Improving Korean-English Cross-Lingual Retrieval: A Data-Centric Study of Language Composition and Model Merging
Year: 2025
Type: preprint
Abstract: With the increasing utilization of multilingual text information, Cross-Lingual Information Retrieval (CLIR) has become a crucial research area. However, the impact of training data composition on both CLIR and Mono-Lingual Information Retrieval (IR) performance remains under-explored. To systematically investigate this data-centric aspect, we construct linguistically parallel Korean-English datasets and train retrieval models with various language combinations. Our experiments reveal that the language composition of training data significantly influences IR performance, exhibiting important inter-lingual correlations: CLIR performance improves with specific language pairs, while Mono-Lingual IR performance declines. Our work demonstrates that Model Merging can effectively mitigate this trade-off, achieving strong CLIR results while preserving Mono-Lingual IR capabilities. Our findings underscore the effects of linguistic configuration of training data on both CLIR and Mono-Lingual IR, and present Model Merging as a viable strategy to optimize performance across these tasks.
Source: arXiv (Cornell University)
Authors: Jang, Youngjoon, Son, Junyoung, Lee, Taemin, Hong, Seongtae, Moon, Hyeonseok, Lee, Seungyoon, Matteson, Andrew, Lim, Heuiseok
Institution: Korea University
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6979328962
Cites:
Cited by:
Related to: