Bridging Anaphora Resolution as Question Answering
Author:
Preprint
Abstract
Most previous studies on bridging anaphora resolution (Poesio et al., 2004; Hou et al., 2013b; Hou, 2018a) use the pairwise model to tackle the problem and assume that the gold mention information is given. In this paper, we cast bridging anaphora resolution as question answering based on context. This allows us to find the antecedent for a given anaphor without knowing any gold mention information (except the anaphor itself). We present a question answering framework (BARQA) for this task, which leverages the power of transfer learning. Furthermore, we propose a novel method to generate a large amount of "quasi-bridging" training data. We show that our model pre-trained on this dataset and fine-tuned on a small amount of in-domain dataset achieves new state-of-the-art results for bridging anaphora resolution on two bridging corpora (ISNotes (Markert et al., 2012) and BASHI (Roesiger, 2018)).Keywords
All Related Versions
This publication has 3 references indexed in Scilit:
- SpanBERT: Improving Pre-training by Representing and Predicting SpansTransactions of the Association for Computational Linguistics, 2020
- Unrestricted Bridging ResolutionComputational Linguistics, 2018
- Definiteness and the Processing of Noun Phrases in Natural DiscourseJournal of Semantics, 1990