paper-with-me

Papers

Are Language-Agnostic Sentence Representations Actually Language-Agnostic?

2021-09-01 · RANLP 2021 9 · Yu Chen, Tania Avgustinova

With the emergence of pre-trained multilingual models, multilingual embeddings have been widely applied in various natural language processing tasks. Language-agnostic models provide a versatile way to convert linguistic units from different languages into a shared vector representation space. The relevant work on multilingual sentence embeddings has reportedly reached low error rate in cross-lingual similarity search tasks. In this paper, we apply the pre-trained embedding models and the cross-lingual similarity search task in diverse scenarios, and observed large discrepancy in results in comparison to the original paper. Our findings on cross-lingual similarity search with different newly constructed multilingual datasets show not only correlation with observable language similarities but also strong influence from factors such as translation paths, which limits the interpretation of the language-agnostic property of the LASER model. %

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

SentenceSentence EmbeddingsTranslation

Similar Papers 제목 키워드 기반

In Search for Linear Relations in Sentence Embedding Spaces

2019-10-08 · Petra Barančíková, Ondřej Bojar

We present an introductory investigation into continuous-space vector representations of sentences. We acquire pairs of very similar sentences differing only by a small alterations (such as change of a noun, adding an ad…

Natural Language InferenceSentenceSentence EmbeddingSentence-Embedding

Cross-Lingual Phrase Retrieval

2022-04-19 · ACL 2022 5 · Heqi Zheng, Xiao Zhang, Zewen Chi, Heyan Huang 외

Cross-lingual retrieval aims to retrieve relevant text across languages. Current methods typically achieve cross-lingual retrieval by learning language-agnostic text representations in word or sentence level. However, ho…

RetrievalSentence

LAWDR: Language-Agnostic Weighted Document Representations from Pre-trained Models

2021-06-07 · Hongyu Gong, Vishrav Chaudhary, Yuqing Tang, Francisco Guzmán

Cross-lingual document representations enable language understanding in multilingual contexts and allow transfer learning from high-resource to low-resource languages at the document level. Recently large pre-trained lan…

Representation LearningSentenceSentence EmbeddingsTransfer Learning

Which Evaluations Uncover Sense Representations that Actually Make Sense?

2020-05-01 · LREC 2020 5 · Jordan Boyd-Graber, Fenfei Guo, Leah Findlater, Mohit Iyyer

Text representations are critical for modern natural language processing. One form of text representation, sense-specific embeddings, reflect a word{'}s sense in a sentence better than single-prototype word embeddings ti…

Coherence EvaluationSentenceWord Embeddings

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