Unification-based Reconstruction of Multi-hop Explanations for Science Questions

Marco Valentino, Mokanarangan Thayaparan, André Freitas

Information Retrieval, Search and Question Answering Long paper Paper

Gather-2A: Apr 22, Gather-2A: Apr 22 (13:00-15:00 UTC) [Join Gather Meeting]

You can open the pre-recorded video in separate windows.

Abstract: This paper presents a novel framework for reconstructing multi-hop explanations in science Question Answering (QA). While existing approaches for multi-hop reasoning build explanations considering each question in isolation, we propose a method to leverage explanatory patterns emerging in a corpus of scientific explanations. Specifically, the framework ranks a set of atomic facts by integrating lexical relevance with the notion of unification power, estimated analysing explanations for similar questions in the corpus. An extensive evaluation is performed on the Worldtree corpus, integrating k-NN clustering and Information Retrieval (IR) techniques. We present the following conclusions: (1) The proposed method achieves results competitive with Transformers, yet being orders of magnitude faster, a feature that makes it scalable to large explanatory corpora (2) The unification-based mechanism has a key role in reducing semantic drift, contributing to the reconstruction of many hops explanations (6 or more facts) and the ranking of complex inference facts (+12.0 Mean Average Precision) (3) Crucially, the constructed explanations can support downstream QA models, improving the accuracy of BERT by up to 10% overall.
NOTE: Video may display a random order of authors. Correct author list is at the top of this page.

Connected Papers in EACL2021

Similar Papers

Learning From Revisions: Quality Assessment of Claims in Argumentation at Scale
Gabriella Skitalinskaya, Jonas Klaff, Henning Wachsmuth,
Knowledge Base Question Answering through Recursive Hypergraphs
Naganand yadati, Dayanidhi R S, Vaishnavi S, Indira K M, srinidhi g,
Discourse Understanding and Factual Consistency in Abstractive Summarization
Saadia Gabriel, Antoine Bosselut, Jeff Da, Ari Holtzman, Jan Buys, Kyle Lo, Asli Celikyilmaz, Yejin Choi,
Complementary Evidence Identification in Open-Domain Question Answering
Xiangyang Mou, Mo Yu, Shiyu Chang, Yufei Feng, Li Zhang, Hui Su,