Improving Zero-shot Translation with Language-Independent Constraints

被引:0
|
作者
Pham, Ngoc-Quan [1 ]
Niehues, Jan [2 ]
Ha, Thanh-Le [2 ]
Waibel, Alex [2 ]
机构
[1] Karlsruhe Inst Technol, Karlsruhe, Germany
[2] Maastricht Univ, Maastricht, Netherlands
基金
欧盟地平线“2020”;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
An important concern in training multilingual neural machine translation (NMT) is to translate between language pairs unseen during training, i.e zero-shot translation. Improving this ability kills two birds with one stone by providing an alternative to pivot translation which also allows us to better understand how the model captures information between languages. In this work, we carried out an investigation on this capability of the multilingual NMT models. First, we intentionally create an encoder architecture which is independent with respect to the source language. Such experiments shed light on the ability of NMT encoders to learn multilingual representations, in general. Based on such proof of concept, we were able to design regularization methods into the standard Transformer model, so that the whole architecture becomes more robust in zero-shot conditions. We investigated the behaviour of such models on the standard IWSLT 2017 multilingual dataset. We achieved an average improvement of 2.23 BLEU points across 12 language pairs compared to the zero-shot performance of a state-of-the-art multilingual system. Additionally, we carry out further experiments in which the effect is confirmed even for language pairs with multiple intermediate pivots.
引用
收藏
页码:13 / 23
页数:11
相关论文
共 50 条
  • [1] Improving Zero-Shot Translation by Disentangling Positional Information
    Liu, Danni
    Niehues, Jan
    Cross, James
    Guzman, Francisco
    Li, Xian
    59TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 11TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 1 (ACL-IJCNLP 2021), 2021, : 1259 - 1273
  • [2] Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation
    Zhang, Biao
    Williams, Philip
    Titov, Ivan
    Sennrich, Rico
    58TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2020), 2020, : 1628 - 1639
  • [3] Language Tags Matter for Zero-Shot Neural Machine Translation
    Wu, Liwei
    Cheng, Shanbo
    Wang, Mingxuan
    Li, Lei
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL-IJCNLP 2021, 2021, : 3001 - 3007
  • [4] Improving Zero-shot Neural Machine Translation on Language-specific Encoders-Decoders
    Liao, Junwei
    Shi, Yu
    Gong, Ming
    Shou, Linjun
    Qu, Hong
    Zeng, Michael
    2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,
  • [5] Frustratingly Simple but Surprisingly Strong: Using Language-Independent Features for Zero-shot Cross-lingual Semantic Parsing
    Yang, Jingfeng
    Fancellu, Federico
    Webber, Bonnie
    Yang, Diyi
    2021 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2021), 2021, : 5848 - 5856
  • [6] Zero-Shot Translation of Attention Patterns in VQA Models to Natural Language
    Salewski, Leonard
    Koepke, A. Sophia
    Lensch, Hendrik P. A.
    Akata, Zeynep
    PATTERN RECOGNITION, DAGM GCPR 2023, 2024, 14264 : 378 - 393
  • [7] ZeroST: Zero-Shot Speech Translation
    Khurana, Sameer
    Horii, Chiori
    Laurent, Antoine
    Wichern, Gordon
    Le Roux, Jonathan
    INTERSPEECH 2024, 2024, : 392 - 396
  • [8] Zero-Shot Recommendation as Language Modeling
    Sileo, Damien
    Vossen, Wout
    Raymaekers, Robbe
    ADVANCES IN INFORMATION RETRIEVAL, PT II, 2022, 13186 : 223 - 230
  • [9] Towards Zero-shot Language Modeling
    Ponti, Edoardo M.
    Vulic, Ivan
    Cotterell, Ryan
    Reichart, Roi
    Korhonen, Anna
    2019 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING AND THE 9TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (EMNLP-IJCNLP 2019): PROCEEDINGS OF THE CONFERENCE, 2019, : 2900 - +
  • [10] Effective Guidance in Zero-Shot Multilingual Translation via Multiple Language Prototypes
    Zheng, Yafang
    Lin, Lei
    Yuan, Yuxuan
    Shi, Xiaodong
    NEURAL INFORMATION PROCESSING, ICONIP 2023, PT VI, 2024, 14452 : 226 - 238