Papers
See AI2's Award Winning Papers
Learn more about AI2's Lasting Impact Award
Viewing 241-250 of 293 papers
RNN Architecture Learning with Sparse Regularization
Jesse Dodge, Roy Schwartz, Hao Peng, Noah A. SmithEMNLP • 2019 Neural models for NLP typically use large numbers of parameters to reach state-of-the-art performance, which can lead to excessive memory usage and increased runtime. We present a structure learning method for learning sparse, parameter-efficient NLP models…Show Your Work: Improved Reporting of Experimental Results
Jesse Dodge, Suchin Gururangan, Dallas Card, Roy Schwartz, Noah A. SmithEMNLP • 2019 Research in natural language processing proceeds, in part, by demonstrating that new models achieve superior performance (e.g., accuracy) on held-out test data, compared to previous results. In this paper, we demonstrate that test-set performance scores alone…Topics to Avoid: Demoting Latent Confounds in Text Classification
Sachin Kumar, Shuly Wintner, Noah A. Smith, Yulia TsvetkovEMNLP • 2019 Despite impressive performance on many text classification tasks, deep neural networks tend to learn frequent superficial patterns that are specific to the training data and do not always generalize well. In this work, we observe this limitation with respect…Universal Adversarial Triggers for Attacking and Analyzing NLP
Eric Wallace, Shi Feng, Nikhil Kandpal, Matthew Gardner, Sameer Singh EMNLP • 2019 dversarial examples highlight model vulnerabilities and are useful for evaluation and interpretation. We define universal adversarial triggers: input-agnostic sequences of tokens that trigger a model to produce a specific prediction when concatenated to any…Y'all should read this! Identifying Plurality in Second-Person Personal Pronouns in English Texts
Gabriel Stanovsky, Ronen TamariEMNLP • W-NUT • 2019 Distinguishing between singular and plural "you" in English is a challenging task which has potential for downstream applications, such as machine translation or coreference resolution. While formal written English does not distinguish between these cases…Compositional Questions Do Not Necessitate Multi-hop Reasoning
Sewon Min, Eric Wallace, Sameer Singh, Matt Gardner, Hannaneh Hajishirzi, Luke ZettlemoyerACL • 2019 Multi-hop reading comprehension (RC) questions are challenging because they require reading and reasoning over multiple paragraphs. We argue that it can be difficult to construct large multi-hop RC datasets. For example, even highly compositional questions…GrapAL: Connecting the Dots in Scientific Literature
Christine Betts, Joanna Power, Waleed AmmarACL • 2019 We introduce GrapAL (Graph database of Academic Literature), a versatile tool for exploring and investigating a knowledge base of scientific literature, that was semi-automatically constructed using NLP methods. GrapAL satisfies a variety of use cases and…The Risk of Racial Bias in Hate Speech Detection
Maarten Sap, Dallas Card, Saadia Gabriel, Yejin Choi, Noah A. SmithACL • 2019 We investigate how annotators’ insensitivity to differences in dialect can lead to racial bias in automatic hate speech detection models, potentially amplifying harm against minority populations. We first uncover unexpected correlations between surface…Question Answering is a Format; When is it Useful?
Matt Gardner, Jonathan Berant, Hannaneh Hajishirzi, Alon Talmor, Sewon MinarXiv • 2019 Recent years have seen a dramatic expansion of tasks and datasets posed as question answering, from reading comprehension, semantic role labeling, and even machine translation, to image and video understanding. With this expansion, there are many differing…Robust Navigation with Language Pretraining and Stochastic Sampling
Xiujun Li, Chunyuan Li, Qiaolin Xia, Yonatan Bisk, Asli Celikyilmaz, Jianfeng Gao, Noah A. Smith, Yejin ChoiEMNLP • 2019 Core to the vision-and-language navigation (VLN) challenge is building robust instruction representations and action decoding schemes, which can generalize well to previously unseen instructions and environments. In this paper, we report two simple but highly…