paper-with-me

Papers

A Simple yet Effective Joint Training Method for Cross-Lingual Universal Dependency Parsing

2018-10-01 · CONLL 2018 10 · Danlu Chen, Mengxiao Lin, Zhifeng Hu, Xipeng Qiu

This paper describes Fudan{'}s submission to CoNLL 2018{'}s shared task Universal Dependency Parsing. We jointly train models when two languages are similar according to linguistic typology and then ensemble the models using a simple re-parse algorithm. We outperform the baseline method by 4.4{\%} (2.1{\%}) on average on development (test) set in CoNLL 2018 UD Shared Task.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Dependency ParsingTransfer Learning

Similar Papers 제목 키워드 기반

Cross-lingual Alignment vs Joint Training: A Comparative Study and A Simple Unified Framework

2019-10-10 · ICLR 2020 1 · Zirui Wang, Jiateng Xie, Ruochen Xu, Yiming Yang 외

Learning multilingual representations of text has proven a successful method for many cross-lingual transfer learning tasks. There are two main paradigms for learning such representations: (1) alignment, which maps diffe…

Bilingual Lexicon InductionCross-Lingual NERCross-Lingual TransferNER+1

Multilingual and cross-lingual document classification: A meta-learning approach

2021-01-27 · EACL 2021 2 · Niels van der Heijden, Helen Yannakoudakis, Pushkar Mishra, Ekaterina Shutova

The great majority of languages in the world are considered under-resourced for the successful application of deep learning methods. In this work, we propose a meta-learning approach to document classification in limited…

Cross-Lingual Document ClassificationDocument ClassificationGeneral ClassificationMeta-Learning

Multilingual Seq2seq Training with Similarity Loss for Cross-Lingual Document Classification

2018-07-01 · WS 2018 7 · Katherine Yu, Haoran Li, Barlas Oguz

In this paper we continue experiments where neural machine translation training is used to produce joint cross-lingual fixed-dimensional sentence embeddings. In this framework we introduce a simple method of adding a los…

Cross-Lingual Document ClassificationCross-Lingual TransferDocument ClassificationGeneral Classification+7

Cross-neutralising: Probing for joint encoding of linguistic information in multilingual models

2020-10-24 · Rochelle Choenni, Ekaterina Shutova

Multilingual sentence encoders are widely used to transfer NLP models across languages. The success of this transfer is, however, dependent on the model's ability to encode the patterns of cross-lingual similarity and va…

SentenceXLM-R

Language Clustering for Multilingual Named Entity Recognition

2021-11-01 · Findings (EMNLP) 2021 11 · Kyle Shaffer

Recent work in multilingual natural language processing has shown progress in various tasks such as natural language inference and joint multilingual translation. Despite success in learning across many languages, challe…

ClusteringLanguage IdentificationLanguage ModelingLanguage Modelling+7