Multilingual Generative Retrieval via Cross-lingual Semantic Compression
By: Yuxin Huang , Simeng Wu , Ran Song and more
Potential Business Impact:
Finds information in any language faster.
Generative Information Retrieval is an emerging retrieval paradigm that exhibits remarkable performance in monolingual scenarios.However, applying these methods to multilingual retrieval still encounters two primary challenges, cross-lingual identifier misalignment and identifier inflation. To address these limitations, we propose Multilingual Generative Retrieval via Cross-lingual Semantic Compression (MGR-CSC), a novel framework that unifies semantically equivalent multilingual keywords into shared atoms to align semantics and compresses the identifier space, and we propose a dynamic multi-step constrained decoding strategy during retrieval. MGR-CSC improves cross-lingual alignment by assigning consistent identifiers and enhances decoding efficiency by reducing redundancy. Experiments demonstrate that MGR-CSC achieves outstanding retrieval accuracy, improving by 6.83% on mMarco100k and 4.77% on mNQ320k, while reducing document identifiers length by 74.51% and 78.2%, respectively.
Similar Papers
SemCORE: A Semantic-Enhanced Generative Cross-Modal Retrieval Framework with MLLMs
Information Retrieval
Finds matching pictures or words better.
Does Generative Retrieval Overcome the Limitations of Dense Retrieval?
Information Retrieval
Finds information by creating answers, not just searching.
Hybrid Retrieval-Augmented Generation for Robust Multilingual Document Question Answering
Digital Libraries
Helps computers answer questions from old, messy papers.