Asking Effective and Diverse Questions: A Machine Reading Comprehension based Framework for Joint Entity-Relation Extraction

Abstract

<jats:p>Recent advances cast the entity-relation extraction to a multi-turn question answering (QA) task and provide an effective solution based on the machine reading comprehension (MRC) models. However, they use a single question to characterize the meaning of entities and relations, which is intuitively not enough because of the variety of context semantics. Meanwhile, existing models enumerate all relation types to generate questions, which is inefficient and easily leads to confusing questions. In this paper, we improve the existing MRC-based entity-relation extraction model through diverse question answering. First, a diversity question answering mechanism is introduced to detect entity spans and two answering selection strategies are designed to integrate different answers. Then, we propose to predict a subset of potential relations and filter out irrelevant ones to generate questions effectively. Finally, entity and relation extractions are integrated in an end-to-end way and optimized through joint learning. Experiment results show that the proposed method significantly outperforms baseline models, which improves the relation F1 to 62.1% (+1.9%) on ACE05 and 71.9% (+3.0%) on CoNLL04. Our implementation is available at https://github.com/TanyaZhao/MRC4ERE.</jats:p>

Revisiting the Negative Data of Distantly Supervised Relation Extraction

“…Last but not the least, relation classifier can be regarded as a pruning step when applied to practical tasks. Many existing methods treat relation extraction as question answering (Li et al, 2019;Zhao et al, 2020). However, without first identifying the relation, they all need to iterate over all the possible relations and ask diverse questions.…”

Enhancement of Target‐Oriented Opinion Words Extraction with Multiview‐Trained Machine Reading Comprehension Model

“…MRC is a flexible paradigm to infuse information between the given question and context and is naturally adapted to information extraction tasks [ 23 ]. Instead of only extract one span per passage, these methods modify the prediction layer and leverage sequence labeling technique to hand potential multiple answers and achieve state-of-the-art results on named entity recognition [ 24 ], relation extraction [ 25 ], and event argument extraction [ 7 , 26 ].…”

“…These works mainly investigate methods to build informative questions that contribute to identifying expected answer spans. For example, as suggested in [ 25 ], diverse questions templates yield better performances than a single question. In this work, we utilize the MRC-based model to extract target-oriented opinion words.…”

Enhancing Dialogue-based Relation Extraction by Speaker and Trigger Words Prediction

“…The task of relation extraction is to identify the relation facts between two arguments from plain text, which is the fundamental step of many natural language processing applications. Recent years have seen increasing efforts on sentence-level RE, e.g., relations only hold within a single sentence (Fu et al, 2019;Luan et al, 2019;Zhao et al, 2020;Wang and Lu, 2020;. To adapt to complex scenarios, some current works have moved forward to the document-level RE, e.g., relations can exist across multiple sentences (Yao et al, 2019;Nan et al, 2020;Jain et al, 2020;Zhou et al, 2021).…”