Language-Agnostic Transformers and Assessing ChatGPT-Based Query Rewriting for Multilingual Document-Grounded QA

Anonymous

Paper Type: short - archival

Keywords: Question Answering, Query Rewriting, Language agnostic, multilingual, multilingual conversational retriever

TL;DR: Compares language-agnostic and language-aware paradigms for multilingual document-grounded dialogue, showing that the former is more effective, and concludes that query rewriting using LLMs is ineffective due to irrelevant topics and topic switching.

Abstract: The DialDoc 2023 shared task has expanded the document-grounded dialogue task to encompass multiple languages, despite having limited annotated data. This paper assesses the effectiveness of both language-agnostic and language-aware paradigms for multilingual pre-trained transformer models in a bi-encoder-based dense passage retriever (DPR), concluding that the language-agnostic approach is superior. Additionally, the study investigates the impact of query rewriting techniques using large language models, such as ChatGPT, on multilingual, document-grounded question-answering systems. The experiments conducted demonstrate that, for the examples examined, query rewriting does not enhance performance compared to the original queries. This failure is due to topic switching in final dialogue turns and irrelevant topics being considered for query rewriting.