paper-with-me

Papers

Cross-Lingual BERT Transformation for Zero-Shot Dependency Parsing

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

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 contextualized word embeddings based on publicly available pre-trained BERT models (Devlin et al., 2018). In this approach, a linear transformation is learned from contextual word alignments to align the contextualized embeddings independently trained in different languages. We demonstrate the effectiveness of this approach on zero-shot cross-lingual transfer parsing. Experiments show that our embeddings substantially outperform the previous state-of-the-art that uses static embeddings. We further compare our approach with XLM (Lample and Conneau, 2019), a recently proposed cross-lingual language model trained with massive parallel data, and achieve highly competitive results.

📄 PDF Abstract BibTeX arXiv:1909.06775

Code (1)

WangYuxuan93/CLBT 공식 구현 pytorch

Tasks

Cross-Lingual TransferDependency ParsingLanguage ModelingLanguage ModellingWord EmbeddingsZero-Shot Cross-Lingual Transfer

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
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.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Weight Decay 설명 없음
XLM XLM is a Transformer based architecture that is pre-trained using one of three language modelling objectives: 1. Causal…
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 &…

Similar Papers 제목 키워드 기반

Linear Transformations for Cross-lingual Sentiment Analysis

2022-09-15 · Pavel Přibáň, Jakub Šmíd, Adam Mištera, Pavel Král

This paper deals with cross-lingual sentiment analysis in Czech, English and French languages. We perform zero-shot cross-lingual classification using five linear transformations combined with LSTM and CNN based classifi…

ClassificationSentiment Analysis

Feature Aggregation in Zero-Shot Cross-Lingual Transfer Using Multilingual BERT

2022-05-17 · Beiduo Chen, Wu Guo, Quan Liu, Kun Tao

Multilingual BERT (mBERT), a language model pre-trained on large multilingual corpora, has impressive zero-shot cross-lingual transfer capabilities and performs surprisingly well on zero-shot POS tagging and Named Entity…

Cross-Lingual TransferLanguage ModelingLanguage Modellingnamed-entity-recognition+6

Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT

2019-04-19 · IJCNLP 2019 11 · Shijie Wu, Mark Dredze

Pretrained contextual representation models (Peters et al., 2018; Devlin et al., 2018) have pushed forward the state-of-the-art on many NLP tasks. A new release of BERT (Devlin, 2018) includes a model simultaneously pret…

Cross-Lingual NERCross-Lingual TransferDependency ParsingDocument Classification+5

Examining Cross-lingual Contextual Embeddings with Orthogonal Structural Probes

2021-09-10 · EMNLP 2021 11 · Tomasz Limisiewicz, David Mareček

State-of-the-art contextual embeddings are obtained from large language models available only for a few languages. For others, we need to learn representations using a multilingual model. There is an ongoing debate on wh…

An Empirical Study of Pre-trained Transformers for Arabic Information Extraction

2020-04-30 · EMNLP 2020 11 · Wuwei Lan, Yang Chen, Wei Xu, Alan Ritter

Multilingual pre-trained Transformers, such as mBERT (Devlin et al., 2019) and XLM-RoBERTa (Conneau et al., 2020a), have been shown to enable the effective cross-lingual zero-shot transfer. However, their performance on …

Cross-Lingual TransferLanguage Modellingnamed-entity-recognitionNamed Entity Recognition+8