In those,backward runs in O(s|Q||Σ|). We proposean algorithm for semiring-weighted automatawhich runs in O(|E| + s|Σ||Q||Tmax| log |Σ|),where |Tmax| is the size of the largest con-nected component of failure transitions. Ad-ditionally, we propose faster algorithms fortwo specific cases. For ring-weighted WF-SAs we propose an algorithm with complex-ity O(|E| + s|Σ||Q||πmax|), where |πmax| de-notes the longest path length of failure transi-tions stemming from q and Σ(q) the set of sym-bols on the outgoing transitions from q. Forsemiring-weighted WFSAs whose failure tran-sition topology satisfies a condition exemplifiedby CRFs, we propose an algorithm with com-plexity O(|E| + s|Σ||Q| log |Σ|).

pdf
When More Data Hurts: A Troubling Quirk in Developing Broad-Coverage Natural Language Understanding Systems
Elias Stengel-Eskin | Emmanouil Antonios Platanios | Adam Pauls | Sam Thomson | Hao Fang | Benjamin Van Durme | Jason Eisner | Yu Su
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

In natural language understanding (NLU) production systems, users’ evolving needs necessitate the addition of new features over time, indexed by new symbols added to the meaning representation space. This requires additional training data and results in ever-growing datasets. We present the first systematic investigation into this incremental symbol learning scenario. Our analysis reveals a troubling quirk in building broad-coverage NLU systems: as the training dataset grows, performance on a small set of new symbols often decreases. We show that this trend holds for multiple mainstream models on two common NLU tasks: intent recognition and semantic parsing. Rejecting class imbalance as the sole culprit, we reveal that the trend is closely associated with an effect we call source signal dilution, where strong lexical cues for the new symbol become diluted as the training dataset grows. Selectively dropping training examples to prevent dilution often reverses the trend, showing the over-reliance of mainstream neural NLU models on simple lexical cues.

2021

pdf
Searching for More Efficient Dynamic Programs
Tim Vieira | Ryan Cotterell | Jason Eisner
Findings of the Association for Computational Linguistics: EMNLP 2021

Computational models of human language often involve combinatorial problems. For instance, a probabilistic parser may marginalize over exponentially many trees to make predictions. Algorithms for such problems often employ dynamic programming and are not always unique. Finding one with optimal asymptotic runtime can be unintuitive, time-consuming, and error-prone. Our work aims to automate this laborious process. Given an initial correct declarative program, we search for a sequence of semantics-preserving transformations to improve its running time as much as possible. To this end, we describe a set of program transformations, a simple metric for assessing the efficiency of a transformed program, and a heuristic search procedure to improve this metric. We show that in practice, automated search—like the mental search performed by human programmers—can find substantial improvements to the initial program. Empirically, we show that many speed-ups described in the NLP literature could have been discovered automatically by our system.

pdf
Constrained Language Models Yield Few-Shot Semantic Parsers
Richard Shin | Christopher Lin | Sam Thomson | Charles Chen | Subhro Roy | Emmanouil Antonios Platanios | Adam Pauls | Dan Klein | Jason Eisner | Benjamin Van Durme
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

We explore the use of large pretrained language models as few-shot semantic parsers. The goal in semantic parsing is to generate a structured meaning representation given a natural language input. However, language models are trained to generate natural language. To bridge the gap, we use language models to paraphrase inputs into a controlled sublanguage resembling English that can be automatically mapped to a target meaning representation. Our results demonstrate that with only a small amount of data and very little code to convert into English-like representations, our blueprint for rapidly bootstrapping semantic parsers leads to surprisingly effective performance on multiple community tasks, greatly exceeding baseline methods also trained on the same limited data.

pdf
Limitations of Autoregressive Models and Their Alternatives
Chu-Cheng Lin | Aaron Jaech | Xin Li | Matthew R. Gormley | Jason Eisner
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Standard autoregressive language models perform only polynomial-time computation to compute the probability of the next symbol. While this is attractive, it means they cannot model distributions whose next-symbol probability is hard to compute. Indeed, they cannot even model them well enough to solve associated easy decision problems for which an engineer might want to consult a language model. These limitations apply no matter how much computation and data are used to train the model, unless the model is given access to oracle parameters that grow superpolynomially in sequence length. Thus, simply training larger autoregressive language models is not a panacea for NLP. Alternatives include energy-based models (which give up efficient sampling) and latent-variable autoregressive models (which give up efficient scoring of a given string). Both are powerful enough to escape the above limitations.

pdf
Learning How to Ask: Querying LMs with Mixtures of Soft Prompts
Guanghui Qin | Jason Eisner
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Natural-language prompts have recently been used to coax pretrained language models into performing other AI tasks, using a fill-in-the-blank paradigm (Petroni et al., 2019) or a few-shot extrapolation paradigm (Brown et al., 2020). For example, language models retain factual knowledge from their training corpora that can be extracted by asking them to “fill in the blank” in a sentential prompt. However, where does this prompt come from? We explore the idea of learning prompts by gradient descent—either fine-tuning prompts taken from previous work, or starting from random initialization. Our prompts consist of “soft words,” i.e., continuous vectors that are not necessarily word type embeddings from the language model. Furthermore, for each task, we optimize a mixture of prompts, learning which prompts are most effective and how to ensemble them. Across multiple English LMs and tasks, our approach hugely outperforms previous methods, showing that the implicit factual knowledge in language models was previously underestimated. Moreover, this knowledge is cheap to elicit: random initialization is nearly as good as informed initialization.

2020

pdf
Task-Oriented Dialogue as Dataflow Synthesis
Jacob Andreas | John Bufe | David Burkett | Charles Chen | Josh Clausman | Jean Crawford | Kate Crim | Jordan DeLoach | Leah Dorner | Jason Eisner | Hao Fang | Alan Guo | David Hall | Kristin Hayes | Kellie Hill | Diana Ho | Wendy Iwaszuk | Smriti Jha | Dan Klein | Jayant Krishnamurthy | Theo Lanman | Percy Liang | Christopher H. Lin | Ilya Lintsbakh | Andy McGovern | Aleksandr Nisnevich | Adam Pauls | Dmitrij Petters | Brent Read | Dan Roth | Subhro Roy | Jesse Rusak | Beth Short | Div Slomin | Ben Snyder | Stephon Striplin | Yu Su | Zachary Tellman | Sam Thomson | Andrei Vorobev | Izabela Witoszko | Jason Wolfe | Abby Wray | Yuchen Zhang | Alexander Zotov
Transactions of the Association for Computational Linguistics, Volume 8

We describe an approach to task-oriented dialogue in which dialogue state is represented as a dataflow graph. A dialogue agent maps each user utterance to a program that extends this graph. Programs include metacomputation operators for reference and revision that reuse dataflow fragments from previous turns. Our graph-based state enables the expression and manipulation of complex user intents, and explicit metacomputation makes these intents easier for learned models to predict. We introduce a new dataset, SMCalFlow, featuring complex dialogues about events, weather, places, and people. Experiments show that dataflow graphs and metacomputation substantially improve representability and predictability in these natural dialogues. Additional experiments on the MultiWOZ dataset show that our dataflow representation enables an otherwise off-the-shelf sequence-to-sequence model to match the best existing task-specific state tracking model. The SMCalFlow dataset, code for replicating experiments, and a public leaderboard are available at https://www.microsoft.com/en-us/research/project/dataflow-based-dialogue-semantic-machines.

pdf
A Corpus for Large-Scale Phonetic Typology
Elizabeth Salesky | Eleanor Chodroff | Tiago Pimentel | Matthew Wiesner | Ryan Cotterell | Alan W Black | Jason Eisner
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

A major hurdle in data-driven research on typology is having sufficient data in many languages to draw meaningful conclusions. We present VoxClamantis v1.0, the first large-scale corpus for phonetic typology, with aligned segments and estimated phoneme-level labels in 690 readings spanning 635 languages, along with acoustic-phonetic measures of vowels and sibilants. Access to such data can greatly facilitate investigation of phonetic typology at a large scale and across many languages. However, it is non-trivial and computationally intensive to obtain such alignments for hundreds of languages, many of which have few to no resources presently available. We describe the methodology to create our corpus, discuss caveats with current methods and their impact on the utility of this data, and illustrate possible research directions through a series of case studies on the 48 highest-quality readings. Our corpus and scripts are publicly available for non-commercial use at https://voxclamantisproject.github.io.

2019

pdf
What Kind of Language Is Hard to Language-Model?
Sabrina J. Mielke | Ryan Cotterell | Kyle Gorman | Brian Roark | Jason Eisner
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

How language-agnostic are current state-of-the-art NLP tools? Are there some types of language that are easier to model with current methods? In prior work (Cotterell et al., 2018) we attempted to address this question for language modeling, and observed that recurrent neural network language models do not perform equally well over all the high-resource European languages found in the Europarl corpus. We speculated that inflectional morphology may be the primary culprit for the discrepancy. In this paper, we extend these earlier experiments to cover 69 languages from 13 language families using a multilingual Bible corpus. Methodologically, we introduce a new paired-sample multiplicative mixed-effects model to obtain language difficulty coefficients from at-least-pairwise parallel corpora. In other words, the model is aware of inter-sentence variation and can handle missing data. Exploiting this model, we show that “translationese” is not any easier to model than natively written language in a fair comparison. Trying to answer the question of what features difficult languages have in common, we try and fail to reproduce our earlier (Cotterell et al., 2018) observation about morphological complexity and instead reveal far simpler statistics of the data that seem to drive complexity in a much larger sample.

pdf
On the Complexity and Typology of Inflectional Morphological Systems
Ryan Cotterell | Christo Kirov | Mans Hulden | Jason Eisner
Transactions of the Association for Computational Linguistics, Volume 7

We quantify the linguistic complexity of different languages’ morphological systems. We verify that there is a statistically significant empirical trade-off between paradigm size and irregularity: A language’s inflectional paradigms may be either large in size or highly irregular, but never both. We define a new measure of paradigm irregularity based on the conditional entropy of the surface realization of a paradigm— how hard it is to jointly predict all the word forms in a paradigm from the lemma. We estimate irregularity by training a predictive model. Our measurements are taken on large morphological paradigms from 36 typologically diverse languages.

pdf
A Generative Model for Punctuation in Dependency Trees
Xiang Lisa Li | Dingquan Wang | Jason Eisner
Transactions of the Association for Computational Linguistics, Volume 7

Treebanks traditionally treat punctuation marks as ordinary words, but linguists have suggested that a tree’s “true” punctuation marks are not observed (Nunberg, 1990). These latent “underlying” marks serve to delimit or separate constituents in the syntax tree. When the tree’s yield is rendered as a written sentence, a string rewriting mechanism transduces the underlying marks into “surface” marks, which are part of the observed (surface) string but should not be regarded as part of the tree. We formalize this idea in a generative model of punctuation that admits efficient dynamic programming. We train it without observing the underlying marks, by locally maximizing the incomplete data likelihood (similarly to the EM algorithm). When we use the trained model to reconstruct the tree’s underlying punctuation, the results appear plausible across 5 languages, and in particular are consistent with Nunberg’s analysis of English. We show that our generative model can be used to beat baselines on punctuation restoration. Also, our reconstruction of a sentence’s underlying punctuation lets us appropriately render the surface punctuation (via our trained underlying-to-surface mechanism) when we syntactically transform the sentence.

pdf
Neural Finite-State Transducers: Beyond Rational Relations
Chu-Cheng Lin | Hao Zhu | Matthew R. Gormley | Jason Eisner
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

We introduce neural finite state transducers (NFSTs), a family of string transduction models defining joint and conditional probability distributions over pairs of strings. The probability of a string pair is obtained by marginalizing over all its accepting paths in a finite state transducer. In contrast to ordinary weighted FSTs, however, each path is scored using an arbitrary function such as a recurrent neural network, which breaks the usual conditional independence assumption (Markov property). NFSTs are more powerful than previous finite-state models with neural features (Rastogi et al., 2016.) We present training and inference algorithms for locally and globally normalized variants of NFSTs. In experiments on different transduction tasks, they compete favorably against seq2seq models while offering interpretable paths that correspond to hard monotonic alignments.

pdf
Contextualization of Morphological Inflection
Ekaterina Vylomova | Ryan Cotterell | Trevor Cohn | Timothy Baldwin | Jason Eisner
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

Critical to natural language generation is the production of correctly inflected text. In this paper, we isolate the task of predicting a fully inflected sentence from its partially lemmatized version. Unlike traditional morphological inflection or surface realization, our task input does not provide “gold” tags that specify what morphological features to realize on each lemmatized word; rather, such features must be inferred from sentential context. We develop a neural hybrid graphical model that explicitly reconstructs morphological features before predicting the inflected forms, and compare this to a system that directly predicts the inflected forms without relying on any morphological annotation. We experiment on several typologically diverse languages from the Universal Dependencies treebanks, showing the utility of incorporating linguistically-motivated latent variables into NLP models.

pdf
Specializing Word Embeddings (for Parsing) by Information Bottleneck
Xiang Lisa Li | Jason Eisner
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Pre-trained word embeddings like ELMo and BERT contain rich syntactic and semantic information, resulting in state-of-the-art performance on various tasks. We propose a very fast variational information bottleneck (VIB) method to nonlinearly compress these embeddings, keeping only the information that helps a discriminative parser. We compress each word embedding to either a discrete tag or a continuous vector. In the discrete version, our automatically compressed tags form an alternative tag set: we show experimentally that our tags capture most of the information in traditional POS tag annotations, but our tag sequences can be parsed more accurately at the same level of tag granularity. In the continuous version, we show experimentally that moderately compressing the word embeddings by our method yields a more accurate parser in 8 of 9 languages, unlike simple dimensionality reduction.

pdf
Spelling-Aware Construction of Macaronic Texts for Teaching Foreign-Language Vocabulary
Adithya Renduchintala | Philipp Koehn | Jason Eisner
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

We present a machine foreign-language teacher that modifies text in a student’s native language (L1) by replacing some word tokens with glosses in a foreign language (L2), in such a way that the student can acquire L2 vocabulary simply by reading the resulting macaronic text. The machine teacher uses no supervised data from human students. Instead, to guide the machine teacher’s choice of which words to replace, we equip a cloze language model with a training procedure that can incrementally learn representations for novel words, and use this model as a proxy for the word guessing and learning ability of real human students. We use Mechanical Turk to evaluate two variants of the student model: (i) one that generates a representation for a novel word using only surrounding context and (ii) an extension that also uses the spelling of the novel word.

pdf bib
Proceedings of the Workshop on Deep Learning and Formal Languages: Building Bridges
Jason Eisner | Matthias Gallé | Jeffrey Heinz | Ariadna Quattoni | Guillaume Rabusseau
Proceedings of the Workshop on Deep Learning and Formal Languages: Building Bridges

pdf
Simple Construction of Mixed-Language Texts for Vocabulary Learning
Adithya Renduchintala | Philipp Koehn | Jason Eisner
Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications

We present a machine foreign-language teacher that takes documents written in a student’s native language and detects situations where it can replace words with their foreign glosses such that new foreign vocabulary can be learned simply through reading the resulting mixed-language text. We show that it is possible to design such a machine teacher without any supervised data from (human) students. We accomplish this by modifying a cloze language model to incrementally learn new vocabulary items, and use this language model as a proxy for the word guessing and learning ability of real students. Our machine foreign-language teacher decides which subset of words to replace by consulting this language model. We evaluate three variants of our student proxy language models through a study on Amazon Mechanical Turk (MTurk). We find that MTurk “students” were able to guess the meanings of foreign words introduced by the machine teacher with high accuracy for both function words as well as content words in two out of the three models. In addition, we show that students are able to retain their knowledge about the foreign words after they finish reading the document.

2018

pdf bib
The CoNLLSIGMORPHON 2018 Shared Task: Universal Morphological Reinflection
Ryan Cotterell | Christo Kirov | John Sylak-Glassman | Géraldine Walther | Ekaterina Vylomova | Arya D. McCarthy | Katharina Kann | Sabrina J. Mielke | Garrett Nicolai | Miikka Silfverberg | David Yarowsky | Jason Eisner | Mans Hulden
Proceedings of the CoNLL–SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection

pdf
Surface Statistics of an Unknown Language Indicate How to Parse It
Dingquan Wang | Jason Eisner
Transactions of the Association for Computational Linguistics, Volume 6

We introduce a novel framework for delexicalized dependency parsing in a new language. We show that useful features of the target language can be extracted automatically from an unparsed corpus, which consists only of gold part-of-speech (POS) sequences. Providing these features to our neural parser enables it to parse sequences like those in the corpus. Strikingly, our system has no supervision in the target language. Rather, it is a multilingual system that is trained end-to-end on a variety of other languages, so it learns a feature extractor that works well. We show experimentally across multiple languages: (1) Features computed from the unparsed corpus improve parsing accuracy. (2) Including thousands of synthetic languages in the training yields further improvement. (3) Despite being computed from unparsed corpora, our learned task-specific features beat previous work’s interpretable typological features that require parsed corpora or expert categorization of the language. Our best method improved attachment scores on held-out test languages by an average of 5.6 percentage points over past work that does not inspect the unparsed data (McDonald et al., 2011), and by 20.7 points over past “grammar induction” work that does not use training languages (Naseem et al., 2010).

pdf
UniMorph 2.0: Universal Morphology
Christo Kirov | Ryan Cotterell | John Sylak-Glassman | Géraldine Walther | Ekaterina Vylomova | Patrick Xia | Manaal Faruqui | Sabrina J. Mielke | Arya McCarthy | Sandra Kübler | David Yarowsky | Jason Eisner | Mans Hulden
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

pdf
Synthetic Data Made to Order: The Case of Parsing
Dingquan Wang | Jason Eisner
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

To approximately parse an unfamiliar language, it helps to have a treebank of a similar language. But what if the closest available treebank still has the wrong word order? We show how to (stochastically) permute the constituents of an existing dependency treebank so that its surface part-of-speech statistics approximately match those of the target language. The parameters of the permutation model can be evaluated for quality by dynamic programming and tuned by gradient descent (up to a local optimum). This optimization procedure yields trees for a new artificial language that resembles the target language. We show that delexicalized parsers for the target language can be successfully trained using such “made to order” artificial languages.

pdf
A Deep Generative Model of Vowel Formant Typology
Ryan Cotterell | Jason Eisner
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)

What makes some types of languages more probable than others? For instance, we know that almost all spoken languages contain the vowel phoneme /i/; why should that be? The field of linguistic typology seeks to answer these questions and, thereby, divine the mechanisms that underlie human language. In our work, we tackle the problem of vowel system typology, i.e., we propose a generative probability model of which vowels a language contains. In contrast to previous work, we work directly with the acoustic information—the first two formant values—rather than modeling discrete sets of symbols from the international phonetic alphabet. We develop a novel generative probability model and report results on over 200 languages.

pdf
Neural Particle Smoothing for Sampling from Conditional Sequence Models
Chu-Cheng Lin | Jason Eisner
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)

We introduce neural particle smoothing, a sequential Monte Carlo method for sampling annotations of an input string from a given probability model. In contrast to conventional particle filtering algorithms, we train a proposal distribution that looks ahead to the end of the input string by means of a right-to-left LSTM. We demonstrate that this innovation can improve the quality of the sample. To motivate our formal choices, we explain how neural transduction models and our sampler can be viewed as low-dimensional but nonlinear approximations to working with HMMs over very large state spaces.

pdf
Are All Languages Equally Hard to Language-Model?
Ryan Cotterell | Sabrina J. Mielke | Jason Eisner | Brian Roark
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)

For general modeling methods applied to diverse languages, a natural question is: how well should we expect our models to work on languages with differing typological profiles? In this work, we develop an evaluation framework for fair cross-linguistic comparison of language models, using translated text so that all models are asked to predict approximately the same information. We then conduct a study on 21 languages, demonstrating that in some languages, the textual expression of the information is harder to predict with both n-gram and LSTM language models. We show complex inflectional morphology to be a cause of performance differences among languages.

pdf
Unsupervised Disambiguation of Syncretism in Inflected Lexicons
Ryan Cotterell | Christo Kirov | Sabrina J. Mielke | Jason Eisner
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)

Lexical ambiguity makes it difficult to compute useful statistics of a corpus. A given word form might represent any of several morphological feature bundles. One can, however, use unsupervised learning (as in EM) to fit a model that probabilistically disambiguates word forms. We present such an approach, which employs a neural network to smoothly model a prior distribution over feature bundles (even rare ones). Although this basic model does not consider a token’s context, that very property allows it to operate on a simple list of unigram type counts, partitioning each count among different analyses of that unigram. We discuss evaluation metrics for this novel task and report results on 5 languages.

2017

pdf
Bayesian Modeling of Lexical Resources for Low-Resource Settings
Nicholas Andrews | Mark Dredze | Benjamin Van Durme | Jason Eisner
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Lexical resources such as dictionaries and gazetteers are often used as auxiliary data for tasks such as part-of-speech induction and named-entity recognition. However, discriminative training with lexical features requires annotated data to reliably estimate the lexical feature weights and may result in overfitting the lexical features at the expense of features which generalize better. In this paper, we investigate a more robust approach: we stipulate that the lexicon is the result of an assumed generative process. Practically, this means that we may treat the lexical resources as observations under the proposed generative model. The lexical resources provide training data for the generative model without requiring separate data to estimate lexical feature weights. We evaluate the proposed approach in two settings: part-of-speech induction and low-resource named-entity recognition.

pdf
Probabilistic Typology: Deep Generative Models of Vowel Inventories
Ryan Cotterell | Jason Eisner
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Linguistic typology studies the range of structures present in human language. The main goal of the field is to discover which sets of possible phenomena are universal, and which are merely frequent. For example, all languages have vowels, while most—but not all—languages have an /u/ sound. In this paper we present the first probabilistic treatment of a basic question in phonological typology: What makes a natural vowel inventory? We introduce a series of deep stochastic point processes, and contrast them with previous computational, simulation-based approaches. We provide a comprehensive suite of experiments on over 200 distinct languages.

pdf
Knowledge Tracing in Sequential Learning of Inflected Vocabulary
Adithya Renduchintala | Philipp Koehn | Jason Eisner
Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)

We present a feature-rich knowledge tracing method that captures a student’s acquisition and retention of knowledge during a foreign language phrase learning task. We model the student’s behavior as making predictions under a log-linear model, and adopt a neural gating mechanism to model how the student updates their log-linear parameters in response to feedback. The gating mechanism allows the model to learn complex patterns of retention and acquisition for each feature, while the log-linear parameterization results in an interpretable knowledge state. We collect human data and evaluate several versions of the model.

pdf bib
CoNLL-SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection in 52 Languages
Ryan Cotterell | Christo Kirov | John Sylak-Glassman | Géraldine Walther | Ekaterina Vylomova | Patrick Xia | Manaal Faruqui | Sandra Kübler | David Yarowsky | Jason Eisner | Mans Hulden
Proceedings of the CoNLL SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection

pdf
Explaining and Generalizing Skip-Gram through Exponential Family Principal Component Analysis
Ryan Cotterell | Adam Poliak | Benjamin Van Durme | Jason Eisner
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers

The popular skip-gram model induces word embeddings by exploiting the signal from word-context coocurrence. We offer a new interpretation of skip-gram based on exponential family PCA-a form of matrix factorization to generalize the skip-gram model to tensor factorization. In turn, this lets us train embeddings through richer higher-order coocurrences, e.g., triples that include positional information (to incorporate syntax) or morphological information (to share parameters across related words). We experiment on 40 languages and show our model improves upon skip-gram.

pdf
Fine-Grained Prediction of Syntactic Typology: Discovering Latent Structure with Supervised Learning
Dingquan Wang | Jason Eisner
Transactions of the Association for Computational Linguistics, Volume 5

We show how to predict the basic word-order facts of a novel language given only a corpus of part-of-speech (POS) sequences. We predict how often direct objects follow their verbs, how often adjectives follow their nouns, and in general the directionalities of all dependency relations. Such typological properties could be helpful in grammar induction. While such a problem is usually regarded as unsupervised learning, our innovation is to treat it as supervised learning, using a large collection of realistic synthetic languages as training data. The supervised learner must identify surface features of a language’s POS sequence (hand-engineered or neural features) that correlate with the language’s deeper structure (latent trees). In the experiment, we show: 1) Given a small set of real languages, it helps to add many synthetic languages to the training data. 2) Our system is robust even when the POS sequences include noise. 3) Our system on this task outperforms a grammar induction baseline by a large margin.

pdf
Learning to Prune: Exploring the Frontier of Fast and Accurate Parsing
Tim Vieira | Jason Eisner
Transactions of the Association for Computational Linguistics, Volume 5

Pruning hypotheses during dynamic programming is commonly used to speed up inference in settings such as parsing. Unlike prior work, we train a pruning policy under an objective that measures end-to-end performance: we search for a fast and accurate policy. This poses a difficult machine learning problem, which we tackle with the lols algorithm. lols training must continually compute the effects of changing pruning decisions: we show how to make this efficient in the constituency parsing setting, via dynamic programming and change propagation algorithms. We find that optimizing end-to-end performance in this way leads to a better Pareto frontier—i.e., parsers which are more accurate for a given runtime.

2016

pdf
The Galactic Dependencies Treebanks: Getting More Data by Synthesizing New Languages
Dingquan Wang | Jason Eisner
Transactions of the Association for Computational Linguistics, Volume 4

We release Galactic Dependencies 1.0—a large set of synthetic languages not found on Earth, but annotated in Universal Dependencies format. This new resource aims to provide training and development data for NLP methods that aim to adapt to unfamiliar languages. Each synthetic treebank is produced from a real treebank by stochastically permuting the dependents of nouns and/or verbs to match the word order of other real languages. We discuss the usefulness, realism, parsability, perplexity, and diversity of the synthetic languages. As a simple demonstration of the use of Galactic Dependencies, we consider single-source transfer, which attempts to parse a real target language using a parser trained on a “nearby” source language. We find that including synthetic source languages somewhat increases the diversity of the source pool, which significantly improves results for most target languages.

pdf
Analyzing Learner Understanding of Novel L2 Vocabulary
Rebecca Knowles | Adithya Renduchintala | Philipp Koehn | Jason Eisner
Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning

pdf bib
The SIGMORPHON 2016 Shared Task—Morphological Reinflection
Ryan Cotterell | Christo Kirov | John Sylak-Glassman | David Yarowsky | Jason Eisner | Mans Hulden
Proceedings of the 14th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology

pdf bib
Inside-Outside and Forward-Backward Algorithms Are Just Backprop (tutorial paper)
Jason Eisner
Proceedings of the Workshop on Structured Prediction for NLP

pdf
Weighting Finite-State Transductions With Neural Context
Pushpendre Rastogi | Ryan Cotterell | Jason Eisner
Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

pdf
Morphological Smoothing and Extrapolation of Word Embeddings
Ryan Cotterell | Hinrich Schütze | Jason Eisner
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf
User Modeling in Language Learning with Macaronic Texts
Adithya Renduchintala | Rebecca Knowles | Philipp Koehn | Jason Eisner
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf
Creating Interactive Macaronic Interfaces for Language Learning
Adithya Renduchintala | Rebecca Knowles | Philipp Koehn | Jason Eisner
Proceedings of ACL-2016 System Demonstrations

pdf
Speed-Accuracy Tradeoffs in Tagging with Variable-Order CRFs and Structured Sparsity
Tim Vieira | Ryan Cotterell | Jason Eisner
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

2015

pdf
Dual Decomposition Inference for Graphical Models over Strings
Nanyun Peng | Ryan Cotterell | Jason Eisner
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

pdf bib
Structured Belief Propagation for NLP
Matthew R. Gormley | Jason Eisner
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing: Tutorial Abstracts

pdf
Modeling Word Forms Using Latent Underlying Morphs and Phonology
Ryan Cotterell | Nanyun Peng | Jason Eisner
Transactions of the Association for Computational Linguistics, Volume 3

The observed pronunciations or spellings of words are often explained as arising from the “underlying forms” of their morphemes. These forms are latent strings that linguists try to reconstruct by hand. We propose to reconstruct them automatically at scale, enabling generalization to new words. Given some surface word types of a concatenative language along with the abstract morpheme sequences that they express, we show how to recover consistent underlying forms for these morphemes, together with the (stochastic) phonology that maps each concatenation of underlying forms to a surface form. Our technique involves loopy belief propagation in a natural directed graphical model whose variables are unknown strings and whose conditional distributions are encoded as finite-state machines with trainable weights. We define training and evaluation paradigms for the task of surface word prediction, and report results on subsets of 7 languages.

pdf
Approximation-Aware Dependency Parsing by Belief Propagation
Matthew R. Gormley | Mark Dredze | Jason Eisner
Transactions of the Association for Computational Linguistics, Volume 3

We show how to train the fast dependency parser of Smith and Eisner (2008) for improved accuracy. This parser can consider higher-order interactions among edges while retaining O(n3) runtime. It outputs the parse with maximum expected recall—but for speed, this expectation is taken under a posterior distribution that is constructed only approximately, using loopy belief propagation through structured factors. We show how to adjust the model parameters to compensate for the errors introduced by this approximation, by following the gradient of the actual loss on training data. We find this gradient by back-propagation. That is, we treat the entire parser (approximations and all) as a differentiable circuit, as others have done for loopy CRFs (Domke, 2010; Stoyanov et al., 2011; Domke, 2011; Stoyanov and Eisner, 2012). The resulting parser obtains higher accuracy with fewer iterations of belief propagation than one trained by conditional log-likelihood.

pdf
Penalized Expectation Propagation for Graphical Models over Strings
Ryan Cotterell | Jason Eisner
Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

2014

pdf
Robust Entity Clustering via Phylogenetic Inference
Nicholas Andrews | Jason Eisner | Mark Dredze
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf
Stochastic Contextual Edit Distance and Probabilistic FSTs
Ryan Cotterell | Nanyun Peng | Jason Eisner
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

pdf
Structured Belief Propagation for NLP
Matthew Gormley | Jason Eisner
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics: Tutorials

2013

pdf
Dynamic Feature Selection for Dependency Parsing
He He | Hal Daumé III | Jason Eisner
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing

pdf
Introducing Computational Concepts in a Linguistics Olympiad
Patrick Littell | Lori Levin | Jason Eisner | Dragomir Radev
Proceedings of the Fourth Workshop on Teaching NLP and CL

pdf
A Virtual Manipulative for Learning Log-Linear Models
Francis Ferraro | Jason Eisner
Proceedings of the Fourth Workshop on Teaching NLP and CL

pdf
Nonconvex Global Optimization for Latent-Variable Models
Matthew R. Gormley | Jason Eisner
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

2012

pdf
Minimum-Risk Training of Approximate CRF-Based NLP Systems
Veselin Stoyanov | Jason Eisner
Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

pdf
Unsupervised Learning on an Approximate Corpus
Jason Smith | Jason Eisner
Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

pdf
Implicitly Intersecting Weighted Automata using Dual Decomposition
Michael J. Paul | Jason Eisner
Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

pdf
Shared Components Topic Models
Matthew R. Gormley | Mark Dredze | Benjamin Van Durme | Jason Eisner
Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

pdf
Easy-first Coreference Resolution
Veselin Stoyanov | Jason Eisner
Proceedings of COLING 2012

pdf
Name Phylogeny: A Generative Model of String Variation
Nicholas Andrews | Jason Eisner | Mark Dredze
Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning

2011

pdf
Discovering Morphological Paradigms from Plain Text Using a Dirichlet Process Mixture Model
Markus Dreyer | Jason Eisner
Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing

pdf
Minimum Imputed-Risk: Unsupervised Discriminative Training for Machine Translation
Zhifei Li | Ziyuan Wang | Jason Eisner | Sanjeev Khudanpur | Brian Roark
Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing

2010

pdf
Unsupervised Discriminative Language Model Training for Machine Translation using Simulated Confusion Sets
Zhifei Li | Ziyuan Wang | Sanjeev Khudanpur | Jason Eisner
Coling 2010: Posters

2009

pdf
First- and Second-Order Expectation Semirings with Applications to Minimum-Risk Training on Translation Forests
Zhifei Li | Jason Eisner
Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing

pdf
Graphical Models over Multiple Strings
Markus Dreyer | Jason Eisner
Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing

pdf
Parser Adaptation and Projection with Quasi-Synchronous Grammar Features
David A. Smith | Jason Eisner
Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing

pdf
Learning Linear Ordering Problems for Better Translation
Roy Tromble | Jason Eisner
Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing

pdf
Variational Decoding for Statistical Machine Translation
Zhifei Li | Jason Eisner | Sanjeev Khudanpur
Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP

2008

pdf
Modeling Annotators: A Generative Approach to Learning from Annotator Rationales
Omar Zaidan | Jason Eisner
Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing

pdf
Dependency Parsing by Belief Propagation
David Smith | Jason Eisner
Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing

pdf
Latent-Variable Modeling of String Transductions with Finite-State Methods
Markus Dreyer | Jason Smith | Jason Eisner
Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing

pdf
Machine Translation System Combination using ITG-based Alignments
Damianos Karakos | Jason Eisner | Sanjeev Khudanpur | Markus Dreyer
Proceedings of ACL-08: HLT, Short Papers

pdf
Competitive Grammar Writing
Jason Eisner | Noah A. Smith
Proceedings of the Third Workshop on Issues in Teaching Computational Linguistics

pdf bib
Proceedings of the Tenth Meeting of ACL Special Interest Group on Computational Morphology and Phonology
Jason Eisner | Jeffrey Heinz
Proceedings of the Tenth Meeting of ACL Special Interest Group on Computational Morphology and Phonology

2007

pdf bib
Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)
Jason Eisner
Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)

pdf
Bootstrapping Feature-Rich Dependency Parsers with Entropic Priors
David A. Smith | Jason Eisner
Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)

pdf
Cross-Instance Tuning of Unsupervised Document Clustering Algorithms
Damianos Karakos | Jason Eisner | Sanjeev Khudanpur | Carey Priebe
Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Proceedings of the Main Conference

pdf
Using “Annotator Rationales” to Improve Machine Learning for Text Categorization
Omar Zaidan | Jason Eisner | Christine Piatko
Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Proceedings of the Main Conference

2006

pdf
A fast finite-state relaxation method for enforcing global constraints on sequence decoding
Roy Tromble | Jason Eisner
Proceedings of the Human Language Technology Conference of the NAACL, Main Conference

pdf
Annealing Structural Bias in Multilingual Weighted Grammar Induction
Noah A. Smith | Jason Eisner
Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics

pdf
Minimum Risk Annealing for Training Log-Linear Models
David A. Smith | Jason Eisner
Proceedings of the COLING/ACL 2006 Main Conference Poster Sessions

pdf
Better Informed Training of Latent Syntactic Features
Markus Dreyer | Jason Eisner
Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing

pdf
Quasi-Synchronous Grammars: Alignment by Soft Projection of Syntactic Dependencies
David Smith | Jason Eisner
Proceedings on the Workshop on Statistical Machine Translation

2005

pdf
Parsing with Soft and Hard Constraints on Dependency Length
Jason Eisner | Noah A. Smith
Proceedings of the Ninth International Workshop on Parsing Technology

pdf
Compiling Comp Ling: Weighted Dynamic Programming and the Dyna Language
Jason Eisner | Eric Goldlust | Noah A. Smith
Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing

pdf
Bootstrapping Without the Boot
Jason Eisner | Damianos Karakos
Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing

pdf
Contrastive Estimation: Training Log-Linear Models on Unlabeled Data
Noah A. Smith | Jason Eisner
Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL’05)

2004

pdf
Annealing Techniques For Unsupervised Statistical Language Learning
Noah A. Smith | Jason Eisner
Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL-04)

pdf
Dyna: A Language for Weighted Dynamic Programming
Jason Eisner | Eric Goldlust | Noah A. Smith
Proceedings of the ACL Interactive Poster and Demonstration Sessions

2003

pdf
Learning Non-Isomorphic Tree Mappings for Machine Translation
Jason Eisner
The Companion Volume to the Proceedings of 41st Annual Meeting of the Association for Computational Linguistics

pdf
Simpler and More General Minimization for Weighted Finite-State Automata
Jason Eisner
Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics

2002

pdf bib
Parameter Estimation for Probabilistic Finite-State Transducers
Jason Eisner
Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics

pdf
Phonological Comprehension and the Compilation of Optimality Theory
Jason Eisner
Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics

pdf bib
An Interactive Spreadsheet for Teaching the Forward-Backward Algorithm
Jason Eisner
Proceedings of the ACL-02 Workshop on Effective Tools and Methodologies for Teaching Natural Language Processing and Computational Linguistics

pdf
Transformational Priors Over Grammars
Jason Eisner
Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing (EMNLP 2002)

2000

pdf bib
Proceedings of the Fifth Workshop of the ACL Special Interest Group in Computational Phonology
Jason Eisner | Lauri Karttunen | Alain Thèriault
Proceedings of the Fifth Workshop of the ACL Special Interest Group in Computational Phonology

pdf
Easy and Hard Constraint Ranking in OT: Algorithms and Complexity
Jason Eisner
Proceedings of the Fifth Workshop of the ACL Special Interest Group in Computational Phonology

pdf
A faster parsing algorithm for Lexicalized Tree-Adjoining Grammars
Jason Eisner | Giorgio Satta
Proceedings of the Fifth International Workshop on Tree Adjoining Grammar and Related Frameworks (TAG+5)

pdf
Directional Constraint Evaluation in Optimality Theory
Jason Eisner
COLING 2000 Volume 1: The 18th International Conference on Computational Linguistics

pdf
Book Reviews: Optimality Theory
Jason Eisner
Computational Linguistics, Volume 26, Number 2, June 2000

1999

pdf
Efficient Parsing for Bilexical Context-Free Grammars and Head Automaton Grammars
Jason Eisner | Giorgio Satta
Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics

1997

pdf
Bilexical Grammars and a Cubic-time Probabilistic Parser
Jason Eisner
Proceedings of the Fifth International Workshop on Parsing Technologies

pdf
Efficient Generation in Primitive Optimality Theory
Jason Eisner
35th Annual Meeting of the Association for Computational Linguistics and 8th Conference of the European Chapter of the Association for Computational Linguistics

1996

pdf
Efficient Normal-Form Parsing for Combinatory Categorial Grammar
Jason Eisner
34th Annual Meeting of the Association for Computational Linguistics

pdf
Three New Probabilistic Models for Dependency Parsing: An Exploration
Jason M. Eisner
COLING 1996 Volume 1: The 16th International Conference on Computational Linguistics

1995

pdf
University of Pennsylvania: Description of the University of Pennsylvania System Used for MUC-6
Breck Baldwin | Jeff Reynar | Mike Collins | Jason Eisner | Adwait Ratnaparkhi | Joseph Rosenzweig | Anoop Sarkar | Srinivas
Sixth Message Understanding Conference (MUC-6): Proceedings of a Conference Held in Columbia, Maryland, November 6-8, 1995

Search
Co-authors