Papers
See AI2's Award Winning Papers
Learn more about AI2's Lasting Impact Award
Viewing 191-200 of 222 papers
Inoculation by Fine-Tuning: A Method for Analyzing Challenge Datasets
Nelson F. Liu, Roy Schwartz, Noah SmithNAACL • 2019 Several datasets have recently been constructed to expose brittleness in models trained on existing benchmarks. While model performance on these challenge datasets is significantly lower compared to the original benchmark, it is unclear what particular…Iterative Search for Weakly Supervised Semantic Parsing
Pradeep Dasigi, Matt Gardner, Shikhar Murty, Luke Zettlemoyer, Ed HovyNAACL • 2019 Training semantic parsers from question-answer pairs typically involves searching over an exponentially large space of logical forms, and an unguided search can easily be misled by spurious logical forms that coincidentally evaluate to the correct answer. We…Linguistic Knowledge and Transferability of Contextual Representations
Nelson F. Liu, Matt Gardner, Yonatan Belinkov, Matthew Peters, Noah A. SmithNAACL • 2019 Contextual word representations derived from large-scale neural language models are successful across a diverse set of NLP tasks, suggesting that they encode useful and transferable features of language. To shed light on the linguistic knowledge they capture…Polyglot Contextual Representations Improve Crosslingual Transfer
Phoebe Mulcaire, Jungo Kasai, Noah A. SmithNAACL • 2019 We introduce a method to produce multilingual contextual word representations by training a single language model on text from multiple languages. Our method combines the advantages of contextual word representations with those of multilingual representation…ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning
Maarten Sap, Ronan Le Bras, Emily Allaway, Chandra Bhagavatula, Nicholas Lourie, Hannah Rashkin, Brendan Roof, Noah A. Smith, Yejin ChoiAAAI • 2019 We present ATOMIC, an atlas of everyday commonsense reasoning, organized through 877k textual descriptions of inferential knowledge. Compared to existing resources that center around taxonomic knowledge, ATOMIC focuses on inferential knowledge organized as…QuaRel: A Dataset and Models for Answering Questions about Qualitative Relationships
Oyvind Tafjord, Peter Clark, Matt Gardner, Wen-tau Yih, Ashish SabharwalAAAI • 2019 Many natural language questions require recognizing and reasoning with qualitative relationships (e.g., in science, economics, and medicine), but are challenging to answer with corpus-based methods. Qualitative modeling provides tools that support such…Dissecting Contextual Word Embeddings: Architecture and Representation
Matthew Peters, Mark Neumann, Wen-tau Yih, and Luke ZettlemoyerEMNLP • 2018 Contextual word representations derived from pre-trained bidirectional language models (biLMs) have recently been shown to provide significant improvements to the state of the art for a wide range of NLP tasks. However, many questions remain as to how and why…Neural Cross-Lingual Named Entity Recognition with Minimal Resources
Jiateng Xie, Zhilin Yang, Graham Neubig, Noah A. Smith, Jaime CarbonellEMNLP • 2018 For languages with no annotated resources, unsupervised transfer of natural language processing models such as named-entity recognition (NER) from resource-rich languages would be an appealing capability. However, differences in words and word order across…Rational Recurrences
Hao Peng, Roy Schwartz, Sam Thomson, and Noah A. SmithEMNLP • 2018 Despite the tremendous empirical success of neural models in natural language processing, many of them lack the strong intuitions that accompany classical machine learning approaches. Recently, connections have been shown between convolutional neural networks…Reasoning about Actions and State Changes by Injecting Commonsense Knowledge
Niket Tandon, Bhavana Dalvi Mishra, Joel Grus, Wen-tau Yih, Antoine Bosselut, Peter ClarkEMNLP • 2018 Comprehending procedural text, e.g., a paragraph describing photosynthesis, requires modeling actions and the state changes they produce, so that questions about entities at different timepoints can be answered. Although several recent systems have shown…