Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing

被引:0
|
作者
Schuster, Tal [1 ]
Ram, Ori [2 ]
Barzilay, Regina [1 ]
Globerson, Amir [2 ]
机构
[1] MIT, Comp Sci & Artificial Intelligence Lab, Cambridge, MA 02139 USA
[2] Tel Aviv Univ, Tel Aviv, Israel
基金
美国国家科学基金会;
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
We introduce a novel method for multilingual transfer that utilizes deep contextual embeddings, pretrained in an unsupervised fashion. While contextual embeddings have been shown to yield richer representations of meaning compared to their static counterparts, aligning them poses a challenge due to their dynamic nature. To this end, we construct context-independent variants of the original monolingual spaces and utilize their mapping to derive an alignment for the context-dependent spaces. This mapping readily supports processing of a target language, improving transfer by context-aware embeddings. Our experimental results demonstrate the effectiveness of this approach for zero-shot and few-shot learning of dependency parsing. Specifically, our method consistently outperforms the previous state-of-the-art on 6 tested languages, yielding an improvement of 6.8 LAS points on average.
引用
收藏
页码:1599 / 1613
页数:15
相关论文
共 50 条
  • [31] Zero-Shot Cross-Lingual Machine Reading Comprehension via Inter-sentence Dependency Graph
    Xu, Liyan
    Zhang, Xuchao
    Zong, Bo
    Liu, Yanchi
    Cheng, Wei
    Ni, Jingchao
    Chen, Haifeng
    Zhao, Liang
    Choi, Jinho D.
    [J]. THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 11538 - 11546
  • [32] Combining Cross-lingual and Cross-task Supervision for Zero-Shot Learning
    Pikuliak, Matus
    Simko, Marian
    [J]. TEXT, SPEECH, AND DIALOGUE (TSD 2020), 2020, 12284 : 162 - 170
  • [33] Curriculum meta-learning for zero-shot cross-lingual transfer
    Doan, Toan
    Le, Bac
    [J]. KNOWLEDGE-BASED SYSTEMS, 2024, 301
  • [34] Analyzing Zero-shot Cross-lingual Transfer in Supervised NLP Tasks
    Choi, Hyunjin
    Kim, Judong
    Joe, Seongho
    Min, Seungjai
    Gwon, Youngjune
    [J]. 2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2021, : 9608 - 9613
  • [35] Synthetic Data Augmentation for Zero-Shot Cross-Lingual Question Answering
    Riabi, Arij
    Scialom, Thomas
    Keraron, Rachel
    Sagot, Benoit
    Seddah, Djame
    Staiano, Jacopo
    [J]. 2021 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2021), 2021, : 7016 - 7030
  • [36] Rumour Detection via Zero-Shot Cross-Lingual Transfer Learning
    Tian, Lin
    Zhang, Xiuzhen
    Lau, Jey Han
    [J]. MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, 2021, 12975 : 603 - 618
  • [37] Zero-Shot Text Normalization via Cross-Lingual Knowledge Distillation
    Wang, Linqin
    Huang, Xiang
    Yu, Zhengtao
    Peng, Hao
    Gao, Shengxiang
    Mao, Cunli
    Huang, Yuxin
    Dong, Ling
    Yu, Philip S.
    [J]. IEEE/ACM Transactions on Audio Speech and Language Processing, 2024, 32 : 4631 - 4646
  • [38] Cross-Lingual Transfer in Zero-Shot Cross-Language Entity Linking
    Schumacher, Elliot
    Mayfield, James
    Dredze, Mark
    [J]. FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL-IJCNLP 2021, 2021, : 583 - 595
  • [39] Synthetic Treebanking for Cross-Lingual Dependency Parsing
    Tiedemann, Joerg
    Agic, Zeljko
    [J]. JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH, 2016, 55 : 209 - 248
  • [40] Zero-shot Cross-lingual Dialogue Systems with Transferable Latent Variables
    Liu, Zihan
    Shin, Jamin
    Xu, Yan
    Winata, Genta Indra
    Xu, Peng
    Madotto, Andrea
    Fung, Pascale
    [J]. 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, : 1297 - 1303