CLAILGJun 12, 2019

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

arXiv:1906.05373v21099 citationsHas Code
Originality Incremental advance
AI Analysis

This addresses the challenge of helping users answer high-level questions when rules are unclear, with incremental improvements in performance and explainability.

The paper tackles the problem of conversational machine reading, where systems must extract decision rules from procedural texts and determine which rules are entailed by conversation history to ask users questions, achieving a new state-of-the-art on the ShARC dataset.

Conversational machine reading systems help users answer high-level questions (e.g. determine if they qualify for particular government benefits) when they do not know the exact rules by which the determination is made(e.g. whether they need certain income levels or veteran status). The key challenge is that these rules are only provided in the form of a procedural text (e.g. guidelines from government website) which the system must read to figure out what to ask the user. We present a new conversational machine reading model that jointly extracts a set of decision rules from the procedural text while reasoning about which are entailed by the conversational history and which still need to be edited to create questions for the user. On the recently introduced ShARC conversational machine reading dataset, our Entailment-driven Extract and Edit network (E3) achieves a new state-of-the-art, outperforming existing systems as well as a new BERT-based baseline. In addition, by explicitly highlighting which information still needs to be gathered, E3 provides a more explainable alternative to prior work. We release source code for our models and experiments at https://github.com/vzhong/e3.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes