paper-with-me

Papers

Analyzing Zero-shot Cross-lingual Transfer in Supervised NLP Tasks

2021-01-26 · Hyunjin Choi, Judong Kim, Seongho Joe, Seungjai Min, Youngjune Gwon

In zero-shot cross-lingual transfer, a supervised NLP task trained on a corpus in one language is directly applicable to another language without any additional training. A source of cross-lingual transfer can be as straightforward as lexical overlap between languages (e.g., use of the same scripts, shared subwords) that naturally forces text embeddings to occupy a similar representation space. Recently introduced cross-lingual language model (XLM) pretraining brings out neural parameter sharing in Transformer-style networks as the most important factor for the transfer. In this paper, we aim to validate the hypothetically strong cross-lingual transfer properties induced by XLM pretraining. Particularly, we take XLM-RoBERTa (XLMR) in our experiments that extend semantic textual similarity (STS), SQuAD and KorQuAD for machine reading comprehension, sentiment analysis, and alignment of sentence embeddings under various cross-lingual settings. Our results indicate that the presence of cross-lingual transfer is most pronounced in STS, sentiment analysis the next, and MRC the last. That is, the complexity of a downstream task softens the degree of crosslingual transfer. All of our results are empirically observed and measured, and we make our code and data publicly available.

📄 PDF Abstract BibTeX arXiv:2101.10649

Code (0)

등록된 구현이 없습니다.

Tasks

Cross-Lingual TransferLanguage ModelingLanguage ModellingMachine Reading ComprehensionReading ComprehensionSemantic Textual SimilaritySentenceSentence EmbeddingsSentiment AnalysisSTSZero-Shot Cross-Lingual Transfer

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
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 &…
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…
Attention 설명 없음
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…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Analyzing the Effects of Reasoning Types on Cross-Lingual Transfer Performance

2021-10-05 · EMNLP (MRL) 2021 11 · Karthikeyan K, Aalok Sathe, Somak Aditya, Monojit Choudhury

Multilingual language models achieve impressive zero-shot accuracies in many languages in complex tasks such as Natural Language Inference (NLI). Examples in NLI (and equivalent complex tasks) often pertain to various ty…

Cross-Lingual TransferNatural Language Inference

A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters

2020-12-31 · ACL 2021 5 · Mengjie Zhao, Yi Zhu, Ehsan Shareghi, Ivan Vulić 외

Few-shot crosslingual transfer has been shown to outperform its zero-shot counterpart with pretrained encoders like multilingual BERT. Despite its growing popularity, little to no attention has been paid to standardizing…

Few-Shot Learning

Analyzing the Evaluation of Cross-Lingual Knowledge Transfer in Multilingual Language Models

2024-02-03 · Sara Rajaee, Christof Monz

Recent advances in training multilingual language models on large datasets seem to have shown promising results in knowledge transfer across languages and achieve high performance on downstream tasks. However, we questio…

Transfer Learning

Realistic Zero-Shot Cross-Lingual Transfer in Legal Topic Classification

2022-06-08 · Stratos Xenouleas, Alexia Tsoukara, Giannis Panagiotakis, Ilias Chalkidis 외

We consider zero-shot cross-lingual transfer in legal topic classification using the recent MultiEURLEX dataset. Since the original dataset contains parallel documents, which is unrealistic for zero-shot cross-lingual tr…

Cross-Lingual TransferTopic ClassificationTranslationZero-Shot Cross-Lingual Transfer

Realistic Zero-Shot Cross-Lingual Transfer in Legal Topic Classification

2022-01-16 · ACL ARR January 2022 1 · Anonymous

We consider zero-shot cross-lingual transfer in legal topic classification using the recent Multi-EURLEX dataset. Since the original dataset contains parallel documents, which is unrealistic for zero-shot cross-lingual t…

ClassificationCross-Lingual TransferTopic ClassificationTranslation+1