We present the results of the NLP Community Metasurvey. Run from May to June 2022, it elicited opinions on controversial issues, including industry influence in the field, concerns about AGI, and ethics. Our results put concrete numbers to several controversies: For example, respondents are split in half on the importance of artificial general intelligence, whether language models understand language, and the necessity of linguistic structure and inductive bias for solving NLP problems. In addition, the survey posed meta-questions, asking respondents to predict the distribution of survey responses. This allows us to uncover false sociological beliefs where the community’s predictions don’t match reality. Among other results, we find that the community greatly overestimates its own belief in the usefulness of benchmarks and the potential for scaling to solve real-world problems, while underestimating its belief in the importance of linguistic structure, inductive bias, and interdisciplinary science.

Metrics for Inter-Annotator Agreement (IAA), like Cohen’s Kappa, are crucial for validating annotated datasets. Although high agreement is often used to show the reliability of annotation procedures, it is insufficient to ensure or reproducibility. While researchers are encouraged to increase annotator agreement, this can lead to specific and tailored annotation guidelines. We hypothesize that this may result in diverging annotations from different groups. To study this, we first propose the Lee et al. Protocol (LEAP), a standardized and codified annotation protocol. LEAP strictly enforces transparency in the annotation process, which ensures reproducibility of annotation guidelines. Using LEAP to annotate a dialog dataset, we empirically show that while research groups may create reliable guidelines by raising agreement, this can cause divergent annotations across different research groups, thus questioning the validity of the annotations. Therefore, we caution NLP researchers against using reliability as a proxy for reproducibility and validity.

To enable building and testing models on long-document comprehension, we introduce QuALITY, a multiple-choice QA dataset with context passages in English that have an average length of about 5,000 tokens, much longer than typical current models can process. Unlike in prior work with passages, our questions are written and validated by contributors who have read the entire passage, rather than relying on summaries or excerpts. In addition, only half of the questions are answerable by annotators working under tight time constraints, indicating that skimming and simple search are not enough to consistently perform well. Our baseline models perform poorly on this task (55.4%) and significantly lag behind human performance (93.5%).

For a natural language understanding benchmark to be useful in research, it has to consist of examples that are diverse and difficult enough to discriminate among current and near-future state-of-the-art systems. However, we do not yet know how best to select text sources to collect a variety of challenging examples. In this study, we crowdsource multiple-choice reading comprehension questions for passages taken from seven qualitatively distinct sources, analyzing what attributes of passages contribute to the difficulty and question types of the collected examples. To our surprise, we find that passage source, length, and readability measures do not significantly affect question difficulty. Through our manual annotation of seven reasoning types, we observe several trends between passage sources and reasoning types, e.g., logical reasoning is more often required in questions written for technical passages. These results suggest that when creating a new benchmark dataset, selecting a diverse set of passages can help ensure a diverse range of question types, but that passage difficulty need not be a priority.

It is well documented that NLP models learn social biases, but little work has been done on how these biases manifest in model outputs for applied tasks like question answering (QA). We introduce the Bias Benchmark for QA (BBQ), a dataset of question-sets constructed by the authors that highlight attested social biases against people belonging to protected classes along nine social dimensions relevant for U.S. English-speaking contexts. Our task evaluate model responses at two levels: (i) given an under-informative context, we test how strongly responses reflect social biases, and (ii) given an adequately informative context, we test whether the model’s biases override a correct answer choice. We find that models often rely on stereotypes when the context is under-informative, meaning the model’s outputs consistently reproduce harmful biases in this setting. Though models are more accurate when the context provides an informative answer, they still rely on stereotypes and average up to 3.4 percentage points higher accuracy when the correct answer aligns with a social bias than when it conflicts, with this difference widening to over 5 points on examples targeting gender for most models tested.

Current QA systems can generate reasonable-sounding yet false answers without explanation or evidence for the generated answer, which is especially problematic when humans cannot readily check the model’s answers. This presents a challenge for building trust in machine learning systems. We take inspiration from real-world situations where difficult questions are answered by considering opposing sides (see Irving et al., 2018). For multiple-choice QA examples, we build a dataset of single arguments for both a correct and incorrect answer option in a debate-style set-up as an initial step in training models to produce explanations for two candidate answers. We use long contexts—humans familiar with the context write convincing explanations for pre-selected correct and incorrect answers, and we test if those explanations allow humans who have not read the full context to more accurately determine the correct answer. We do not find that explanations in our set-up improve human accuracy, but a baseline condition shows that providing human-selected text snippets does improve accuracy. We use these findings to suggest ways of improving the debate set up for future data collection efforts.

Crowdsourcing is widely used to create data for common natural language understanding tasks. Despite the importance of these datasets for measuring and refining model understanding of language, there has been little focus on the crowdsourcing methods used for collecting the datasets. In this paper, we compare the efficacy of interventions that have been proposed in prior work as ways of improving data quality. We use multiple-choice question answering as a testbed and run a randomized trial by assigning crowdworkers to write questions under one of four different data collection protocols. We find that asking workers to write explanations for their examples is an ineffective stand-alone strategy for boosting NLU example difficulty. However, we find that training crowdworkers, and then using an iterative process of collecting data, sending feedback, and qualifying workers based on expert judgments is an effective means of collecting challenging data. But using crowdsourced, instead of expert judgments, to qualify workers and send feedback does not prove to be effective. We observe that the data from the iterative protocol with expert assessments is more challenging by several measures. Notably, the human–model gap on the unanimous agreement portion of this data is, on average, twice as large as the gap for the baseline protocol data.

Many crowdsourced NLP datasets contain systematic artifacts that are identified only after data collection is complete. Earlier identification of these issues should make it easier to create high-quality training and evaluation data. We attempt this by evaluating protocols in which expert linguists work ‘in the loop’ during data collection to identify and address these issues by adjusting task instructions and incentives. Using natural language inference as a test case, we compare three data collection protocols: (i) a baseline protocol with no linguist involvement, (ii) a linguist-in-the-loop intervention with iteratively-updated constraints on the writing task, and (iii) an extension that adds direct interaction between linguists and crowdworkers via a chatroom. We find that linguist involvement does not lead to increased accuracy on out-of-domain test sets compared to baseline, and adding a chatroom has no effect on the data. Linguist involvement does, however, lead to more challenging evaluation data and higher accuracy on some challenge sets, demonstrating the benefits of integrating expert analysis during data collection.

Crowdsourcing from non-experts is one of the most common approaches to collecting data and annotations in NLP. Even though it is such a fundamental tool in NLP, crowdsourcing use is largely guided by common practices and the personal experience of researchers. Developing a theory of crowdsourcing use for practical language problems remains an open challenge. However, there are various principles and practices that have proven effective in generating high quality and diverse data. This tutorial exposes NLP researchers to such data collection crowdsourcing methods and principles through a detailed discussion of a diverse set of case studies. The selection of case studies focuses on challenging settings where crowdworkers are asked to write original text or otherwise perform relatively unconstrained work. Through these case studies, we discuss in detail processes that were carefully designed to achieve data with specific properties, for example to require logical inference, grounded reasoning or conversational understanding. Each case study focuses on data collection crowdsourcing protocol details that often receive limited attention in research presentations, for example in conferences, but are critical for research success.

Pretrained language models, especially masked language models (MLMs) have seen success across many NLP tasks. However, there is ample evidence that they use the cultural biases that are undoubtedly present in the corpora they are trained on, implicitly creating harm with biased representations. To measure some forms of social bias in language models against protected demographic groups in the US, we introduce the Crowdsourced Stereotype Pairs benchmark (CrowS-Pairs). CrowS-Pairs has 1508 examples that cover stereotypes dealing with nine types of bias, like race, religion, and age. In CrowS-Pairs a model is presented with two sentences: one that is more stereotyping and another that is less stereotyping. The data focuses on stereotypes about historically disadvantaged groups and contrasts them with advantaged groups. We find that all three of the widely-used MLMs we evaluate substantially favor sentences that express stereotypes in every category in CrowS-Pairs. As work on building less biased models advances, this dataset can be used as a benchmark to evaluate progress.

The GLUE benchmark (Wang et al., 2019b) is a suite of language understanding tasks which has seen dramatic progress in the past year, with average performance moving from 70.0 at launch to 83.9, state of the art at the time of writing (May 24, 2019). Here, we measure human performance on the benchmark, in order to learn whether significant headroom remains for further progress. We provide a conservative estimate of human performance on the benchmark through crowdsourcing: Our annotators are non-experts who must learn each task from a brief set of instructions and 20 examples. In spite of limited training, these annotators robustly outperform the state of the art on six of the nine GLUE tasks and achieve an average score of 87.1. Given the fast pace of progress however, the headroom we observe is quite limited. To reproduce the data-poor setting that our annotators must learn in, we also train the BERT model (Devlin et al., 2019) in limited-data regimes, and conclude that low-resource sentence classification remains a challenge for modern neural network approaches to text understanding.

Latent structure models are a powerful tool for modeling compositional data, discovering linguistic structure, and building NLP pipelines. They are appealing for two main reasons: they allow incorporating structural bias during training, leading to more accurate models; and they allow discovering hidden linguistic structure, which provides better interpretability. This tutorial will cover recent advances in discrete latent structure models. We discuss their motivation, potential, and limitations, then explore in detail three strategies for designing such models: gradient approximation, reinforcement learning, and end-to-end differentiable methods. We highlight connections among all these methods, enumerating their strengths and weaknesses. The models we present and analyze have been applied to a wide variety of NLP tasks, including sentiment analysis, natural language inference, language modeling, machine translation, and semantic parsing. Examples and evaluation will be covered throughout. After attending the tutorial, a practitioner will be better informed about which method is best suited for their problem.

This paper introduces the Multi-Genre Natural Language Inference (MultiNLI) corpus, a dataset designed for use in the development and evaluation of machine learning models for sentence understanding. At 433k examples, this resource is one of the largest corpora available for natural language inference (a.k.a. recognizing textual entailment), improving upon available resources in both its coverage and difficulty. MultiNLI accomplishes this by offering data from ten distinct genres of written and spoken English, making it possible to evaluate systems on nearly the full complexity of the language, while supplying an explicit setting for evaluating cross-genre domain adaptation. In addition, an evaluation using existing machine learning models designed for the Stanford NLI corpus shows that it represents a substantially more difficult task than does that corpus, despite the two showing similar levels of inter-annotator agreement.

Latent tree learning models learn to parse a sentence without syntactic supervision, and use that parse to build the sentence representation. Existing work on such models has shown that, while they perform well on tasks like sentence classification, they do not learn grammars that conform to any plausible semantic or syntactic formalism (Williams et al., 2018a). Studying the parsing ability of such models in natural language can be challenging due to the inherent complexities of natural language, like having several valid parses for a single sentence. In this paper we introduce ListOps, a toy dataset created to study the parsing ability of latent tree models. ListOps sequences are in the style of prefix arithmetic. The dataset is designed to have a single correct parsing strategy that a system needs to learn to succeed at the task. We show that the current leading latent tree models are unable to learn to parse and succeed at ListOps. These models achieve accuracies worse than purely sequential RNNs.

This paper presents the results of the RepEval 2017 Shared Task, which evaluated neural network sentence representation learning models on the Multi-Genre Natural Language Inference corpus (MultiNLI) recently introduced by Williams et al. (2017). All of the five participating teams beat the bidirectional LSTM (BiLSTM) and continuous bag of words baselines reported in Williams et al. The best single model used stacked BiLSTMs with residual connections to extract sentence features and reached 74.5% accuracy on the genre-matched test set. Surprisingly, the results of the competition were fairly consistent across the genre-matched and genre-mismatched test sets, and across subsets of the test data representing a variety of linguistic phenomena, suggesting that all of the submitted systems learned reasonably domain-independent representations for sentence meaning.