paper-with-me

홈 › Papers

Scalable Cross-Lingual Transfer of Neural Sentence Embeddings

2019-04-11 · SEMEVAL 2019 6 · Hanan Aldarmaki, Mona Diab

We develop and investigate several cross-lingual alignment approaches for neural sentence embedding models, such as the supervised inference classifier, InferSent, and sequential encoder-decoder models. We evaluate three alignment frameworks applied to these models: joint modeling, representation transfer learning, and sentence mapping, using parallel text to guide the alignment. Our results support representation transfer as a scalable approach for modular cross-lingual alignment of neural sentence embeddings, where we observe better performance compared to joint models in intrinsic and extrinsic evaluations, particularly with smaller sets of parallel data.

📄 PDF Abstract BibTeX arXiv:1904.05542

Code (0)

등록된 구현이 없습니다.

Tasks

Cross-Lingual TransferDecoderSentenceSentence EmbeddingSentence-EmbeddingSentence EmbeddingsTransfer Learning

Similar Papers 제목 키워드 기반

Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond

2018-12-26 · TACL 2019 3 · Mikel Artetxe, Holger Schwenk

We introduce an architecture to learn joint multilingual sentence representations for 93 languages, belonging to more than 30 different families and written in 28 different scripts. Our system uses a single BiLSTM encode…

Cross-Lingual Bitext MiningCross-Lingual Document ClassificationCross-Lingual Natural Language InferenceCross-Lingual Transfer+8

Retrofitting Multilingual Sentence Embeddings with Abstract Meaning Representation

2022-10-18 · Deng Cai, Xin Li, Jackie Chun-Sing Ho, Lidong Bing 외

We introduce a new method to improve existing multilingual sentence embeddings with Abstract Meaning Representation (AMR). Compared with the original textual input, AMR is a structured semantic representation that presen…

Abstract Meaning RepresentationSemantic SimilaritySemantic Textual SimilaritySentence+1

Lingua Custodi's participation at the WMT 2025 Terminology shared task

2025-10-20 · Jingshu Liu, Raheel Qader, Gaëtan Caillaut, Mariam Nakhlé arxiv

While BERT is an effective method for learning monolingual sentence embeddings for semantic similarity and embedding based transfer learning BERT based cross-lingual sentence embeddings have yet to be explored. We system…

Semantic SimilarityTransfer LearningText Retrieval

Leveraging Multi-lingual Positive Instances in Contrastive Learning to Improve Sentence Embedding

2023-09-16 · Kaiyan Zhao, Qiyu Wu, Xin-Qiang Cai, Yoshimasa Tsuruoka

Learning multi-lingual sentence embeddings is a fundamental task in natural language processing. Recent trends in learning both mono-lingual and multi-lingual sentence embeddings are mainly based on contrastive learning …

Contrastive LearningCross-Lingual TransferRetrievalSemantic Similarity+5

Language-agnostic BERT Sentence Embedding

2020-07-03 · ACL 2022 5 · Fangxiaoyu Feng, Yinfei Yang, Daniel Cer, Naveen Arivazhagan 외

While BERT is an effective method for learning monolingual sentence embeddings for semantic similarity and embedding based transfer learning (Reimers and Gurevych, 2019), BERT based cross-lingual sentence embeddings have…

Language ModelingLanguage ModellingMasked Language ModelingMultilingual NLP+11