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

## TL;DR

This paper introduces E3, a novel model for conversational machine reading that extracts decision rules from procedural texts, reasons about their entailment, and edits questions to improve answer accuracy and explainability.

## Contribution

E3 is the first model to jointly extract, reason, and edit decision rules for conversational machine reading, achieving state-of-the-art results on the ShARC dataset.

## Key findings

- E3 outperforms existing systems and baselines on ShARC dataset.
- E3 provides more explainability by highlighting information gaps.
- E3 sets a new state-of-the-art in conversational rule understanding.

## Abstract

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.