Fluent Response Generation for Conversational Question Answering

TL;DR

This paper introduces a novel approach for conversational question answering that integrates natural language generation with data augmentation, resulting in more fluent and contextually appropriate responses, as validated by human evaluations.

Contribution

It presents a SEQ2SEQ NLG-based method with data augmentation and ranking to improve response fluency and correctness in conversational QA systems.

Findings

Outperforms baseline models in human evaluations

Effective data augmentation with syntactic transformations

Scalable to larger datasets like CoQA

Abstract

Question answering (QA) is an important aspect of open-domain conversational agents, garnering specific research focus in the conversational QA (ConvQA) subtask. One notable limitation of recent ConvQA efforts is the response being answer span extraction from the target corpus, thus ignoring the natural language generation (NLG) aspect of high-quality conversational agents. In this work, we propose a method for situating QA responses within a SEQ2SEQ NLG approach to generate fluent grammatical answer responses while maintaining correctness. From a technical perspective, we use data augmentation to generate training data for an end-to-end system. Specifically, we develop Syntactic Transformations (STs) to produce question-specific candidate answer responses and rank them using a BERT-based classifier (Devlin et al., 2019). Human evaluation on SQuAD 2.0 data (Rajpurkar et al., 2018) demonstrate that the proposed model outperforms baseline CoQA and QuAC models in generating conversational responses. We further show our model's scalability by conducting tests on the CoQA dataset. The code and data are available at https://github.com/abaheti95/QADialogSystem.