Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading

October 05, 2020 · Entered Twilight · 🏛 Conference on Empirical Methods in Natural Language Processing

"Last commit was 5.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, README.md, evaluator.py, evaluator_qg.py, fix_question.py, model, preprocess_decision.py, preprocess_span.py, qg.py, segedu, train_sharc.py, unilmqg

Authors Yifan Gao, Chien-Sheng Wu, Jingjing Li, Shafiq Joty, Steven C. H. Hoi, Caiming Xiong, Irwin King, Michael R. Lyu arXiv ID 2010.01838 Category cs.CL: Computation & Language Cross-listed cs.AI, cs.LG Citations 53 Venue Conference on Empirical Methods in Natural Language Processing Repository https://github.com/Yifan-Gao/Discern ⭐ 38 Last Checked 1 month ago

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. Code and models are released at https://github.com/Yifan-Gao/Discern.