84 citations · 655 across the 44 of their papers we have counts for
5 papers · 1 filter
Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering
Sewon Min, Danqi Chen, Luke Zettlemoyer +1
We introduce an approach for open-domain question answering (QA) that retrieves and reads a passage graph, where vertices are passages of text and edges represent relationships tha…
Question Answering is a Format; When is it Useful?
Matt Gardner, Jonathan Berant, Hannaneh Hajishirzi +2
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…
A Discrete Hard EM Approach for Weakly Supervised Question Answering
Sewon Min, Danqi Chen, Hannaneh Hajishirzi +1
Many question answering (QA) tasks only provide weak supervision for how the answer should be computed. For example, TriviaQA answers are entities that can be mentioned multiple ti…
Multi-hop Reading Comprehension through Question Decomposition and Rescoring
Sewon Min, Victor Zhong, Luke Zettlemoyer +1
Multi-hop Reading Comprehension (RC) requires reasoning and aggregation across several paragraphs. We propose a system for multi-hop RC that decomposes a compositional question int…
Compositional Questions Do Not Necessitate Multi-hop Reasoning
Sewon Min, Eric Wallace, Sameer Singh +3
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 l…