Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading
This work addresses document interpretation and dialog understanding for conversational AI systems, representing an incremental improvement with specific gains in accuracy and generation metrics.
The paper tackled conversational machine reading by proposing Discern, a discourse-aware entailment reasoning network that splits documents into elementary discourse units and predicts entailment from user feedback, achieving state-of-the-art results of 78.3% macro-averaged accuracy on decision making and 64.0 BLEU1 on follow-up question generation on the ShARC benchmark.
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.