# Investigating the use of Paraphrase Generation for Question Reformulation in the FRANK QA system

arXiv: https://arxiv.org/abs/2206.02737 · HTML: https://mlsanity.com/paper/2206.02737/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 35 references that are in the map.
- First posted on arXiv 6 Jun 2022.

## Builds on (most cited first, 8 of 8)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings](https://mlsanity.com/paper/1909.00512/) (2019)
- [Coarse-to-Fine Decoding for Neural Semantic Parsing](https://mlsanity.com/paper/1805.04793/) (2018)
- [BLEU might be Guilty but References are not Innocent](https://mlsanity.com/paper/2004.06063/) (2020)
- [Learning to Paraphrase for Question Answering](https://mlsanity.com/paper/1708.06022/) (2017)
- [ComQA: A Community-sourced Dataset for Complex Factoid Question Answering with Paraphrase Clusters](https://mlsanity.com/paper/1809.09528/) (2018)
- [Learning Paraphrastic Sentence Embeddings from Back-Translated Bitext](https://mlsanity.com/paper/1706.01847/) (2017)
- [Factorising Meaning and Form for Intent-Preserving Paraphrasing](https://mlsanity.com/paper/2105.15053/) (2021)

## Built on by (most cited first, 1 of 1)

- [Instant Answering in E-Commerce Buyer-Seller Messaging using Message-to-Question Reformulation](https://mlsanity.com/paper/2401.09785/) (2024)

## Abstract (arXiv)

We present a study into the ability of paraphrase generation methods to increase the variety of natural language questions that the FRANK Question Answering system can answer. We first evaluate paraphrase generation methods on the LC-QuAD 2.0 dataset using both automatic metrics and human judgement, and discuss their correlation. Error analysis on the dataset is also performed using both automatic and manual approaches, and we discuss how paraphrase generation and evaluation is affected by data points which contain error. We then simulate an implementation of the best performing paraphrase generation method (an English-French backtranslation) into FRANK in order to test our original hypothesis, using a small challenge dataset. Our two main conclusions are that cleaning of LC-QuAD 2.0 is required as the errors present can affect evaluation; and that, due to limitations of FRANK's parser, paraphrase generation is not a method which we can rely on to improve the variety of natural language questions that FRANK can answer.