Large-scale neural network models combining text and images have made incredible progress in recent years. However, it remains an open question to what extent such models encode compositional representations of the concepts over which they operate, such as correctly identifying ‘red cube’ by reasoning over the constituents ‘red’ and ‘cube’. In this work, we focus on the ability of a large pretrained vision and language model (CLIP) to encode compositional concepts and to bind variables in a structure-sensitive way (e.g., differentiating ‘cube behind sphere’ from ‘sphere behind cube’). To inspect the performance of CLIP, we compare several architectures from research on compositional distributional semantics models (CDSMs), a line of research that attempts to implement traditional compositional linguistic structures within embedding spaces. We benchmark them on three synthetic datasets – single-object, two-object, and relational – designed to test concept binding. We find that CLIP can compose concepts in a single-object setting, but in situations where concept binding is needed, performance drops dramatically. At the same time, CDSMs also perform poorly, with best performance at chance level.

Many pretrained multilingual models exhibit cross-lingual transfer ability, which is often attributed to a learned language-neutral representation during pretraining. However, it remains unclear what factors contribute to the learning of a language-neutral representation, and whether the learned language-neutral representation suffices to facilitate cross-lingual transfer. We propose a synthetic task, Multilingual Othello (mOthello), as a testbed to delve into these two questions. We find that: (1) models trained with naive multilingual pretraining fail to learn a language-neutral representation across all input languages; (2) the introduction of “anchor tokens” (i.e., lexical items that are identical across languages) helps cross-lingual representation alignment; and (3) the learning of a language-neutral representation alone is not sufficient to facilitate cross-lingual transfer. Based on our findings, we propose a novel approach – multilingual pretraining with unified output space – that both induces the learning of language-neutral representation and facilitates cross-lingual transfer.

A primary criticism towards language models (LMs) is their inscrutability. This paper presents evidence that, despite their size and complexity, LMs sometimes exploit a simple vector arithmetic style mechanism to solve some relational tasks using regularities encoded in the hidden space of the model (e.g., Poland:Warsaw::China:Beijing). We investigate a range of language model sizes (from 124M parameters to 176B parameters) in an in-context learning setting, and find that for a variety of tasks (involving capital cities, uppercasing, and past-tensing) a key part of the mechanism reduces to a simple additive update typically applied by the feedforward (FFN) networks. We further show that this mechanism is specific to tasks that require retrieval from pretraining memory, rather than retrieval from local context. Our results contribute to a growing body of work on the interpretability of LMs, and offer reason to be optimistic that, despite the massive and non-linear nature of the models, the strategies they ultimately use to solve tasks can sometimes reduce to familiar and even intuitive algorithms.

Prompts have been the center of progress in advancing language models’ zero-shot and few-shot performance. However, recent work finds that models can perform surprisingly well when given intentionally irrelevant or misleading prompts. Such results may be interpreted as evidence that model behavior is not “human like’. In this study, we challenge a central assumption in such work: that humans would perform badly when given pathological instructions. We find that humans are able to reliably ignore irrelevant instructions and thus, like models, perform well on the underlying task despite an apparent lack of signal regarding the task they are being asked to do. However, when given deliberately misleading instructions, humans follow the instructions faithfully, whereas models do not. Thus, our conclusion is mixed with respect to prior work. We argue against the earlier claim that high performance with irrelevant prompts constitutes evidence against models’ instruction understanding, but we reinforce the claim that models’ failure to follow misleading instructions raises concerns. More broadly, we caution that future research should not idealize human behaviors as a monolith and should not train or evaluate models to mimic assumptions about these behaviors without first validating humans’ behaviors empirically.

Modular neural networks without additional training have recently been shown to surpass end-to-end neural networks on challenging vision–language tasks. The latest such methods simultaneously introduce LLM-based code generation to build programs and a number of skill-specific, task-oriented modules to execute them. In this paper, we focus on ViperGPT and ask where its additional performance comes from and how much is due to the (state-of-art, end-to-end) BLIP-2 model it subsumes vs. additional symbolic components. To do so, we conduct a controlled study (comparing end-to-end, modular, and prompting-based methods across several VQA benchmarks). We find that ViperGPT’s reported gains over BLIP-2 can be attributed to its selection of task-specific modules, and when we run ViperGPT using a more task-agnostic selection of modules, these gains go away. ViperGPT retains much of its performance if we make prominent alterations to its selection of modules: e.g. removing or retaining only BLIP-2. We also compare ViperGPT against a prompting-based decomposition strategy and find that, on some benchmarks, modular approaches significantly benefit by representing subtasks with natural language, instead of code. Our code is fully available at https://github.com/brown-palm/visual-question-decomposition.

Language Models (LMs) often must integrate facts they memorized in pretraining with new information that appears in a given context. These two sources can disagree, causing competition within the model, and it is unclear how an LM will resolve the conflict. On a dataset that queries for knowledge of world capitals, we investigate both distributional and mechanistic determinants of LM behavior in such situations. Specifically, we measure the proportion of the time an LM will use a counterfactual prefix (e.g., “The capital of Poland is London”) to overwrite what it learned in pretraining (“Warsaw”). On Pythia and GPT2, the training frequency of both the query country (”Poland”) and the in-context city (”London”) highly affect the models’ likelihood of using the counterfactual. We then use head attribution to identify individual attention heads that either promote the memorized answer or the in-context answer in the logits. By scaling up or down the value vector of these heads, we can control the likelihood of using the in-context answer on new data. This method can increase the rate of generating the in-context answer to 88% of the time simply by scaling a single head at runtime. Our work contributes to a body of evidence showing that we can often localize model behaviors to specific components and provides a proof of concept for how future methods might control model behavior dynamically at runtime.

Decision making via sequence modeling aims to mimic the success of language models, where actions taken by an embodied agent are modeled as tokens to predict. Despite their promising performance, it remains unclear if embodied sequence modeling leads to the emergence of internal representations that represent the environmental state information. A model that lacks abstract state representations would be liable to make decisions based on surface statistics which fail to generalize. We take the BabyAI environment, a grid world in which language-conditioned navigation tasks are performed, and build a sequence modeling Transformer, which takes a language instruction, a sequence of actions, and environmental observations as its inputs. In order to investigate the emergence of abstract state representations, we design a “blindfolded” navigation task, where only the initial environmental layout, the language instruction, and the action sequence to complete the task are available for training. Our probing results show that intermediate environmental layouts can be reasonably reconstructed from the internal activations of a trained model, and that language instructions play a role in the reconstruction accuracy. Our results suggest that many key features of state representations can emerge via embodied sequence modeling, supporting an optimistic outlook for applications of sequence modeling objectives to more complex embodied decision-making domains.

Lexical semantics and cognitive science point to affordances (i.e. the actions that objects support) as critical for understanding and representing nouns and verbs. However, study of these semantic features has not yet been integrated with the ?foundation? models that currently dominate language representation research. We hypothesize that predictive modeling of object state over time will result in representations that encode object affordance information ?for free?. We train a neural network to predict objects? trajectories in a simulated interaction and show that our network?s latent representations differentiate between both observed and unobserved affordances. We find that models trained using 3D simulations outperform conventional 2D computer vision models trained on a similar task, and, on initial inspection, that differences between concepts correspond to expected features (e.g., roll entails rotation) . Our results suggest a way in which modern deep learning approaches to grounded language learning can be integrated with traditional formal semantic notions of lexical representations.

Many complex problems are naturally understood in terms of symbolic concepts. For example, our concept of “cat” is related to our concepts of “ears” and “whiskers” in a non-arbitrary way. Fodor (1998) proposes one theory of concepts, which emphasizes symbolic representations related via constituency structures. Whether neural networks are consistent with such a theory is open for debate. We propose unit tests for evaluating whether a system’s behavior is consistent with several key aspects of Fodor’s criteria. Using a simple visual concept learning task, we evaluate several modern neural architectures against this specification. We find that models succeed on tests of groundedness, modularity, and reusability of concepts, but that important questions about causality remain open. Resolving these will require new methods for analyzing models’ internal states.

Recently, a boom of papers has shown extraordinary progress in zero-shot and few-shot learning with various prompt-based models. It is commonly argued that prompts help models to learn faster in the same way that humans learn faster when provided with task instructions expressed in natural language. In this study, we experiment with over 30 prompts manually written for natural language inference (NLI). We find that models can learn just as fast with many prompts that are intentionally irrelevant or even pathologically misleading as they do with instructively “good” prompts. Further, such patterns hold even for models as large as 175 billion parameters (Brown et al., 2020) as well as the recently proposed instruction-tuned models which are trained on hundreds of prompts (Sanh et al., 2021). That is, instruction-tuned models often produce good predictions with irrelevant and misleading prompts even at zero shots. In sum, notwithstanding prompt-based models’ impressive improvement, we find evidence of serious limitations that question the degree to which such improvement is derived from models understanding task instructions in ways analogous to humans’ use of task instructions.

Distributional models learn representations of words from text, but are criticized for their lack of grounding, or the linking of text to the non-linguistic world. Grounded language models have had success in learning to connect concrete categories like nouns and adjectives to the world via images and videos, but can struggle to isolate the meaning of the verbs themselves from the context in which they typically occur. In this paper, we investigate the extent to which trajectories (i.e. the position and rotation of objects over time) naturally encode verb semantics. We build a procedurally generated agent-object-interaction dataset, obtain human annotations for the verbs that occur in this data, and compare several methods for representation learning given the trajectories. We find that trajectories correlate as-is with some verbs (e.g., fall), and that additional abstraction via self-supervised pretraining can further capture nuanced differences in verb meaning (e.g., roll and slide).

Linguistic representations derived from text alone have been criticized for their lack of grounding, i.e., connecting words to their meanings in the physical world. Vision-and- Language (VL) models, trained jointly on text and image or video data, have been offered as a response to such criticisms. However, while VL pretraining has shown success on multimodal tasks such as visual question answering, it is not yet known how the internal linguistic representations themselves compare to their text-only counterparts. This paper compares the semantic representations learned via VL vs. text-only pretraining for two recent VL models using a suite of analyses (clustering, probing, and performance on a commonsense question answering task) in a language-only setting. We find that the multimodal models fail to significantly outperform the text-only variants, suggesting that future work is required if multimodal pretraining is to be pursued as a means of improving NLP in general.

Pre-trained language models perform well on a variety of linguistic tasks that require symbolic reasoning, raising the question of whether such models implicitly represent abstract symbols and rules. We investigate this question using the case study of BERT’s performance on English subject–verb agreement. Unlike prior work, we train multiple instances of BERT from scratch, allowing us to perform a series of controlled interventions at pre-training time. We show that BERT often generalizes well to subject–verb pairs that never occurred in training, suggesting a degree of rule-governed behavior. We also find, however, that performance is heavily influenced by word frequency, with experiments showing that both the absolute frequency of a verb form, as well as the frequency relative to the alternate inflection, are causally implicated in the predictions BERT makes at inference time. Closer analysis of these frequency effects reveals that BERT’s behavior is consistent with a system that correctly applies the SVA rule in general but struggles to overcome strong training priors and to estimate agreement features (singular vs. plural) on infrequent lexical items.

People use language in subtle and nuanced ways to convey their beliefs. For instance, saying claimed instead of said casts doubt on the truthfulness of the underlying proposition, thus representing the author’s opinion on the matter. Several works have identified such linguistic classes of words that occur frequently in natural language text and are bias-inducing by virtue of their framing effects. In this paper, we test whether generative language models (including GPT-2 (CITATION) are sensitive to these linguistic framing effects. In particular, we test whether prompts that contain linguistic markers of author bias (e.g., hedges, implicatives, subjective intensifiers, assertives) influence the distribution of the generated text. Although these framing effects are subtle and stylistic, we find evidence that they lead to measurable style and topic differences in the generated text, leading to language that is, on average, more polarised and more skewed towards controversial entities and events.

Pretrained language models have been shown to encode relational information, such as the relations between entities or concepts in knowledge-bases — (Paris, Capital, France). However, simple relations of this type can often be recovered heuristically and the extent to which models implicitly reflect topological structure that is grounded in world, such as perceptual structure, is unknown. To explore this question, we conduct a thorough case study on color. Namely, we employ a dataset of monolexemic color terms and color chips represented in CIELAB, a color space with a perceptually meaningful distance metric. Using two methods of evaluating the structural alignment of colors in this space with text-derived color term representations, we find significant correspondence. Analyzing the differences in alignment across the color spectrum, we find that warmer colors are, on average, better aligned to the perceptual color space than cooler ones, suggesting an intriguing connection to findings from recent work on efficient communication in color naming. Further analysis suggests that differences in alignment are, in part, mediated by collocationality and differences in syntactic usage, posing questions as to the relationship between color perception and usage and context.

In modern natural language processing pipelines, it is common practice to “pretrain” a generative language model on a large corpus of text, and then to “finetune” the created representations by continuing to train them on a discriminative textual inference task. However, it is not immediately clear whether the logical meaning necessary to model logical entailment is captured by language models in this paradigm. We examine this pretrain-finetune recipe with language models trained on a synthetic propositional language entailment task, and present results on test sets probing models’ knowledge of axioms of first order logic.

Many Question-Answering (QA) datasets contain unanswerable questions, but their treatment in QA systems remains primitive. Our analysis of the Natural Questions (Kwiatkowski et al. 2019) dataset reveals that a substantial portion of unanswerable questions (~21%) can be explained based on the presence of unverifiable presuppositions. Through a user preference study, we demonstrate that the oracle behavior of our proposed system—which provides responses based on presupposition failure—is preferred over the oracle behavior of existing QA systems. Then, we present a novel framework for implementing such a system in three steps: presupposition generation, presupposition verification, and explanation generation, reporting progress on each. Finally, we show that a simple modification of adding presuppositions and their verifiability to the input of a competitive end-to-end QA system yields modest gains in QA performance and unanswerability detection, demonstrating the promise of our approach.

A current open question in natural language processing is to what extent language models, which are trained with access only to the form of language, are able to capture the meaning of language. This question is challenging to answer in general, as there is no clear line between meaning and form, but rather meaning constrains form in consistent ways. The goal of this study is to offer insights into a narrower but critical subquestion: Under what conditions should we expect that meaning and form covary sufficiently, such that a language model with access only to form might nonetheless succeed in emulating meaning? Focusing on several formal languages (propositional logic and a set of programming languages), we generate training corpora using a variety of motivated constraints, and measure a distributional language model’s ability to differentiate logical symbols (AND, OR, and NOT). Our findings are largely negative: none of our simulated training corpora result in models which definitively differentiate meaningfully different symbols (e.g., AND vs. OR), suggesting a limitation to the types of semantic signals that current models are able to exploit.

We introduce a new dataset for training and evaluating grounded language models. Our data is collected within a virtual reality environment and is designed to emulate the quality of language data to which a pre-verbal child is likely to have access: That is, naturalistic, spontaneous speech paired with richly grounded visuospatial context. We use the collected data to compare several distributional semantics models for verb learning. We evaluate neural models based on 2D (pixel) features as well as feature-engineered models based on 3D (symbolic, spatial) features, and show that neither modeling approach achieves satisfactory performance. Our results are consistent with evidence from child language acquisition that emphasizes the difficulty of learning verbs from naive distributional data. We discuss avenues for future work on cognitively-inspired grounded language learning, and release our corpus with the intent of facilitating research on the topic.

While deep learning has transformed the natural language processing (NLP) field and impacted the larger computational linguistics community, the rise of neural networks is stained by their opaque nature: It is challenging to interpret the inner workings of neural network models, and explicate their behavior. Therefore, in the last few years, an increasingly large body of work has been devoted to the analysis and interpretation of neural network models in NLP. This body of work is so far lacking a common framework and methodology. Moreover, approaching the analysis of modern neural networks can be difficult for newcomers to the field. This tutorial aims to fill this gap and introduce the nascent field of interpretability and analysis of neural networks in NLP. The tutorial will cover the main lines of analysis work, such as structural analyses using probing classifiers, behavioral studies and test suites, and interactive visualizations. We will highlight not only the most commonly applied analysis methods, but also the specific limitations and shortcomings of current approaches, in order to inform participants where to focus future efforts.

In politics, neologisms are frequently invented for partisan objectives. For example, “undocumented workers” and “illegal aliens” refer to the same group of people (i.e., they have the same denotation), but they carry clearly different connotations. Examples like these have traditionally posed a challenge to reference-based semantic theories and led to increasing acceptance of alternative theories (e.g., Two-Factor Semantics) among philosophers and cognitive scientists. In NLP, however, popular pretrained models encode both denotation and connotation as one entangled representation. In this study, we propose an adversarial nerual netowrk that decomposes a pretrained representation as independent denotation and connotation representations. For intrinsic interpretability, we show that words with the same denotation but different connotations (e.g., “immigrants” vs. “aliens”, “estate tax” vs. “death tax”) move closer to each other in denotation space while moving further apart in connotation space. For extrinsic application, we train an information retrieval system with our disentangled representations and show that the denotation vectors improve the viewpoint diversity of document rankings.

While much recent work has examined how linguistic information is encoded in pre-trained sentence representations, comparatively little is understood about how these models change when adapted to solve downstream tasks. Using a suite of analysis techniques—supervised probing, unsupervised similarity analysis, and layer-based ablations—we investigate how fine-tuning affects the representations of the BERT model. We find that while fine-tuning necessarily makes some significant changes, there is no catastrophic forgetting of linguistic phenomena. We instead find that fine-tuning is a conservative process that primarily affects the top layers of BERT, albeit with noteworthy variation across tasks. In particular, dependency parsing reconfigures most of the model, whereas SQuAD and MNLI involve much shallower processing. Finally, we also find that fine-tuning has a weaker effect on representations of out-of-domain sentences, suggesting room for improvement in model generalization.

The fields of cognitive science and philosophy have proposed many different theories for how humans represent “concepts”. Multiple such theories are compatible with state-of-the-art NLP methods, and could in principle be operationalized using neural networks. We focus on two particularly prominent theories–Classical Theory and Prototype Theory–in the context of visually-grounded lexical representations. We compare when and how the behavior of models based on these theories differs in terms of categorization and entailment tasks. Our preliminary results suggest that Classical-based representations perform better for entailment and Prototype-based representations perform better for categorization. We discuss plans for additional experiments needed to confirm these initial observations.

In natural language inference (NLI), contexts are considered veridical if they allow us to infer that their underlying propositions make true claims about the real world. We investigate whether a state-of-the-art natural language inference model (BERT) learns to make correct inferences about veridicality in verb-complement constructions. We introduce an NLI dataset for veridicality evaluation consisting of 1,500 sentence pairs, covering 137 unique verbs. We find that both human and model inferences generally follow theoretical patterns, but exhibit a systematic bias towards assuming that verbs are veridical–a bias which is amplified in BERT. We further show that, encouragingly, BERT’s inferences are sensitive not only to the presence of individual verb types, but also to the syntactic role of the verb, the form of the complement clause (to- vs. that-complements), and negation.

A machine learning system can score well on a given test set by relying on heuristics that are effective for frequent example types but break down in more challenging cases. We study this issue within natural language inference (NLI), the task of determining whether one sentence entails another. We hypothesize that statistical NLI models may adopt three fallible syntactic heuristics: the lexical overlap heuristic, the subsequence heuristic, and the constituent heuristic. To determine whether models have adopted these heuristics, we introduce a controlled evaluation set called HANS (Heuristic Analysis for NLI Systems), which contains many examples where the heuristics fail. We find that models trained on MNLI, including BERT, a state-of-the-art model, perform very poorly on HANS, suggesting that they have indeed adopted these heuristics. We conclude that there is substantial room for improvement in NLI systems, and that the HANS dataset can motivate and measure progress in this area.

Natural language understanding has recently seen a surge of progress with the use of sentence encoders like ELMo (Peters et al., 2018a) and BERT (Devlin et al., 2019) which are pretrained on variants of language modeling. We conduct the first large-scale systematic study of candidate pretraining tasks, comparing 19 different tasks both as alternatives and complements to language modeling. Our primary results support the use language modeling, especially when combined with pretraining on additional labeled-data tasks. However, our results are mixed across pretraining tasks and show some concerning trends: In ELMo’s pretrain-then-freeze paradigm, random baselines are worryingly strong and results vary strikingly across target tasks. In addition, fine-tuning BERT on an intermediate task often negatively impacts downstream transfer. In a more positive trend, we see modest gains from multitask training, suggesting the development of more sophisticated multitask and transfer learning techniques as an avenue for further research.

Pre-trained text encoders have rapidly advanced the state of the art on many NLP tasks. We focus on one such model, BERT, and aim to quantify where linguistic information is captured within the network. We find that the model represents the steps of the traditional NLP pipeline in an interpretable and localizable way, and that the regions responsible for each step appear in the expected sequence: POS tagging, parsing, NER, semantic roles, then coreference. Qualitative analysis reveals that the model can and often does adjust this pipeline dynamically, revising lower-level decisions on the basis of disambiguating information from higher-level representations.

We analyze human’s disagreements about the validity of natural language inferences. We show that, very often, disagreements are not dismissible as annotation “noise”, but rather persist as we collect more ratings and as we vary the amount of context provided to raters. We further show that the type of uncertainty captured by current state-of-the-art models for natural language inference is not reflective of the type of uncertainty present in human disagreements. We discuss implications of our results in relation to the recognizing textual entailment (RTE)/natural language inference (NLI) task. We argue for a refined evaluation objective that requires models to explicitly capture the full distribution of plausible human judgments.

We introduce a set of nine challenge tasks that test for the understanding of function words. These tasks are created by structurally mutating sentences from existing datasets to target the comprehension of specific types of function words (e.g., prepositions, wh-words). Using these probing tasks, we explore the effects of various pretraining objectives for sentence encoders (e.g., language modeling, CCG supertagging and natural language inference (NLI)) on the learned representations. Our results show that pretraining on CCG—our most syntactic objective—performs the best on average across our probing tasks, suggesting that syntactic knowledge helps function word comprehension. Language modeling also shows strong performance, supporting its widespread use for pretraining state-of-the-art NLP models. Overall, no pretraining objective dominates across the board, and our function word probing tasks highlight several intuitive differences between pretraining objectives, e.g., that NLI helps the comprehension of negation.

We present a large-scale collection of diverse natural language inference (NLI) datasets that help provide insight into how well a sentence representation captures distinct types of reasoning. The collection results from recasting 13 existing datasets from 7 semantic phenomena into a common NLI structure, resulting in over half a million labeled context-hypothesis pairs in total. We refer to our collection as the DNC: Diverse Natural Language Inference Collection. The DNC is available online at https://www.decomp.net, and will grow over time as additional resources are recast and added from novel sources.

We release a corpus of 43 million atomic edits across 8 languages. These edits are mined from Wikipedia edit history and consist of instances in which a human editor has inserted a single contiguous phrase into, or deleted a single contiguous phrase from, an existing sentence. We use the collected data to show that the language generated during editing differs from the language that we observe in standard corpora, and that models trained on edits encode different aspects of semantics and discourse than models trained on raw text. We release the full corpus as a resource to aid ongoing research in semantics, discourse, and representation learning.

Adjectives like “warm”, “hot”, and “scalding” all describe temperature but differ in intensity. Understanding these differences between adjectives is a necessary part of reasoning about natural language. We propose a new paraphrase-based method to automatically learn the relative intensity relation that holds between a pair of scalar adjectives. Our approach analyzes over 36k adjectival pairs from the Paraphrase Database under the assumption that, for example, paraphrase pair “really hot” <–> “scalding” suggests that “hot” < “scalding”. We show that combining this paraphrase evidence with existing, complementary pattern- and lexicon-based approaches improves the quality of systems for automatically ordering sets of scalar adjectives and inferring the polarity of indirect answers to “yes/no” questions.

We present a large scale collection of diverse natural language inference (NLI) datasets that help provide insight into how well a sentence representation encoded by a neural network captures distinct types of reasoning. The collection results from recasting 13 existing datasets from 7 semantic phenomena into a common NLI structure, resulting in over half a million labeled context-hypothesis pairs in total. Our collection of diverse datasets is available at http://www.decomp.net/, and will grow over time as additional resources are recast and added from novel sources.

We present a method for populating fine-grained classes (e.g., “1950s American jazz musicians”) with instances (e.g., Charles Mingus ). While state-of-the-art methods tend to treat class labels as single lexical units, the proposed method considers each of the individual modifiers in the class label relative to the head. An evaluation on the task of reconstructing Wikipedia category pages demonstrates a >10 point increase in AUC, over a strong baseline relying on widely-used Hearst patterns.

This paper presents an empirical study of linguistic formality. We perform an analysis of humans’ perceptions of formality in four different genres. These findings are used to develop a statistical model for predicting formality, which is evaluated under different feature settings and genres. We apply our model to an investigation of formality in online discussion forums, and present findings consistent with theories of formality and linguistic coordination.

Most recent sentence simplification systems use basic machine translation models to learn lexical and syntactic paraphrases from a manually simplified parallel corpus. These methods are limited by the quality and quantity of manually simplified corpora, which are expensive to build. In this paper, we conduct an in-depth adaptation of statistical machine translation to perform text simplification, taking advantage of large-scale paraphrases learned from bilingual texts and a small amount of manual simplifications with multiple references. Our work is the first to design automatic metrics that are effective for tuning and evaluating simplification systems, which will facilitate iterative development for this task.

We present a large scale study of the languages spoken by bilingual workers on Mechanical Turk (MTurk). We establish a methodology for determining the language skills of anonymous crowd workers that is more robust than simple surveying. We validate workers’ self-reported language skill claims by measuring their ability to correctly translate words, and by geolocating workers to see if they reside in countries where the languages are likely to be spoken. Rather than posting a one-off survey, we posted paid tasks consisting of 1,000 assignments to translate a total of 10,000 words in each of 100 languages. Our study ran for several months, and was highly visible on the MTurk crowdsourcing platform, increasing the chances that bilingual workers would complete it. Our study was useful both to create bilingual dictionaries and to act as census of the bilingual speakers on MTurk. We use this data to recommend languages with the largest speaker populations as good candidates for other researchers who want to develop crowdsourced, multilingual technologies. To further demonstrate the value of creating data via crowdsourcing, we hire workers to create bilingual parallel corpora in six Indian languages, and use them to train statistical machine translation systems.