paper-with-me

Papers

Adversarial Learning with Contextual Embeddings for Zero-resource Cross-lingual Classification and NER

2019-08-31 · IJCNLP 2019 11 · Phillip Keung, Yichao Lu, Vikas Bhardwaj

Contextual word embeddings (e.g. GPT, BERT, ELMo, etc.) have demonstrated state-of-the-art performance on various NLP tasks. Recent work with the multilingual version of BERT has shown that the model performs very well in zero-shot and zero-resource cross-lingual settings, where only labeled English data is used to finetune the model. We improve upon multilingual BERT's zero-resource cross-lingual performance via adversarial learning. We report the magnitude of the improvement on the multilingual MLDoc text classification and CoNLL 2002/2003 named entity recognition tasks. Furthermore, we show that language-adversarial training encourages BERT to align the embeddings of English documents and their translations, which may be the cause of the observed performance gains.

📄 PDF Abstract BibTeX arXiv:1909.00153

Code (0)

등록된 구현이 없습니다.

Tasks

General Classificationnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NERtext-classificationText ClassificationWord Embeddings

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
BiLSTM A Bidirectional LSTM, or biLSTM, is a sequence processing model that consists of two LSTMs: one taking the input in a forward direction, and the other in a backwards…
Discriminative Fine-Tuning Discriminative Fine-Tuning is a fine-tuning strategy that is used for ULMFiT type models. Instead of using the same learning rate…
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…

Similar Papers 제목 키워드 기반

Detecting Urgency Status of Crisis Tweets: A Transfer Learning Approach for Low Resource Languages

2020-12-01 · COLING 2020 8 · Efsun Sarioglu Kayi, Linyong Nan, Bohan Qu, Mona Diab 외

We release an urgency dataset that consists of English tweets relating to natural crises, along with annotations of their corresponding urgency status. Additionally, we release evaluation datasets for two low-resource la…

Transfer LearningXLM-R

A Comparison of Architectures and Pretraining Methods for Contextualized Multilingual Word Embeddings

2019-12-15 · Niels van der Heijden, Samira Abnar, Ekaterina Shutova

The lack of annotated data in many languages is a well-known challenge within the field of multilingual natural language processing (NLP). Therefore, many recent studies focus on zero-shot transfer learning and joint tra…

Multilingual Word Embeddingsnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+7

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 TransferDependency ParsingTransfer LearningWord Embeddings

Cross-Lingual BERT Transformation for Zero-Shot Dependency Parsing

2019-09-15 · IJCNLP 2019 11 · Yuxuan Wang, Wanxiang Che, Jiang Guo, Yijia Liu 외

This paper investigates the problem of learning cross-lingual representations in a contextual space. We propose Cross-Lingual BERT Transformation (CLBT), a simple and efficient approach to generate cross-lingual contextu…

Cross-Lingual TransferDependency ParsingLanguage ModelingLanguage Modelling+2

Cross-lingual alignments of ELMo contextual embeddings

2021-06-30 · Matej Ulčar, Marko Robnik-Šikonja

Building machine learning prediction models for a specific NLP task requires sufficient training data, which can be difficult to obtain for less-resourced languages. Cross-lingual embeddings map word embeddings from a le…

Dependency Parsingnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+3