Relation Extraction in Dialogues: A Deep Learning Model Based on the Generality and Specialty of Dialogue Text

Mengjia Zhou, Donghong Ji, Fei Li

Abstract: Relation extraction from dialogue text is an innovative task in natural language processing. In addition to the general characteristics of general relation extraction from news or scientific publication text, the task is of certain special features. For example, the context in dialogues frequently switches between speakers, and there exist rich pronoun anaphora in the dialogue text. Thus, it is important for the model to be aware of such features to improve the performance. Taking these factors together, we propose an end to-end neural model for dialogue-based relation extraction, which includes four modules to handle the problems existing in the task from different aspects: (1) the word-relation attention to model a natural intuition that different words contribute differently for the identification of different relations; (2) the graph reasoning to consider the global context information in the dialogue that contains many inter-sentence relations; (3) the speaker embeddings to incorporate speaker information into our model; (4) the speaker coreference to associate pronouns with speakers and enrich the information of graph reasoning. Our model was evaluated on a recently-proposed dataset for dialogue-based relation extraction, and achieved the state of the-art performance. We show that our proposed modules are effective through ablation studies. Our work can be a competitive benchmark for the study of dialogue based relation extraction.

External IDs:dblp:journals/taslp/ZhouJL21