Document interpretation and dialog understanding are the two major challenges for conversational machine reading. In this work, we propose DISCERN, a discourse-aware entailment reasoning network to strengthen the connection and enhance the understanding for both document and dialog. Specifically, we split the document into clause-like elementary discourse units (EDU) using a pre-trained discourse segmentation model, and we train our model in a weakly-supervised manner to predict whether each EDU is entailed by the user feedback in a conversation. Based on the learned EDU and entailment representations, we either reply to the user our final decision “yes/no/irrelevant” of the initial question, or generate a follow-up question to inquiry more information. Our experiments on the ShARC benchmark (blind, held-out test set) show that DISCERN achieves state-of-the-art results of 78.3% macro-averaged accuracy on decision making and 64.0 BLEU1 on follow-up question generation.

@inproceedings{Gao-et-al-emnlp-20, abstract = {Document interpretation and dialog understanding are the two major challenges for conversational machine reading. In this work, we propose DISCERN, a discourse-aware entailment reasoning network to strengthen the connection and enhance the understanding for both document and dialog. Specifically, we split the document into clause-like elementary discourse units (EDU) using a pre-trained discourse segmentation model, and we train our model in a weakly-supervised manner to predict whether each EDU is entailed by the user feedback in a conversation. Based on the learned EDU and entailment representations, we either reply to the user our final decision “yes/no/irrelevant” of the initial question, or generate a follow-up question to inquiry more information. Our experiments on the ShARC benchmark (blind, held-out test set) show that DISCERN achieves state-of-the-art results of 78.3% macro-averaged accuracy on decision making and 64.0 BLEU1 on follow-up question generation.}, address = {Punta Cana, Dominican Republic}, author = {Yifan Gao and Chien-Sheng Wu and Jingjing Li and Shafiq Joty and Steven Hoi and Caiming Xiong and Irwin King and Michael Lyu}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing}, numpages = {9}, pages = {2439–-2449}, publisher = {ACL}, series = {EMNLP'20}, title = {Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading}, url = {https://www.aclweb.org/anthology/2020.emnlp-main.191/}, year = {2020} }