mlsanityData to 7 Oct 2026

Enhancing Model Performance in Multilingual Information Retrieval with Comprehensive Data Engineering Techniques

arXiv 2302.07010 ↗First posted 14 Feb 2023cs.IR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we present our solution to the Multilingual Information Retrieval Across a Continuum of Languages (MIRACL) challenge of WSDM CUP 2023footnotehttps://project-miracl.github.io/. Our solution focuses on enhancing the ranking stage, where we fine-tune pre-trained multilingual transformer-based models with MIRACL dataset. Our model improvement is mainly achieved through diverse data engineering techniques, including the collection of additional relevant training data, data augmentation, and negative sampling. Our fine-tuned model effectively determines the semantic relevance between queries and documents, resulting in a significant improvement in the efficiency of the multilingual information retrieval process. Finally, Our team is pleased to achieve remarkable results in this challenging competition, securing 2nd place in the Surprise-Languages track with a score of 0.835 and 3rd place in the Known-Languages track with an average nDCG@10 score of 0.716 across the 16 known languages on the final leaderboard.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 27 references that are in the map. First posted on arXiv 14 Feb 2023.

Builds on

21 of 27 references.

References · 21

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  6. 2017Billion-scale similarity search with GPUscited by 2,477
  7. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
  8. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  9. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,219
  10. 2019Cross-lingual Language Model Pretrainingcited by 1,088
  11. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 846
  12. 2016Recommendations as Treatments: Debiasing Learning and Evaluationcited by 246
9 more
  1. 2021Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Samplingcited by 238
  2. 2020InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Trainingcited by 237
  3. 2021Mr. TyDi: A Multi-lingual Benchmark for Dense Retrievalcited by 118
  4. 2020Rethinking embedding coupling in pre-trained language modelscited by 103
  5. 2022Making a MIRACL: Multilingual Information Retrieval Across a Continuum of Languagescited by 47
  6. 2022Towards Best Practices for Training Multilingual Dense Retrieval Modelscited by 26
  7. 2019Multi-Sample Dropout for Accelerated Training and Better Generalizationcited by 14
  8. 2022Improving BERT-based Query-by-Document Retrieval with Multi-Task Optimizationcited by 5
  9. 2022A Semantic Alignment System for Multilingual Query-Product Retrievalcited by 3

Built on by

Not cited yet.