Existing grammatical error correction tools do not provide natural language explanations of the errors that they correct in user-written text. However, such explanations are essential for helping users learn the language by gaining a deeper understanding of its grammatical rules (DeKeyser, 2003; Ellis et al., 2006).To address this gap, we propose the task of grammar error explanation, where a system needs to provide one-sentence explanations for each grammatical error in a pair of erroneous and corrected sentences. The task is not easily solved by prompting LLMs: we find that, using one-shot prompting, GPT-4 only explains 40.6% of the errors and does not even attempt to explain 39.8% of the errors.Since LLMs struggle to identify grammar errors, we develop a two-step pipeline that leverages fine-tuned and prompted large language models to perform structured atomic token edit extraction, followed by prompting GPT-4 to explain each edit. We evaluate our pipeline on German, Chinese, and English grammar error correction data. Our atomic edit extraction achieves an F1 of 0.93 on German, 0.91 on Chinese, and 0.891 on English. Human evaluation of generated explanations reveals that 93.9% of German errors, 96.4% of Chinese errors, and 92.20% of English errors are correctly detected and explained. To encourage further research, we open-source our data and code.

We present the structured average intersection-over-union ratio (STRUCT-IOU), an evaluation metric that compares a constituency parse tree over automatically recognized spoken word boundaries with the ground-truth parse tree over written words. To compute the metric, we (1) project the ground-truth parse tree to the speech domain by forced alignment, (2) align the projected ground-truth constituents with the predicted ones under certain structured constraints, and (3) calculate the average IOU score across all aligned constituent pairs. STRUCT-IOU takes word boundaries into account and overcomes the challenge that the predicted words and ground truth may not have perfect one-to-one correspondence. Extending to the evaluation of text constituency parsing, we demonstrate that STRUCT-IOU shows higher tolerance to syntactically plausible parses than PARSEVAL (Black et al., 1991).

It has been widely observed that exact or approximate MAP (mode-seeking) decoding from natural language generation (NLG) models consistently leads to degenerate outputs (Holtzman et al., 2019; Stahlberg and Byrne, 2019). Prior work has attributed this behavior to either a fundamental and unavoidable inadequacy of modes in probabilistic models or weaknesses in language modeling. Contrastingly, we argue that degenerate modes can even occur in the absence of any modeling error, due to contamination of the training data. Specifically, we argue that mixing even a tiny amount of low-entropy noise with a population text distribution can cause the data distribution’s mode to become degenerate. We therefore propose to apply MAP decoding to the model’s true conditional distribution where the conditioning variable explicitly avoids specific degenerate behavior. Using exact search, we empirically verify that the length-conditional modes of machine translation models and language models are indeed more fluent and topical than their unconditional modes. For the first time, we also share many examples of exact modal sequences from these models, and from several variants of the LLaMA-7B model. Notably, we observethat various kinds of degenerate modes persist, even at the scale of LLaMA-7B. Although we cannot tractably address these degeneracieswith exact search, we perform a classifier-based approximate search on LLaMA-7B, a model which was not trained for instruction following, and find that we are able to elicit reasonable outputs without any finetuning.

Pretrained language models have improved zero-shot text classification by allowing the transfer of semantic knowledge from the training data in order to classify among specific label sets in downstream tasks. We propose a simple way to further improve zero-shot accuracies with minimal effort. We curate small finetuning datasets intended to describe the labels for a task. Unlike typical finetuning data, which has texts annotated with labels, our data simply describes the labels in language, e.g., using a few related terms, dictionary/encyclopedia entries, and short templates. Across a range of topic and sentiment datasets, our method is more accurate than zero-shot by 17-19% absolute. It is also more robust to choices required for zero-shot classification, such as patterns for prompting the model to classify and mappings from labels to tokens in the model’s vocabulary. Furthermore, since our data merely describes the labels but does not use input texts, finetuning on it yields a model that performs strongly on multiple text domains for a given label set, even improving over few-shot out-of-domain classification in multiple settings.

We present substructure distribution projection (SubDP), a technique that projects a distribution over structures in one domain to another, by projecting substructure distributions separately. Models for the target domain can then be trained, using the projected distributions as soft silver labels. We evaluate SubDP on zero shot cross-lingual dependency parsing, taking dependency arcs as substructures: we project the predicted dependency arc distributions in the source language(s) to target language(s), and train a target language parser on the resulting distributions. Given an English tree bank as the only source of human supervision, SubDP achieves better unlabeled attachment score than all prior work on the Universal Dependencies v2.2 (Nivre et al., 2020) test set across eight diverse target languages, as well as the best labeled attachment score on six languages. In addition, SubDP improves zero shot cross-lingual dependency parsing with very few (e.g., 50) supervised bitext pairs, across a broader range of target languages.

We introduce SummScreen, a summarization dataset comprised of pairs of TV series transcripts and human written recaps. The dataset provides a challenging testbed for abstractive summarization for several reasons. Plot details are often expressed indirectly in character dialogues and may be scattered across the entirety of the transcript. These details must be found and integrated to form the succinct plot descriptions in the recaps. Also, TV scripts contain content that does not directly pertain to the central plot but rather serves to develop characters or provide comic relief. This information is rarely contained in recaps. Since characters are fundamental to TV series, we also propose two entity-centric evaluation metrics. Empirically, we characterize the dataset by evaluating several methods, including neural models and those based on nearest neighbors. An oracle extractive approach outperforms all benchmarked models according to automatic metrics, showing that the neural models are unable to fully exploit the input transcripts. Human evaluation and qualitative analysis reveal that our non-oracle models are competitive with their oracle counterparts in terms of generating faithful plot events and can benefit from better content selectors. Both oracle and non-oracle models generate unfaithful facts, suggesting future research directions.

We present a system that allows users to train their own state-of-the-art paraphrastic sentence representations in a variety of languages. We release trained models for English, Arabic, German, Spanish, French, Russian, Turkish, and Chinese. We train these models on large amounts of data, achieving significantly improved performance from our original papers on a suite of monolingual semantic similarity, cross-lingual semantic similarity, and bitext mining tasks. Moreover, the resulting models surpass all prior work on efficient unsupervised semantic textual similarity, even significantly outperforming supervised BERT-based models like Sentence-BERT (Reimers and Gurevych, 2019). Most importantly, our models are orders of magnitude faster than other strong similarity models and can be used on CPU with little difference in inference speed (even improved speed over GPU when using more CPU cores), making these models an attractive choice for users without access to GPUs or for use on embedded devices. Finally, we add significantly increased functionality to the code bases for training paraphrastic sentence models, easing their use for both inference and for training them for any desired language with parallel data. We also include code to automatically download and preprocess training data.

Neural language models have been analyzed for their linguistic and extra-linguistic knowledge via probing. Of particular interest has been the following question: how much can a language model trained only on form learn about meaning? Recent work has demonstrated via probing classifiers that in the setting of simple procedural text, where by “meaning” we mean the underlying world state, language models have a non-trivial performance on world state tracking. However, our proposed evaluation based on model predictions shows differing results, suggesting that these models are either not capturing the world state or not using it. How do these results change if the model has access to the world state? We explore this alternate setting with access to the underlying world state only during training and investigate ways of “baking in” the state knowledge along with the primary task of language modeling. Our proposed approaches allow for state probing during inference simply via text prompts, avoiding any probing classifier machinery. In terms of performance, we show that baking in the state knowledge during training leads to significant improvements in state tracking performance and text generation quality,

We propose a type-controlled framework for inquisitive question generation. We annotate an inquisitive question dataset with question types, train question type classifiers, and finetune models for type-controlled question generation. Empirical results demonstrate that we can generate a variety of questions that adhere to specific types while drawing from the source texts. We also investigate strategies for selecting a single question from a generated set, considering both an informative vs. inquisitive question classifier and a pairwise ranker trained from a small set of expert annotations. Question selection using the pairwise ranker yields strong results in automatic and manual evaluation. Our human evaluation assesses multiple aspects of the generated questions, finding that the ranker chooses questions with the best syntax (4.59), semantics (4.37), and inquisitiveness (3.92) on a scale of 1-5, even rivaling the performance of human-written questions.

Variational autoencoders (VAEs) are widely used for latent variable modeling of text. We focus on variations that learn expressive prior distributions over the latent variable. We find that existing training strategies are not effective for learning rich priors, so we propose adding the importance-sampled log marginal likelihood as a second term to the standard VAE objective to help when learning the prior. Doing so improves results for all priors evaluated, including a novel choice for sentence VAEs based on normalizing flows (NF). Priors parameterized with NF are no longer constrained to a specific distribution family, allowing a more flexible way to encode the data distribution. Our model, which we call FlowPrior, shows a substantial improvement in language modeling tasks compared to strong baselines. We demonstrate that FlowPrior learns an expressive prior with analysis and several forms of evaluation involving generation.

While coreference resolution is defined independently of dataset domain, most models for performing coreference resolution do not transfer well to unseen domains. We consolidate a set of 8 coreference resolution datasets targeting different domains to evaluate the off-the-shelf performance of models. We then mix three datasets for training; even though their domain, annotation guidelines, and metadata differ, we propose a method for jointly training a single model on this heterogeneous data mixture by using data augmentation to account for annotation differences and sampling to balance the data quantities. We find that in a zero-shot setting, models trained on a single dataset transfer poorly while joint training yields improved overall performance, leading to better generalization in coreference resolution models. This work contributes a new benchmark for robust coreference resolution and multiple new state-of-the-art results.

We present Hidden-State Optimization (HSO), a gradient-based method for improving the performance of transformer language models at inference time. Similar to dynamic evaluation (Krause et al., 2018), HSO computes the gradient of the log-probability the language model assigns to an evaluation text, but uses it to update the cached hidden states rather than the model parameters. We test HSO with pretrained Transformer-XL and GPT-2 language models, finding improvement on the WikiText-103 and PG-19 datasets in terms of perplexity, especially when evaluating a model outside of its training distribution. We also demonstrate downstream applicability by showing gains in the recently developed prompt-based few-shot evaluation setting, again with no extra parameters or training data.

Probabilistic word embeddings have shown effectiveness in capturing notions of generality and entailment, but there is very little work on doing the analogous type of investigation for sentences. In this paper we define probabilistic models that produce distributions for sentences. Our best-performing model treats each word as a linear transformation operator applied to a multivariate Gaussian distribution. We train our models on paraphrases and demonstrate that they naturally capture sentence specificity. While our proposed model achieves the best performance overall, we also show that specificity is represented by simpler architectures via the norm of the sentence vectors. Qualitative analysis shows that our probabilistic model captures sentential entailment and provides ways to analyze the specificity and preciseness of individual words.

Many natural language processing (NLP) tasks involve reasoning with textual spans, including question answering, entity recognition, and coreference resolution. While extensive research has focused on functional architectures for representing words and sentences, there is less work on representing arbitrary spans of text within sentences. In this paper, we conduct a comprehensive empirical evaluation of six span representation methods using eight pretrained language representation models across six tasks, including two tasks that we introduce. We find that, although some simple span representations are fairly reliable across tasks, in general the optimal span representation varies by task, and can also vary within different facets of individual tasks. We also find that the choice of span representation has a bigger impact with a fixed pretrained encoder than with a fine-tuned encoder.

We consider the problem of automatically suggesting distractors for multiple-choice cloze questions designed for second-language learners. We describe the creation of a dataset including collecting manual annotations for distractor selection. We assess the relationship between the choices of the annotators and features based on distractors and the correct answers, both with and without the surrounding passage context in the cloze questions. Simple features of the distractor and correct answer correlate with the annotations, though we find substantial benefit to additionally using large-scale pretrained models to measure the fit of the distractor in the context. Based on these analyses, we propose and train models to automatically select distractors, and measure the importance of model components quantitatively.

We propose to train a non-autoregressive machine translation model to minimize the energy defined by a pretrained autoregressive model. In particular, we view our non-autoregressive translation system as an inference network (Tu and Gimpel, 2018) trained to minimize the autoregressive teacher energy. This contrasts with the popular approach of training a non-autoregressive model on a distilled corpus consisting of the beam-searched outputs of such a teacher model. Our approach, which we call ENGINE (ENerGy-based Inference NEtworks), achieves state-of-the-art non-autoregressive results on the IWSLT 2014 DE-EN and WMT 2016 RO-EN datasets, approaching the performance of autoregressive models.

We propose PeTra, a memory-augmented neural network designed to track entities in its memory slots. PeTra is trained using sparse annotation from the GAP pronoun resolution dataset and outperforms a prior memory model on the task while using a simpler architecture. We empirically compare key modeling choices, finding that we can simplify several aspects of the design of the memory module while retaining strong performance. To measure the people tracking capability of memory models, we (a) propose a new diagnostic evaluation based on counting the number of unique entities in text, and (b) conduct a small scale human evaluation to compare evidence of people tracking in the memory logs of PeTra relative to a previous approach. PeTra is highly effective in both evaluations, demonstrating its ability to track people in its memory despite being trained with limited annotation.

Deep energy-based models are powerful, but pose challenges for learning and inference (Belanger and McCallum, 2016). Tu and Gimpel (2018) developed an efficient framework for energy-based models by training “inference networks” to approximate structured inference instead of using gradient descent. However, their alternating optimization approach suffers from instabilities during training, requiring additional loss terms and careful hyperparameter tuning. In this paper, we contribute several strategies to stabilize and improve this joint training of energy functions and inference networks for structured prediction. We design a compound objective to jointly train both cost-augmented and test-time inference networks along with the energy function. We propose joint parameterizations for the inference networks that encourage them to capture complementary functionality during learning. We empirically validate our strategies on two sequence labeling tasks, showing easier paths to strong performance than prior work, as well as further improvements with global energy terms.

Accurate lexical entailment (LE) and natural language inference (NLI) often require large quantities of costly annotations. To alleviate the need for labeled data, we introduce WikiNLI: a resource for improving model performance on NLI and LE tasks. It contains 428,899 pairs of phrases constructed from naturally annotated category hierarchies in Wikipedia. We show that we can improve strong baselines such as BERT and RoBERTa by pretraining them on WikiNLI and transferring the models on downstream tasks. We conduct systematic comparisons with phrases extracted from other knowledge bases such as WordNet and Wikidata to find that pretraining on WikiNLI gives the best performance. In addition, we construct WikiNLI in other languages, and show that pretraining on them improves performance on NLI tasks of corresponding languages.

Many tasks in natural language processing involve predicting structured outputs, e.g., sequence labeling, semantic role labeling, parsing, and machine translation. Researchers are increasingly applying deep representation learning to these problems, but the structured component of these approaches is usually quite simplistic. In this work, we propose several high-order energy terms to capture complex dependencies among labels in sequence labeling, including several that consider the entire label sequence. We use neural parameterizations for these energy terms, drawing from convolutional, recurrent, and self-attention networks. We use the framework of learning energy-based inference networks (Tu and Gimpel, 2018) for dealing with the difficulties of training and inference with such models. We empirically demonstrate that this approach achieves substantial improvement using a variety of high-order energy terms on four sequence labeling tasks, while having the same decoding speed as simple, local classifiers. We also find high-order energies to help in noisy data conditions.

We analyze several recent unsupervised constituency parsing models, which are tuned with respect to the parsing F1 score on the Wall Street Journal (WSJ) development set (1,700 sentences). We introduce strong baselines for them, by training an existing supervised parsing model (Kitaev and Klein, 2018) on the same labeled examples they access. When training on the 1,700 examples, or even when using only 50 examples for training and 5 for development, such a few-shot parsing approach can outperform all the unsupervised parsing methods by a significant margin. Few-shot parsing can be further improved by a simple data augmentation method and self-training. This suggests that, in order to arrive at fair conclusions, we should carefully consider the amount of labeled data used for model development. We propose two protocols for future work on unsupervised parsing: (i) use fully unsupervised criteria for hyperparameter tuning and model selection; (ii) use as few labeled examples as possible for model development, and compare to few-shot parsing trained on the same labeled examples.

While discriminative neural network classifiers are generally preferred, recent work has shown advantages of generative classifiers in term of data efficiency and robustness. In this paper, we focus on natural language inference (NLI). We propose GenNLI, a generative classifier for NLI tasks, and empirically characterize its performance by comparing it to five baselines, including discriminative models and large-scale pretrained language representation models like BERT. We explore training objectives for discriminative fine-tuning of our generative classifiers, showing improvements over log loss fine-tuning from prior work (Lewis and Fan, 2019). In particular, we find strong results with a simple unbounded modification to log loss, which we call the “infinilog loss”. Our experiments show that GenNLI outperforms both discriminative and pretrained baselines across several challenging NLI experimental settings, including small training sets, imbalanced label distributions, and label noise.

Long document coreference resolution remains a challenging task due to the large memory and runtime requirements of current models. Recent work doing incremental coreference resolution using just the global representation of entities shows practical benefits but requires keeping all entities in memory, which can be impractical for long documents. We argue that keeping all entities in memory is unnecessary, and we propose a memory-augmented neural network that tracks only a small bounded number of entities at a time, thus guaranteeing a linear runtime in length of document. We show that (a) the model remains competitive with models with high memory and computational requirements on OntoNotes and LitBank, and (b) the model learns an efficient memory management strategy easily outperforming a rule-based strategy

We present the Visually Grounded Neural Syntax Learner (VG-NSL), an approach for learning syntactic representations and structures without any explicit supervision. The model learns by looking at natural images and reading paired captions. VG-NSL generates constituency parse trees of texts, recursively composes representations for constituents, and matches them with images. We define concreteness of constituents by their matching scores with images, and use it to guide the parsing of text. Experiments on the MSCOCO data set show that VG-NSL outperforms various unsupervised parsing approaches that do not use visual grounding, in terms of F1 scores against gold parse trees. We find that VGNSL is much more stable with respect to the choice of random initialization and the amount of training data. We also find that the concreteness acquired by VG-NSL correlates well with a similar measure defined by linguists. Finally, we also apply VG-NSL to multiple languages in the Multi30K data set, showing that our model consistently outperforms prior unsupervised approaches.

While most neural machine translation (NMT)systems are still trained using maximum likelihood estimation, recent work has demonstrated that optimizing systems to directly improve evaluation metrics such as BLEU can significantly improve final translation accuracy. However, training with BLEU has some limitations: it doesn’t assign partial credit, it has a limited range of output values, and it can penalize semantically correct hypotheses if they differ lexically from the reference. In this paper, we introduce an alternative reward function for optimizing NMT systems that is based on recent work in semantic similarity. We evaluate on four disparate languages trans-lated to English, and find that training with our proposed metric results in better translations as evaluated by BLEU, semantic similarity, and human evaluation, and also that the optimization procedure converges faster. Analysis suggests that this is because the proposed metric is more conducive to optimization, assigning partial credit and providing more diversity in scores than BLEU

We present a model and methodology for learning paraphrastic sentence embeddings directly from bitext, removing the time-consuming intermediate step of creating para-phrase corpora. Further, we show that the resulting model can be applied to cross lingual tasks where it both outperforms and is orders of magnitude faster than more complex state-of-the-art baselines.

Prior work on controllable text generation usually assumes that the controlled attribute can take on one of a small set of values known a priori. In this work, we propose a novel task, where the syntax of a generated sentence is controlled rather by a sentential exemplar. To evaluate quantitatively with standard metrics, we create a novel dataset with human annotations. We also develop a variational model with a neural module specifically designed for capturing syntactic knowledge and several multitask training objectives to promote disentangled representation learning. Empirically, the proposed model is observed to achieve improvements over baselines and learn to capture desirable characteristics.

We introduce entity post-modifier generation as an instance of a collaborative writing task. Given a sentence about a target entity, the task is to automatically generate a post-modifier phrase that provides contextually relevant information about the entity. For example, for the sentence, “Barack Obama, _______, supported the #MeToo movement.”, the phrase “a father of two girls” is a contextually relevant post-modifier. To this end, we build PoMo, a post-modifier dataset created automatically from news articles reflecting a journalistic need for incorporating entity information that is relevant to a particular news event. PoMo consists of more than 231K sentences with post-modifiers and associated facts extracted from Wikidata for around 57K unique entities. We use crowdsourcing to show that modeling contextual relevance is necessary for accurate post-modifier generation. We adapt a number of existing generation approaches as baselines for this dataset. Our results show there is large room for improvement in terms of both identifying relevant facts to include (knowing which claims are relevant gives a >20% improvement in BLEU score), and generating appropriate post-modifier text for the context (providing relevant claims is not sufficient for accurate generation). We conduct an error analysis that suggests promising directions for future research.

We propose a generative model for a sentence that uses two latent variables, with one intended to represent the syntax of the sentence and the other to represent its semantics. We show we can achieve better disentanglement between semantic and syntactic representations by training with multiple losses, including losses that exploit aligned paraphrastic sentences and word-order information. We evaluate our models on standard semantic similarity tasks and novel syntactic similarity tasks. Empirically, we find that the model with the best performing syntactic and semantic representations also gives rise to the most disentangled representations.

Exact structured inference with neural network scoring functions is computationally challenging but several methods have been proposed for approximating inference. One approach is to perform gradient descent with respect to the output structure directly (Belanger and McCallum, 2016). Another approach, proposed recently, is to train a neural network (an “inference network”) to perform inference (Tu and Gimpel, 2018). In this paper, we compare these two families of inference methods on three sequence labeling datasets. We choose sequence labeling because it permits us to use exact inference as a benchmark in terms of speed, accuracy, and search error. Across datasets, we demonstrate that inference networks achieve a better speed/accuracy/search error trade-off than gradient descent, while also being faster than exact inference at similar accuracy levels. We find further benefit by combining inference networks and gradient descent, using the former to provide a warm start for the latter.

Rich entity representations are useful for a wide class of problems involving entities. Despite their importance, there is no standardized benchmark that evaluates the overall quality of entity representations. In this work, we propose EntEval: a test suite of diverse tasks that require nontrivial understanding of entities including entity typing, entity similarity, entity relation prediction, and entity disambiguation. In addition, we develop training techniques for learning better entity representations by using natural hyperlink annotations in Wikipedia. We identify effective objectives for incorporating the contextual information in hyperlinks into state-of-the-art pretrained language models (Peters et al., 2018) and show that they improve strong baselines on multiple EntEval tasks.

Generative classifiers offer potential advantages over their discriminative counterparts, namely in the areas of data efficiency, robustness to data shift and adversarial examples, and zero-shot learning (Ng and Jordan,2002; Yogatama et al., 2017; Lewis and Fan,2019). In this paper, we improve generative text classifiers by introducing discrete latent variables into the generative story, and explore several graphical model configurations. We parameterize the distributions using standard neural architectures used in conditional language modeling and perform learning by directly maximizing the log marginal likelihood via gradient-based optimization, which avoids the need to do expectation-maximization. We empirically characterize the performance of our models on six text classification datasets. The choice of where to include the latent variable has a significant impact on performance, with the strongest results obtained when using the latent variable as an auxiliary conditioning variable in the generation of the textual input. This model consistently outperforms both the generative and discriminative classifiers in small-data settings. We analyze our model by finding that the latent variable captures interpretable properties of the data, even with very small training sets.

Prior work on pretrained sentence embeddings and benchmarks focus on the capabilities of stand-alone sentences. We propose DiscoEval, a test suite of tasks to evaluate whether sentence representations include broader context information. We also propose a variety of training objectives that makes use of natural annotations from Wikipedia to build sentence encoders capable of modeling discourse. We benchmark sentence encoders pretrained with our proposed training objectives, as well as other popular pretrained sentence encoders on DiscoEval and other sentence evaluation tasks. Empirically, we show that these training objectives help to encode different aspects of information in document structures. Moreover, BERT and ELMo demonstrate strong performances over DiscoEval with individual hidden layers showing different characteristics.

We propose a simple and effective modeling framework for controlled generation of multiple, diverse outputs. We focus on the setting of generating the next sentence of a story given its context. As controllable dimensions, we consider several sentence attributes, including sentiment, length, predicates, frames, and automatically-induced clusters. Our empirical results demonstrate: (1) our framework is accurate in terms of generating outputs that match the target control values; (2) our model yields increased maximum metric scores compared to standard n-best list generation via beam search; (3) controlling generation with semantic frames leads to a stronger combination of diversity and quality than other control variables as measured by automatic metrics. We also conduct a human evaluation to assess the utility of providing multiple suggestions for creative writing, demonstrating promising results for the potential of controllable, diverse generation in a collaborative writing system.

We consider the problem of automatically generating textual paraphrases with modified attributes or properties, focusing on the setting without parallel data (Hu et al., 2017; Shen et al., 2017). This setting poses challenges for evaluation. We show that the metric of post-transfer classification accuracy is insufficient on its own, and propose additional metrics based on semantic preservation and fluency as well as a way to combine them into a single overall score. We contribute new loss functions and training strategies to address the different metrics. Semantic preservation is addressed by adding a cyclic consistency loss and a loss based on paraphrase pairs, while fluency is improved by integrating losses based on style-specific language models. We experiment with a Yelp sentiment dataset and a new literature dataset that we propose, using multiple models that extend prior work (Shen et al., 2017). We demonstrate that our metrics correlate well with human judgments, at both the sentence-level and system-level. Automatic and manual evaluation also show large improvements over the baseline method of Shen et al. (2017). We hope that our proposed metrics can speed up system development for new textual transfer tasks while also encouraging the community to address our three complementary aspects of transfer quality.

In conversational speech, the acoustic signal provides cues that help listeners disambiguate difficult parses. For automatically parsing spoken utterances, we introduce a model that integrates transcribed text and acoustic-prosodic features using a convolutional neural network over energy and pitch trajectories coupled with an attention-based recurrent neural network that accepts text and prosodic features. We find that different types of acoustic-prosodic features are individually helpful, and together give statistically significant improvements in parse and disfluency detection F1 scores over a strong text-only baseline. For this study with known sentence boundaries, error analyses show that the main benefit of acoustic-prosodic features is in sentences with disfluencies, attachment decisions are most improved, and transcription errors obscure gains from prosody.

We propose syntactically controlled paraphrase networks (SCPNs) and use them to generate adversarial examples. Given a sentence and a target syntactic form (e.g., a constituency parse), SCPNs are trained to produce a paraphrase of the sentence with the desired syntax. We show it is possible to create training data for this task by first doing backtranslation at a very large scale, and then using a parser to label the syntactic transformations that naturally occur during this process. Such data allows us to train a neural encoder-decoder model with extra inputs to specify the target syntax. A combination of automated and human evaluations show that SCPNs generate paraphrases that follow their target specifications without decreasing paraphrase quality when compared to baseline (uncontrolled) paraphrase systems. Furthermore, they are more capable of generating syntactically adversarial examples that both (1) “fool” pretrained models and (2) improve the robustness of these models to syntactic variation when used to augment their training data.

Word embedding parameters often dominate overall model sizes in neural methods for natural language processing. We reduce deployed model sizes of text classifiers by learning a hard word clustering in an end-to-end manner. We use the Gumbel-Softmax distribution to maximize over the latent clustering while minimizing the task loss. We propose variations that selectively assign additional parameters to words, which further improves accuracy while still remaining parameter-efficient.

We describe ParaNMT-50M, a dataset of more than 50 million English-English sentential paraphrase pairs. We generated the pairs automatically by using neural machine translation to translate the non-English side of a large parallel corpus, following Wieting et al. (2017). Our hope is that ParaNMT-50M can be a valuable resource for paraphrase generation and can provide a rich source of semantic knowledge to improve downstream natural language understanding tasks. To show its utility, we use ParaNMT-50M to train paraphrastic sentence embeddings that outperform all supervised systems on every SemEval semantic textual similarity competition, in addition to showing how it can be used for paraphrase generation.

We introduce a family of multitask variational methods for semi-supervised sequence labeling. Our model family consists of a latent-variable generative model and a discriminative labeler. The generative models use latent variables to define the conditional probability of a word given its context, drawing inspiration from word prediction objectives commonly used in learning word embeddings. The labeler helps inject discriminative information into the latent space. We explore several latent variable configurations, including ones with hierarchical structure, which enables the model to account for both label-specific and word-specific information. Our models consistently outperform standard sequential baselines on 8 sequence labeling datasets, and improve further with unlabeled data.

We study the problem of measuring the quality of automatically-generated stories. We focus on the setting in which a few sentences of a story are provided and the task is to generate the next sentence (“continuation”) in the story. We seek to identify what makes a story continuation interesting, relevant, and have high overall quality. We crowdsource annotations along these three criteria for the outputs of story continuation systems, design features, and train models to predict the annotations. Our trained scorer can be used as a rich feature function for story generation, a reward function for systems that use reinforcement learning to learn to generate stories, and as a partial evaluation metric for story generation.

We consider the problem of learning general-purpose, paraphrastic sentence embeddings in the setting of Wieting et al. (2016b). We use neural machine translation to generate sentential paraphrases via back-translation of bilingual sentence pairs. We evaluate the paraphrase pairs by their ability to serve as training data for learning paraphrastic sentence embeddings. We find that the data quality is stronger than prior work based on bitext and on par with manually-written English paraphrase pairs, with the advantage that our approach can scale up to generate large training sets for many languages and domains. We experiment with several language pairs and data sources, and develop a variety of data filtering techniques. In the process, we explore how neural machine translation output differs from human-written sentences, finding clear differences in length, the amount of repetition, and the use of rare words.

Progress in text understanding has been driven by large datasets that test particular capabilities, like recent datasets for reading comprehension (Hermann et al., 2015). We focus here on the LAMBADA dataset (Paperno et al., 2016), a word prediction task requiring broader context than the immediate sentence. We view LAMBADA as a reading comprehension problem and apply comprehension models based on neural networks. Though these models are constrained to choose a word from the context, they improve the state of the art on LAMBADA from 7.3% to 49%. We analyze 100 instances, finding that neural network readers perform well in cases that involve selecting a name from the context based on dialogue or discourse cues but struggle when coreference resolution or external knowledge is needed.

A significant number of neural architectures for reading comprehension have recently been developed and evaluated on large cloze-style datasets. We present experiments supporting the emergence of “predication structure” in the hidden state vectors of these readers. More specifically, we provide evidence that the hidden state vectors represent atomic formulas 𝛷c where 𝛷 is a semantic property (predicate) and c is a constant symbol entity identifier.

We present models for embedding words in the context of surrounding words. Such models, which we refer to as token embeddings, represent the characteristics of a word that are specific to a given context, such as word sense, syntactic category, and semantic role. We explore simple, efficient token embedding models based on standard neural network architectures. We learn token embeddings on a large amount of unannotated text and evaluate them as features for part-of-speech taggers and dependency parsers trained on much smaller amounts of annotated data. We find that predictors endowed with token embeddings consistently outperform baseline predictors across a range of context window and training set sizes.

We consider the problem of learning general-purpose, paraphrastic sentence embeddings, revisiting the setting of Wieting et al. (2016b). While they found LSTM recurrent networks to underperform word averaging, we present several developments that together produce the opposite conclusion. These include training on sentence pairs rather than phrase pairs, averaging states to represent sequences, and regularizing aggressively. These improve LSTMs in both transfer learning and supervised settings. We also introduce a new recurrent architecture, the Gated Recurrent Averaging Network, that is inspired by averaging and LSTMs while outperforming them both. We analyze our learned models, finding evidence of preferences for particular parts of speech and dependency relations.

We consider the ROC story cloze task (Mostafazadeh et al., 2016) and present several findings. We develop a model that uses hierarchical recurrent networks with attention to encode the sentences in the story and score candidate endings. By discarding the large training set and only training on the validation set, we achieve an accuracy of 74.7%. Even when we discard the story plots (sentences before the ending) and only train to choose the better of two endings, we can still reach 72.5%. We then analyze this “ending-only” task setting. We estimate human accuracy to be 78% and find several types of clues that lead to this high accuracy, including those related to sentiment, negation, and general ending likelihood regardless of the story context.

Word sense induction (WSI) seeks to automatically discover the senses of a word in a corpus via unsupervised methods. We propose a sense-topic model for WSI, which treats sense and topic as two separate latent variables to be inferred jointly. Topics are informed by the entire document, while senses are informed by the local context surrounding the ambiguous word. We also discuss unsupervised ways of enriching the original corpus in order to improve model performance, including using neural word embeddings and external corpora to expand the context of each data instance. We demonstrate significant improvements over the previous state-of-the-art, achieving the best results reported to date on the SemEval-2013 WSI task.

The Paraphrase Database (PPDB; Ganitkevitch et al., 2013) is an extensive semantic resource, consisting of a list of phrase pairs with (heuristic) confidence estimates. However, it is still unclear how it can best be used, due to the heuristic nature of the confidences and its necessarily incomplete coverage. We propose models to leverage the phrase pairs from the PPDB to build parametric paraphrase models that score paraphrase pairs more accurately than the PPDB’s internal scores while simultaneously improving its coverage. They allow for learning phrase embeddings as well as improved word embeddings. Moreover, we introduce two new, manually annotated datasets to evaluate short-phrase paraphrasing models. Using our paraphrase model trained using PPDB, we achieve state-of-the-art results on standard word and bigram similarity tasks and beat strong baselines on our new short phrase paraphrase tasks.