TY - JOUR
AU - 
AB - Abstractive conversation summarization has received much attention recently. However, these generated summaries often suffer from insufficient, redundant, or incorrect content, largely due to the unstructured and complex characteristics of human-human interactions. To this end, we propose to explicitly model the rich structures in conversations for more precise and accurate conversation summariza- tion, by first incorporating discourse relations between utterances and action triples (“WHO- DOING- WHAT”) in utterances through struc- tured graphs to better encode conversations, and then designing a multi-granularity decoder to generate summaries by combining all lev- els of information. Experiments show that our proposed models outperform state-of-the- art methods and generalize well in other do- mains in terms of both automatic evaluations and human judgments. We have publicly re- leased our code at https://github.com/ GT-SALT/Structure-Aware-BART. 1 Introduction Figure 1: An example of discourse relation graph (a) and action graph (b) from one conversation in SAM- Online interaction has become an indispensable Sum (Gliwa et al., 2019). The annotated summary is component of everyday life and people are increas- Simon was on the phone before, so he didn’t here He- ingly using textual conversations to exchange ideas, len calling. Simon will fetch Helen some tissues. make plans, and 
TI - Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs
JF - Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
DO - 10.18653/v1/2021.naacl-main.109
DA - 2021-01-01
UR - https://www.deepdyve.com/lp/unpaywall/structure-aware-abstractive-conversation-summarization-via-discourse-YumyoHbwm3
DP - DeepDyve
ER -