paper-with-me

Papers

Cross-lingual Knowledge Transfer via Distillation for Multilingual Information Retrieval

2023-02-26 · Zhiqi Huang, Puxuan Yu, James Allan

In this paper, we introduce the approach behind our submission for the MIRACL challenge, a WSDM 2023 Cup competition that centers on ad-hoc retrieval across 18 diverse languages. Our solution contains two neural-based models. The first model is a bi-encoder re-ranker, on which we apply a cross-lingual distillation technique to transfer ranking knowledge from English to the target language space. The second model is a cross-encoder re-ranker trained on multilingual retrieval data generated using neural machine translation. We further fine-tune both models using MIRACL training data and ensemble multiple rank lists to obtain the final result. According to the MIRACL leaderboard, our approach ranks 8th for the Test-A set and 2nd for the Test-B set among the 16 known languages.

📄 PDF Abstract BibTeX arXiv:2302.13400

Code (0)

등록된 구현이 없습니다.

Tasks

Information RetrievalMachine TranslationRetrievalTransfer Learning

Similar Papers 제목 키워드 기반

Limitations of Knowledge Distillation for Zero-shot Transfer Learning

2021-11-01 · EMNLP (sustainlp) 2021 11 · Saleh Soltan, Haidar Khan, Wael Hamza

Pretrained transformer-based encoders such as BERT have been demonstrated to achieve state-of-the-art performance on numerous NLP tasks. Despite their success, BERT style encoders are large in size and have high latency …

CPUCross-Lingual TransferKnowledge DistillationTransfer Learning+1

Improved Cross-Lingual Transfer Learning For Automatic Speech Translation

2023-06-01 · Sameer Khurana, Nauman Dawalatabad, Antoine Laurent, Luis Vicente 외

Research in multilingual speech-to-text translation is topical. Having a single model that supports multiple translation tasks is desirable. The goal of this work it to improve cross-lingual transfer learning in multilin…

automatic-speech-translationCross-Lingual TransferDecoderKnowledge Distillation+5

Multilingual Sentence-Level Semantic Search using Meta-Distillation Learning

2023-09-15 · Meryem M'hamdi, Jonathan May, Franck Dernoncourt, Trung Bui 외

Multilingual semantic search is the task of retrieving relevant contents to a query expressed in different language combinations. This requires a better semantic understanding of the user's intent and its contextual mean…

Sentence

Distilling Multilingual Vision-Language Models: When Smaller Models Stay Multilingual

2025-10-30 · Sukrit Sriratanawilai, Jhayahgrit Thongwat, Romrawin Chumpu, Patomporn Payoungkhamdee 외 arxiv

Vision-language models (VLMs) exhibit uneven performance across languages, a problem that is often exacerbated when the model size is reduced. While Knowledge distillation (KD) demonstrates promising results in transferr…

Knowledge DistillationModel Compression

Promoting Generalized Cross-lingual Question Answering in Few-resource Scenarios via Self-knowledge Distillation

2023-09-29 · Casimiro Pio Carrino, Carlos Escolano, José A. R. Fonollosa

Despite substantial progress in multilingual extractive Question Answering (QA), models with high and uniformly distributed performance across languages remain challenging, especially for languages with limited resources…

Cross-Lingual Question AnsweringCross-Lingual TransferExtractive Question-AnsweringKnowledge Distillation+3