Can I read Repurposing Entailment for Multi-Hop Question Answering Tasks on EtoBox?

Repurposing Entailment for Multi-Hop Question Answering Tasks by Trivedi, Harsh; Kwon, Heeyoung; Khot, Tushar; Sabharwal, Ashish; Balasubramanian, Niranjan is a scholarly article available to read on EtoBox.

What is Repurposing Entailment for Multi-Hop Question Answering Tasks about?

Question Answering (QA) naturally reduces to an entailment problem, namely, verifying whether some text entails the answer to a question. However, for multi-hop QA tasks, which require reasoning with multiple sentences, it remains unclear how best to utilize entailment models pre-trained on large scale datasets such as SNLI, which are based on sentence pairs. We introduce Multee, a general architecture that can effectively use entailment models for multi-hop QA tasks. Multee uses (i) a local module that helps locate important sentences, thereby avoiding distracting information, and (ii) a global module that aggregates information by effectively incorporating importance weights. Importantly, we show that both modules can use entailment functions pre-trained on a large scale NLI datasets. We evaluate performance on MultiRC and OpenBookQA, two multihop QA datasets. When using an entailment function pre-trained on NLI datasets, Multee outperforms QA models trained only on the target QA datasets and the OpenAI transformer models. The code is available at https://github.com/StonyBrookNLP/multee.

Author

Trivedi, Harsh; Kwon, Heeyoung; Khot, Tushar; Sabharwal, Ashish; Balasubramanian, Niranjan

Published

2019

Language

EN