Logo PTI Logo FedCSIS

Proceedings of the 18th Conference on Computer Science and Intelligence Systems

Annals of Computer Science and Information Systems, Volume 35

Multi-index Retrieve and Rerank with Sequence-to-Sequence Model

DOI: http://dx.doi.org/10.15439/2023F3900

Citation: Proceedings of the 18th Conference on Computer Science and Intelligence Systems, M. Ganzha, L. Maciaszek, M. Paprzycki, D. Ślęzak (eds). ACSIS, Vol. 35, pages 1277–1279 ()

Full text

Abstract. This paper presents the solution to PolEval 2022 Task 3: Passage Retrieval. The main goal of the task, was to retrieve relevant text passages for the query. There were three different domains of passages: wikipedia passages, allegro faq and legal documents. The proposed solution incorporated both dense and lexical indexes, as well as, reranking model and reached 67.44 NDCG@10 score in official evaluation.

References

  1. Luiz Henrique Bonifacio, Israel Campiotti, Roberto de Alencar Lotufo, and Rodrigo Nogueira. mmarco: A multilingual version of MS MARCO passage ranking dataset. CoRR, abs/2108.13897, 2021.
  2. Aleksandra Chrabrowa, Łukasz Dragan, Karol Grzegorczyk, Dariusz Kajtoch, Mikołaj Koszowski, Robert Mroczkowski, and Piotr Rybak. Evaluation of transfer learning for polish with a text-to-text model. arXiv preprint https://arxiv.org/abs/2205.08808, 2022.
  3. Fangxiaoyu Feng, Yinfei Yang, Daniel Cer, Naveen Arivazhagan, and Wei Wang. Language-agnostic BERT sentence embedding. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 878–891, Dublin, Ireland, May 2022. Association for Computational Linguistics.
  4. Pengcheng He, Jianfeng Gao, and Weizhu Chen. Debertav3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing. CoRR, abs/2111.09543, 2021.
  5. Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. Unsupervised dense information retrieval with contrastive learning, 2021.
  6. Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. Dense passage retrieval for open-domain question answering. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6769–6781, Online, November 2020. Association for Computational Linguistics.
  7. Jindřich Libovický, Rudolf Rosa, and Alexander Fraser. How language-neutral is multilingual bert?, 2019.
  8. Tri Nguyen, Mir Rosenberg, Xia Song, Jianfeng Gao, Saurabh Tiwary, Rangan Majumder, and Li Deng. Ms marco: A human generated machine reading comprehension dataset. November 2016.
  9. Rodrigo Frassetto Nogueira and Kyunghyun Cho. Passage re-ranking with BERT. CoRR, abs/1901.04085, 2019.
  10. Piotr Rybak. MAUPQA: Massive automatically-created Polish question answering dataset. In Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023), pages 11–16, Dubrovnik, Croatia, May 2023. Association for Computational Linguistics.
  11. Nandan Thakur, Nils Reimers, Andreas Rücklé, Abhishek Srivastava, and Iryna Gurevych. BEIR: A heterogenous benchmark for zero-shot evaluation of information retrieval models. CoRR, abs/2104.08663, 2021.
  12. Wenhui Wang, Hangbo Bao, Shaohan Huang, Li Dong, and Furu Wei. Minilmv2: Multi-head self-attention relation distillation for compressing pretrained transformers. CoRR, abs/2012.15828, 2020.
  13. Konrad Wojtasik, Vadim Shishkin, Kacper Wołowiec, Arkadiusz Janz, and Maciej Piasecki. Beir-pl: Zero shot information retrieval benchmark for the polish language, 2023.
  14. Linting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, and Colin Raffel. mt5: A massively multilingual pre-trained text-to-text transformer. CoRR, abs/2010.11934, 2020.
  15. Xinyu Zhang, Kelechi Ogueji, Xueguang Ma, and Jimmy Lin. Towards best practices for training multilingual dense retrieval models, 2022.