paper-with-me

홈 › Papers

Lessons learned in multilingual grounded language learning

2018-09-20 · CONLL 2018 10 · Ákos Kádár, Desmond Elliott, Marc-Alexandre Côté, Grzegorz Chrupała, Afra Alishahi

Recent work has shown how to learn better visual-semantic embeddings by leveraging image descriptions in more than one language. Here, we investigate in detail which conditions affect the performance of this type of grounded language learning model. We show that multilingual training improves over bilingual training, and that low-resource languages benefit from training with higher-resource languages. We demonstrate that a multilingual model can be trained equally well on either translations or comparable sentence pairs, and that annotating the same set of images in multiple language enables further improvements via an additional caption-caption ranking objective.

📄 PDF Abstract BibTeX arXiv:1809.07615

Code (1)

kadarakos/mulisera 공식 구현 pytorch

Tasks

Grounded language learningSentence

Similar Papers 제목 키워드 기반

Engineering RAG Systems for Real-World Applications: Design, Development, and Evaluation

2025-06-25 · Md Toufique Hasan, Muhammad Waseem, Kai-Kristian Kemell, Ayman Asad Khan 외

Retrieval-Augmented Generation (RAG) systems are emerging as a key approach for grounding Large Language Models (LLMs) in external knowledge, addressing limitations in factual accuracy and contextual relevance. However, …

Optical Character Recognition (OCR)RAGRetrievalRetrieval-augmented Generation+1

Language Technologies for the Creation of Multilingual Terminologies. Lessons Learned from the SSHOC Project

2022-06-01 · LREC 2022 6 · Federica Gamba, Francesca Frontini, Daan Broeder, Monica Monachini

This paper is framed in the context of the SSHOC project and aims at exploring how Language Technologies can help in promoting and facilitating multilingualism in the Social Sciences and Humanities (SSH). Although most S…

Machine TranslationTranslationvalid

Same Lesson, Different Story: Cross-Lingual Reconstruction of Cultural Narratives in Large Language Models

2026-06-23 · Jory Alshaalan, Haya Albaker, Abeer Aldayel, Aljawharah Alabdullatif 외 arxiv

The evaluation of cultural grounding context becomes complex when multiple cultures convey the same moral lesson. This challenge is particularly relevant to large language models (LLMs), which produce narratives across a…

Semantic Similarity

XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation

2021-04-15 · EMNLP 2021 11 · Sebastian Ruder, Noah Constant, Jan Botha, Aditya Siddhant 외

Machine learning has brought striking advances in multilingual natural language processing capabilities over the past year. For example, the latest techniques have improved the state-of-the-art performance on the XTREME …

Cross-Lingual TransferDiagnosticNatural Language UnderstandingRetrieval+1

Lessons Without Borders? Evaluating Cultural Alignment of LLMs Using Multilingual Story Moral Generation

2026-04-09 · Sophie Wu, Andrew Piper arxiv

Stories are key to transmitting values across cultures, but their interpretation varies across linguistic and cultural contexts. Thus, we introduce multilingual story moral generation as a novel culturally grounded evalu…

Semantic Similarity