Implicit Discourse Relation Identification for Open-domain Dialogues

By Mingyu Derek Ma, Kevin K. Bowden, JiaQi Wu, Wen Cui, Marilyn A. Walker. 2019

24 citations recorded by the source corpus.

Discourse relation identification has been an active area of research for many years, and the challenge of identifying implicit relations remains largely an unsolved task, especially in the context of an open-domain dialogue system. Previous work primarily relies on a corpora of formal text which is inherently non-dialogic, i.e., news and journals. This data however is not suitable to handle the nuances of informal dialogue nor is it capable of navigating the plethora of valid topics present in open-domain dialogue. In this paper, we designed a novel discourse relation identification pipeline specifically tuned for open-domain dialogue systems. We firstly propose a method to automatically extract the implicit discourse relation argument pairs and labels from a dataset of dialogic turns, resulting in a novel corpus of discourse relation pairs; the first of its kind to attempt to identify the discourse relations connecting the dialogic turns in open-domain discourse. Moreover, we have taken the first steps to leverage the dialogue features unique to our task to further improve the identification of such relations by performing feature ablation and incorporating dialogue features to enhance the state-of-the-art model.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Tom Young
2. Erik Cambria
3. Jinjie Ni
4. Fuzhao Xue
5. Vlad Pandelea
6. Qing Li
7. Haopeng Ren
8. Yi Cai

Citations in the corpus

• A Two-phase Prototypical Network Model for Incremental Few-shot Relation Classification (2020, background): “, 2019) and dialogue systems (Ma et al., 2019).”
• Recent advances in deep learning based dialogue systems: a systematic survey (2021, methodology): “Empathy means being able to sense other people’s feelings (Ma et al., 2020b). An empathetic dialogue system can sense the user’s emotional changes and produce appropriate responses with a certain sentiment. This is an essential topic in chit-chat systems because it directly affects the user’s feelin”