paper-with-me

홈 › Papers

Scalable Cross-lingual Treebank Synthesis for Improved Production Dependency Parsers

2020-12-01 · COLING 2020 8 · Yousef El-Kurdi, Hiroshi Kanayama, Efsun Sarioglu Kayi, Vittorio Castelli, Todd Ward, Radu Florian

We present scalable Universal Dependency (UD) treebank synthesis techniques that exploit advances in language representation modeling which leverage vast amounts of unlabeled general-purpose multilingual text. We introduce a data augmentation technique that uses synthetic treebanks to improve production-grade parsers. The synthetic treebanks are generated using a state-of-the-art biaffine parser adapted with pretrained Transformer models, such as Multilingual BERT (M-BERT). The new parser improves LAS by up to two points on seven languages. The production models{'} LAS performance improves as the augmented treebanks scale in size, surpassing performance of production models trained on originally annotated UD treebanks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentation

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Weight Decay 설명 없음

Similar Papers 제목 키워드 기반

Cross-Lingual Dependency Parsing Using Code-Mixed TreeBank

2019-09-05 · IJCNLP 2019 11 · Zhang Meishan, Zhang Yue, Fu Guohong

Treebank translation is a promising method for cross-lingual transfer of syntactic dependency knowledge. The basic idea is to map dependency arcs from a source treebank to its target translation according to word alignme…

Cross-Lingual TransferCross-Lingual Word EmbeddingsDependency ParsingTranslation+1

Cross-lingual Universal Dependency Parsing Only from One Monolingual Treebank

2020-12-24 · Kailai Sun, Zuchao Li, Hai Zhao

Syntactic parsing is a highly linguistic processing task whose parser requires training on treebanks from the expensive human annotation. As it is unlikely to obtain a treebank for every human language, in this work, we …

Cross-Lingual TransferDependency ParsingDomain AdaptationLanguage Modeling+2

Multi-source synthetic treebank creation for improved cross-lingual dependency parsing

2018-11-01 · WS 2018 11 · Francis Tyers, Mariya Sheyanova, Aleks Martynova, ra 외

This paper describes a method of creating synthetic treebanks for cross-lingual dependency parsing using a combination of machine translation (including pivot translation), annotation projection and the spanning tree alg…

Dependency ParsingMachine TranslationSentenceTranslation

LyS_ACoruña at SemEval-2022 Task 10: Repurposing Off-the-Shelf Tools for Sentiment Analysis as Semantic Dependency Parsing

2022-04-27 · SemEval (NAACL) 2022 7 · Iago Alonso-Alonso, David Vilares, Carlos Gómez-Rodríguez

This paper addressed the problem of structured sentiment analysis using a bi-affine semantic dependency parser, large pre-trained language models, and publicly available translation models. For the monolingual setup, we …

Dependency ParsingSemantic Dependency ParsingSentiment AnalysisTranslation

A Universal Framework for Inductive Transfer Parsing across Multi-typed Treebanks

2016-12-01 · COLING 2016 12 · Jiang Guo, Wanxiang Che, Haifeng Wang, Ting Liu

Various treebanks have been released for dependency parsing. Despite that treebanks may belong to different languages or have different annotation schemes, they contain common syntactic knowledge that is potential to ben…

Dependency ParsingInformation RetrievalMulti-Task Learning