Dialogue-based relation extraction (DiaRE) aims to detect the structural information from unstructured utterances in dialogues. Existing relation extraction models may be unsatisfactory under such a conversational setting, due to the entangled logic and information sparsity issues in utterances involving multiple speakers. To this end, we introduce SOLS, a novel model which can explicitly induce speaker-oriented latent structures for better DiaRE. Specifically, we learn latent structures to capture the relationships among tokens beyond the utterance boundaries, alleviating the entangled logic issue. During the learning process, our speaker-specific regularization method progressively highlights speaker-related key clues and erases the irrelevant ones, alleviating the information sparsity issue. Experiments on three public datasets demonstrate the effectiveness of our proposed approach.
@article{arxiv.2109.05182,
title = {Speaker-Oriented Latent Structures for Dialogue-Based Relation Extraction},
author = {Guoshun Nan and Guoqing Luo and Sicong Leng and Yao Xiao and Wei Lu},
journal= {arXiv preprint arXiv:2109.05182},
year = {2021}
}
Comments
The experiment part is insufficient, while we are not planning to improve it for now. To avoid potential confusion and to ensure the quality of arxiv papers, we would like to withdraw this submission