paper-with-me

Papers

Locating Language-Specific Information in Contextualized Embeddings

2021-09-16 · Sheng Liang, Philipp Dufter, Hinrich Schütze

Multilingual pretrained language models (MPLMs) exhibit multilinguality and are well suited for transfer across languages. Most MPLMs are trained in an unsupervised fashion and the relationship between their objective and multilinguality is unclear. More specifically, the question whether MPLM representations are language-agnostic or they simply interleave well with learned task prediction heads arises. In this work, we locate language-specific information in MPLMs and identify its dimensionality and the layers where this information occurs. We show that language-specific information is scattered across many dimensions, which can be projected into a linear subspace. Our study contributes to a better understanding of MPLM representations, going beyond treating them as unanalyzable blobs of information.

📄 PDF Abstract BibTeX arXiv:2109.08040

Code (1)

liangsheng02/locating-language-information 공식 구현 pytorch

Similar Papers 제목 키워드 기반

On the Cross-lingual Transferability of Contextualized Sense Embeddings

2021-11-01 · EMNLP (MRL) 2021 11 · Kiamehr Rezaee, Daniel Loureiro, Jose Camacho-Collados, Mohammad Taher Pilehvar

In this paper we analyze the extent to which contextualized sense embeddings, i.e., sense embeddings that are computed based on contextualized word embeddings, are transferable across languages.To this end, we compiled a…

Word EmbeddingsWord Sense Disambiguation

Leveraging Three Types of Embeddings from Masked Language Models in Idiom Token Classification

2022-07-01 · *SEM (NAACL) 2022 7 · Ryosuke Takahashi, Ryohei Sasano, Koichi Takeda

Many linguistic expressions have idiomatic and literal interpretations, and the automatic distinction of these two interpretations has been studied for decades. Recent research has shown that contextualized word embeddin…

Classificationtoken-classificationToken ClassificationWord Embeddings

What Does This Word Mean? Explaining Contextualized Embeddings with Natural Language Definition

2019-11-01 · IJCNLP 2019 11 · Ting-Yun Chang, Yun-Nung Chen

Contextualized word embeddings have boosted many NLP tasks compared with traditional static word embeddings. However, the word with a specific sense may have different contextualized embeddings due to its various context…

Word Embeddings

Representing Affect Information in Word Embeddings

2022-09-21 · Yuhan Zhang, Wenqi Chen, Ruihan Zhang, Xiajie Zhang

A growing body of research in natural language processing (NLP) and natural language understanding (NLU) is investigating human-like knowledge learned or encoded in the word embeddings from large language models. This is…

Natural Language UnderstandingWord Embeddings

Clinical Named Entity Recognition using Contextualized Token Representations

2021-06-23 · Yichao Zhou, Chelsea Ju, J. Harry Caufield, Kevin Shih 외

The clinical named entity recognition (CNER) task seeks to locate and classify clinical terminologies into predefined categories, such as diagnostic procedure, disease disorder, severity, medication, medication dosage, a…

DiagnosticLanguage Modellingnamed-entity-recognitionNamed Entity Recognition+2