We introduce a new large-scale NLI benchmark dataset, collected via an iterative, adversarial human-and-model-in-the-loop procedure. We show that training models on this new dataset leads to state-of-the-art performance on a variety of popular NLI benchmarks, while posing a more difficult challenge with its new test set. Our analysis sheds light on the shortcomings of current state-of-theart models, and shows that non-expert annotators are successful at finding their weaknesses. The data collection method can be applied in a never-ending learning scenario, becoming a moving target for NLU, rather than a static benchmark that will quickly saturate.

The increasing concern with misinformation has stimulated research efforts on automatic fact checking. The recentlyreleased FEVER dataset introduced a benchmark factverification task in which a system is asked to verify a claim using evidential sentences from Wikipedia documents. In this paper, we present a connected system consisting of three homogeneous neural semantic matching models that conduct document retrieval, sentence selection, and claim verification jointly for fact extraction and verification. For evidence retrieval (document retrieval and sentence selection), unlike traditional vector space IR models in which queries and sources are matched in some pre-designed term vector space, we develop neural models to perform deep semantic matching from raw textual input, assuming no intermediate term representation and no access to structured external knowledge bases. We also show that Pageview frequency can also help improve the performance of evidence retrieval results, that later can be matched by using our neural semantic matching network. For claim verification, unlike previous approaches that simply feed upstream retrieved evidence and the claim to a natural language inference (NLI) model, we further enhance the NLI model by providing it with internal semantic relatedness scores (hence integrating it with the evidence retrieval modules) and ontological WordNet features. Experiments on the FEVER dataset indicate that (1) our neural semantic matching method outperforms popular TF-IDF and encoder models, by significant margins on all evidence retrieval metrics, (2) the additional relatedness score and WordNet features improve the NLI model via better semantic awareness, and (3) by formalizing all three subtasks as a similar semantic matching problem and improving on all three stages, the complete model is able to achieve the state-of-the-art results on the FEVER test set (two times greater than baseline results). 1 2 The task is often termed as natural language inference (NLI).

Machine Reading at Scale (MRS) is a challenging task in which a system is given an input query and is asked to produce a precise output by "reading" information from a large knowledge base. The task has gained popularity with its natural combination of information retrieval (IR) and machine comprehension (MC). Advancements in representation learning have led to separated progress in both IR and MC; however, very few studies have examined the relationship and combined design of retrieval and comprehension at different levels of granularity, for development of MRS systems. In this work, we give general guidelines on system design for MRS by proposing a simple yet effective pipeline system with special consideration on hierarchical semantic retrieval at both paragraph and sentence level, and their potential effects on the downstream task. The system is evaluated on both fact verification and open-domain multihop QA, achieving state-of-the-art results on the leaderboard test sets of both FEVER and HOTPOTQA. To further demonstrate the importance of semantic retrieval, we present ablation and analysis studies to quantify the contribution of neural retrieval modules at both paragraph-level and sentence-level, and illustrate that intermediate semantic retrieval modules are vital for not only effectively filtering upstream information and thus saving downstream computation, but also for shaping upstream data distribution and providing better data for downstream modeling. 1

Success in natural language inference (NLI) should require a model to understand both lexical and compositional semantics. However, through adversarial evaluation, we find that several state-of-the-art models with diverse architectures are over-relying on the former and fail to use the latter. Further, this compositionality unawareness is not reflected via standard evaluation on current datasets. We show that removing RNNs in existing models or shuffling input words during training does not induce large performance loss despite the explicit removal of compositional information. Therefore, we propose a compositionality-sensitivity testing setup that analyzes models on natural examples from existing datasets that cannot be solved via lexical features alone (i.e., on which a bag-of-words model gives a high probability to one wrong label), hence revealing the models' actual compositionality awareness. We show that this setup not only highlights the limited compositional ability of current NLI models, but also differentiates model performance based on design, e.g., separating shallow bag-of-words models from deeper, linguistically-grounded tree-based models. Our evaluation setup is an important analysis tool: complementing currently existing adversarial and linguistically driven diagnostic evaluations, and exposing opportunities for future work on evaluating models' compositional understanding. 1 We release our adversaries, compositionality-sensitivity testing setups, and all code at https

We present a simple sequential sentence encoder for multi-domain natural language inference. Our encoder is based on stacked bidirectional LSTM-RNNs with shortcut connections and fine-tuning of word embeddings. The overall supervised model uses the above encoder to encode two input sentences into two vectors, and then uses a classifier over the vector combination to label the relationship between these two sentences as that of entailment, contradiction, or neural. Our ShortcutStacked sentence encoders achieve strong improvements over existing encoders on matched and mismatched multi-domain natural language inference (top singlemodel result in the EMNLP RepEval 2017 Shared Task (Nangia et al., 2017)). Moreover, they achieve the new state-of-theart encoding result on the original SNLI dataset (Bowman et al., 2015).

We introduce Dynabench, an open-source platform for dynamic dataset creation and model benchmarking. Dynabench runs in a web browser and supports human-and-model-inthe-loop dataset creation: annotators seek to create examples that a target model will misclassify, but that another person will not. In this paper, we argue that Dynabench addresses a critical need in our community: contemporary models quickly achieve outstanding performance on benchmark tasks but nonetheless fail on simple challenge examples and falter in real-world scenarios. With Dynabench, dataset creation, model development, and model assessment can directly inform each other, leading to more robust and informative benchmarks. We report on four initial NLP tasks, illustrating these concepts and highlighting the promise of the platform, and address potential objections to dynamic benchmarking as a new standard for the field.

We introduce a new large-scale NLI benchmark dataset, collected via an iterative, adversarial human-and-model-in-the-loop procedure. We show that training models on this new dataset leads to state-of-the-art performance on a variety of popular NLI benchmarks, while posing a more difficult challenge with its new test set. Our analysis sheds light on the shortcomings of current state-of-theart models, and shows that non-expert annotators are successful at finding their weaknesses. The data collection method can be applied in a never-ending learning scenario, becoming a moving target for NLU, rather than a static benchmark that will quickly saturate.

Despite the subjective nature of many NLP tasks, most NLU evaluations have focused on using the majority label with presumably high agreement as the ground truth. Less attention has been paid to the distribution of human opinions. We collect ChaosNLI, a dataset with a total of 464,500 annotations to study Collective HumAn OpinionS in oft-used NLI evaluation sets. This dataset is created by collecting 100 annotations per example for 3,113 examples in SNLI and MNLI and 1,532 examples in αNLI. Analysis reveals that: (1) high human disagreement exists in a noticeable amount of examples in these datasets;(2) the state-of-the-art models lack the ability to recover the distribution over human labels; (3) models achieve near-perfect accuracy on the subset of data with a high level of human agreement, whereas they can barely beat a random guess on the data with low levels of human agreement, which compose most of the common errors made by state-of-the-art models on the evaluation sets. This questions the validity of improving model performance on old metrics for the low-agreement part of evaluation datasets. Hence, we argue for a detailed examination of human agreement in future data collection efforts, and evaluating model outputs against the distribution over collective human opinions. 1