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

by   Yifan Gao, et al.

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.


page 1

page 2

page 3

page 4


EMT: Explicit Memory Tracker with Coarse-to-Fine Reasoning for Conversational Machine Reading

The goal of conversational machine reading is to answer user questions g...

Open-Retrieval Conversational Machine Reading

In conversational machine reading, systems need to interpret natural lan...

Dialogue Graph Modeling for Conversational Machine Reading

Conversational Machine Reading (CMR) aims at answering questions in a co...

E3: Entailment-driven Extracting and Editing for Conversational Machine Reading

Conversational machine reading systems help users answer high-level ques...

DAGN: Discourse-Aware Graph Network for Logical Reasoning

Recent QA with logical reasoning questions requires passage-level relati...

Representation Learning for Conversational Data using Discourse Mutual Information Maximization

Although many pretrained models exist for text or images, there have bee...

Smoothing Dialogue States for Open Conversational Machine Reading

Conversational machine reading (CMR) requires machines to communicate wi...