3.1k citations · 3.6k across the 29 of their papers we have counts for
7 papers · 1 filter
QuaRel: A Dataset and Models for Answering Questions about Qualitative Relationships
Oyvind Tafjord, Peter Clark, Matt Gardner +2
Many natural language questions require recognizing and reasoning with qualitative relationships (e.g., in science, economics, and medicine), but are challenging to answer with cor…
Dissecting Contextual Word Embeddings: Architecture and Representation
Matthew E. Peters, Mark Neumann, Luke Zettlemoyer +1
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…
Policy Shaping and Generalized Update Equations for Semantic Parsing from Denotations
Dipendra Misra, Ming-Wei Chang, Xiaodong He +1
Semantic parsing from denotations faces two key challenges in model training: (1) given only the denotations (e.g., answers), search for good candidate semantic parses, and (2) cho…
Reasoning about Actions and State Changes by Injecting Commonsense Knowledge
Niket Tandon, Bhavana Dalvi Mishra, Joel Grus +3
Comprehending procedural text, e.g., a paragraph describing photosynthesis, requires modeling actions and the state changes they produce, so that questions about entities at differ…
QuAC : Question Answering in Context
Eunsol Choi, He He, Mohit Iyyer +5
We present QuAC, a dataset for Question Answering in Context that contains 14K information-seeking QA dialogs (100K questions in total). The dialogs involve two crowd workers: (1)…
Tracking State Changes in Procedural Text: A Challenge Dataset and Models for Process Paragraph Comprehension
Bhavana Dalvi Mishra, Lifu Huang, Niket Tandon +2
We present a new dataset and models for comprehending paragraphs about processes (e.g., photosynthesis), an important genre of text describing a dynamic world. The new dataset, Pro…
Natural Language to Structured Query Generation via Meta-Learning
Po-Sen Huang, Chenglong Wang, Rishabh Singh +2
In conventional supervised training, a model is trained to fit all the training examples. However, having a monolithic model may not always be the best strategy, as examples could…