TREND: Trigger-Enhanced Relation-Extraction Network for Dialogues
This work addresses a domain-specific challenge in natural language processing for dialogue systems, with incremental improvements in handling unannotated data.
The paper tackles the problem of dialogue relation extraction (DRE) by leveraging trigger annotations to enhance performance, showing that the proposed approach improves relation extraction for unseen relations and demonstrates transferability across domains and datasets.
The goal of dialogue relation extraction (DRE) is to identify the relation between two entities in a given dialogue. During conversations, speakers may expose their relations to certain entities by explicit or implicit clues, such evidences called "triggers". However, trigger annotations may not be always available for the target data, so it is challenging to leverage such information for enhancing the performance. Therefore, this paper proposes to learn how to identify triggers from the data with trigger annotations and then transfers the trigger-finding capability to other datasets for better performance. The experiments show that the proposed approach is capable of improving relation extraction performance of unseen relations and also demonstrate the transferability of our proposed trigger-finding model across different domains and datasets.