Sentence-Level Multilingual Multi-modal Embedding for Natural Language Processing
We propose a novel discriminative ranking model that learns embeddings from multilingual and multi-modal data, meaning that our model can take advantage of images and descriptions in multiple languages to improve embedding quality. To that end, we introduce an objective function that uses pairwise ranking adapted to the case of three or more input sources. We compare our model against different baselines, and evaluate the robustness of our embeddings on image{--}sentence ranking (ISR), semantic textual similarity (STS), and neural machine translation (NMT). We find that the additional multilingual signals lead to improvements on all three tasks, and we highlight that our model can be used to consistently improve the adequacy of translations generated with NMT models when re-ranking n-best lists.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationNMTRe-RankingSemantic Textual SimilaritySentenceSTSTranslationSimilar Papers 제목 키워드 기반
SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation
We propose the SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation learning framework. Unlike previous works on speech representation learning, which learns multilingual context…
Representation LearningRetrievalSentenceSentence Embedding+6SONAR-SLT: Multilingual Sign Language Translation via Language-Agnostic Sentence Embedding Supervision
Sign language translation (SLT) is typically trained with text in a single spoken language, which limits scalability and cross-language generalization. Earlier approaches have replaced gloss supervision with text-based s…
Sign Language TranslationSONAR: Sentence-Level Multimodal and Language-Agnostic Representations
We introduce SONAR, a new multilingual and multimodal fixed-size sentence embedding space. Our single text encoder, covering 200 languages, substantially outperforms existing sentence embeddings such as LASER3 and LabSE …
DecoderMachine TranslationSentenceSentence Embedding+5FLiP: Towards understanding and interpreting multimodal multilingual sentence embeddings
This paper presents factorized linear projection (FLiP) models for understanding pretrained sentence embedding spaces. We train FLiP models to recover the lexical content from multilingual (LaBSE), multimodal (SONAR) and…
Hierarchical Document Encoder for Parallel Corpus Mining
We explore using multilingual document embeddings for nearest neighbor mining of parallel data. Three document-level representations are investigated: (i) document embeddings generated by simply averaging multilingual se…
Parallel Corpus MiningSentenceSentence EmbeddingSentence-Embedding+1