Papers
See AI2's Award Winning Papers
Learn more about AI2's Lasting Impact Award
Viewing 201-210 of 263 papers
ORB: An Open Reading Benchmark for Comprehensive Evaluation of Machine Reading Comprehension
Dheeru Dua, Ananth Gottumukkala, Alon Talmor, Sameer Singh, Matt GardnerEMNLP • MRQA Workshop • 2019 Reading comprehension is one of the crucial tasks for furthering research in natural language understanding. A lot of diverse reading comprehension datasets have recently been introduced to study various phenomena in natural language, ranging from simple…AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models
Eric Wallace, Jens Tuyls, Junlin Wang, Sanjay Subramanian, Matthew Gardner, Sameer SinghEMNLP • 2019 Neural NLP models are increasingly accurate but are imperfect and opaque---they break in counterintuitive ways and leave end users puzzled at their behavior. Model interpretation methods ameliorate this opacity by providing explanations for specific model…Do NLP Models Know Numbers? Probing Numeracy in Embeddings
Eric Wallace, Yizhong Wang, Sujian Li, Sameer Singh, Matt GardnerEMNLP • 2019 The ability to understand and work with numbers (numeracy) is critical for many complex reasoning tasks. Currently, most NLP models treat numbers in text in the same way as other tokens---they embed them as distributed vectors. Is this enough to capture…Efficient Navigation with Language Pre-training and Stochastic Sampling
Xiujun Li, Chunyuan Li, Qiaolin Xia, Yonatan Bisk, Asli Celikyilmaz, Jianfeng Gao, Noah 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…Global Reasoning over Database Structures for Text-to-SQL Parsing
Ben Bogin, Matt Gardner, Jonathan BerantEMNLP • 2019 State-of-the-art semantic parsers rely on auto-regressive decoding, emitting one symbol at a time. When tested against complex databases that are unobserved at training time (zero-shot), the parser often struggles to select the correct set of database…Knowledge Enhanced Contextual Word Representations
Matthew E. Peters, Mark Neumann, Robert L. Logan, Roy Schwartz, Vidur Joshi, Sameer Singh, and Noah A. SmithEMNLP • 2019 Contextual word representations, typically trained on unstructured, unlabeled text, do not contain any explicit grounding to real world entities and are often unable to remember facts about those entities. We propose a general method to embed multiple…Low-Resource Parsing with Crosslingual Contextualized Representations
Phoebe Mulcaire, Jungo Kasai, Noah A. SmithCoNLL • 2019 Despite advances in dependency parsing, languages with small treebanks still present challenges. We assess recent approaches to multilingual contextual word representations (CWRs), and compare them for crosslingual transfer from a language with a large…On the Limits of Learning to Actively Learn Semantic Representations
Omri Koshorek, Gabriel Stanovsky, Yichu Zhou, Vivek Srikumar and Jonathan BerantCoNLL • 2019One of the goals of natural language understanding is to develop models that map sentences into meaning representations. However, training such models requires expensive annotation of complex structures, which hinders their adoption. Learning to actively…Best Paper Honorable MentionPaLM: A Hybrid Parser and Language Model
Hao Peng, Roy Schwartz, Noah A. SmithEMNLP • 2019 We present PaLM, a hybrid parser and neural language model. Building on an RNN language model, PaLM adds an attention layer over text spans in the left context. An unsupervised constituency parser can be derived from its attention weights, using a greedy…Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning
Pradeep Dasigi, Nelson F. Liu, Ana Marasovic, Noah A. Smith, Matt GardnerEMNLP • 2019 Machine comprehension of texts longer than a single sentence often requires coreference resolution. However, most current reading comprehension benchmarks do not contain complex coreferential phenomena and hence fail to evaluate the ability of models to…