LANGUAGE-AGNOSTIC TRANSFORMERS AND ASSESSING CHATGPT-BASED QUERY REWRITING FOR MULTILINGUAL DOCUMENT-GROUNDED QA

Abstract

The DialDoc 2023 shared task has expanded the document-grounded dialogue task to en- compass multiple languages, despite having limited annotated data. This paper assesses the effectiveness of both language-agnostic and language-aware paradigms for multilingual pretrained transformer models in a bi-encoder- based dense passage retriever (DPR), conclud- ing that the language-agnostic approach is su- perior. Additionally, the study investigates the impact of query rewriting techniques us- ing large language models, such as ChatGPT, on multilingual, document-grounded question- answering systems. The experiments con- ducted demonstrate that, for the examples ex- amined, query rewriting does not enhance per- formance compared to the original queries. This failure is due to topic switching in final dialogue turns and irrelevant topics being considered for query rewriting