基於對話中的觸發詞增強對話系統關係抽取網路

Abstract

對話系統關係抽取的旨在識別任意兩個實體在給定的對話中的關係。在對話的過程中，語者可能會透過明示或暗示的線索表達出彼此之間的關係，這種線索可以被稱作觸發詞。然而，並不是所有的目標資料都有觸發詞的標記，所以想要利用這種資訊來增進表現是具有挑戰性的。 因此，本篇論文提出了使用有標記觸發詞的資料學習識別觸發詞，再將已習得的尋找觸發詞的能力遷移到其他的資料上已得到更好的表現。實驗顯示本論文所提出的方法可以有效在訓練時未看過的關係上提升關係抽取的表現，也展示了所提出的尋找觸發詞的模型在不同領域和資料上的遷移能力。

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 pieces of evidence called “triggers." However, trigger annotations may not be always available for the target data, so it is challenging to leverage such information for enhancing performance. Therefore, this paper proposes to learn how to identify triggers from the data with trigger annotations and then transfer 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.