XL-AMR: Enabling Cross-Lingual AMR Parsing with Transfer Learning Techniques

2020-11-01 · EMNLP 2020 11 · Rexhina Blloshmi, Rocco Tripodi, Roberto Navigli

Abstract Meaning Representation (AMR) is a popular formalism of natural language that represents the meaning of a sentence as a semantic graph. It is agnostic about how to derive meanings from strings and for this reason it lends itself well to the encoding of semantics across languages. However, cross-lingual AMR parsing is a hard task, because training data are scarce in languages other than English and the existing English AMR parsers are not directly suited to being used in a cross-lingual setting. In this work we tackle these two problems so as to enable cross-lingual AMR parsing: we explore different transfer learning techniques for producing automatic AMR annotations across languages and develop a cross-lingual AMR parser, XL-AMR. This can be trained on the produced data and does not rely on AMR aligners or source-copy mechanisms as is commonly the case in English AMR parsing. The results of XL-AMR significantly surpass those previously reported in Chinese, German, Italian and Spanish. Finally we provide a qualitative analysis which sheds light on the suitability of AMR across languages. We release XL-AMR at github.com/SapienzaNLP/xl-amr.

📄 PDF Abstract BibTeX

Code (1)

SapienzaNLP/xl-amr 공식 구현 pytorch

Tasks

Abstract Meaning RepresentationAMR ParsingSentenceTransfer Learning

Multi-Source Cross-Lingual Constituency Parsing

2021-12-01 · ICON 2021 12 · Hour Kaing, Chenchen Ding, Katsuhito Sudoh, Masao Utiyama 외

Pretrained multilingual language models have become a key part of cross-lingual transfer for many natural language processing tasks, even those without bilingual information. This work further investigates the cross-ling…

Constituency Parsing Cross-Lingual Transfer Diversity Pretrained Multilingual Language Models

Meta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsing

2021-04-10 · ACL 2022 5 · Anna Langedijk, Verna Dankers, Phillip Lippe, Sander Bos 외

Meta-learning, or learning to learn, is a technique that can help to overcome resource scarcity in cross-lingual NLP problems, by enabling fast adaptation to new tasks. We apply model-agnostic meta-learning (MAML) to the…

Dependency Parsing Few-Shot Learning Meta-Learning

Cross-lingual Dependency Parsing with Unlabeled Auxiliary Languages

2019-09-20 · CONLL 2019 11 · Wasi Uddin Ahmad, Zhisong Zhang, Xuezhe Ma, Kai-Wei Chang 외

Cross-lingual transfer learning has become an important weapon to battle the unavailability of annotated resources for low-resource languages. One of the fundamental techniques to transfer across languages is learning \e…

Cross-Lingual Transfer Dependency Parsing Transfer Learning Word Embeddings

Cross-lingual Constituency Parsing with Linguistic Typology Knowledge

2021-10-16 · ACL ARR October 2021 10 · Anonymous

Cross-lingual Transfer learning (CLT) has successfully been applied to the dependency parsing task. This is the first work that evaluates a CLT based approach to the Constituency parsing task. Furthermore, we utilized th…

Constituency Parsing Cross-Lingual Transfer Dependency Parsing Transfer Learning

Project-then-Transfer: Effective Two-stage Cross-lingual Transfer for Semantic Dependency Parsing

2021-04-01 · EACL 2021 2 · Hiroaki Ozaki, Gaku Morio, Terufumi Morishita, Toshinori Miyoshi

This paper describes the first report on cross-lingual transfer for semantic dependency parsing. We present the insight that there are twodifferent kinds of cross-linguality, namely sur-face level and mantic level, and t…

Cross-Lingual Transfer Dependency Parsing Semantic Dependency Parsing