中文
相关论文

相关论文: A Massively Multilingual Analysis of Cross-lingual…

200 篇论文

Despite their remarkable ability to capture linguistic nuances across diverse languages, questions persist regarding the degree of alignment between languages in multilingual embeddings. Drawing inspiration from research on high-dimensional…

计算与语言 · 计算机科学 2024-05-24 Basel Mousi , Nadir Durrani , Fahim Dalvi , Majd Hawasly , Ahmed Abdelali

We propose an unsupervised method to obtain cross-lingual embeddings without any parallel data or pre-trained word embeddings. The proposed model, which we call multilingual neural language models, takes sentences of multiple languages as…

计算与语言 · 计算机科学 2018-09-10 Takashi Wada , Tomoharu Iwata

With hundreds of multilingual embedding models available, practitioners lack clear guidance on which provide genuine cross-lingual semantic alignment versus task performance through language-specific patterns. Task-driven benchmarks (MTEB)…

计算与语言 · 计算机科学 2026-01-16 Wen G. Gong

NLP research on aligning lexical representation spaces to one another has so far focused on aligning language spaces in their entirety. However, cognitive science has long focused on a local perspective, investigating whether translation…

计算与语言 · 计算机科学 2024-10-11 Taelin Karidi , Eitan Grossman , Omri Abend

The field of cross-lingual sentence embeddings has recently experienced significant advancements, but research concerning low-resource languages has lagged due to the scarcity of parallel corpora. This paper shows that cross-lingual word…

计算与语言 · 计算机科学 2024-04-04 Zhongtao Miao , Qiyu Wu , Kaiyan Zhao , Zilong Wu , Yoshimasa Tsuruoka

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 encoder with a shared BPE…

计算与语言 · 计算机科学 2021-12-28 Mikel Artetxe , Holger Schwenk

While recent work on multilingual language models has demonstrated their capacity for cross-lingual zero-shot transfer on downstream tasks, there is a lack of consensus in the community as to what shared properties between languages enable…

计算与语言 · 计算机科学 2022-05-05 Ameet Deshpande , Partha Talukdar , Karthik Narasimhan

Word alignment which aims to extract lexicon translation equivalents between source and target sentences, serves as a fundamental tool for natural language processing. Recent studies in this area have yielded substantial improvements by…

计算与语言 · 计算机科学 2022-10-11 Siyu Lai , Zhen Yang , Fandong Meng , Yufeng Chen , Jinan Xu , Jie Zhou

Cross-lingual alignment, the meaningful similarity of representations across languages in multilingual language models, has been an active field of research in recent years. We survey the literature of techniques to improve cross-lingual…

计算与语言 · 计算机科学 2024-06-12 Katharina Hämmerl , Jindřich Libovický , Alexander Fraser

Word embeddings represent words in a numeric space so that semantic relations between words are represented as distances and directions in the vector space. Cross-lingual word embeddings transform vector spaces of different languages so…

计算与语言 · 计算机科学 2021-03-25 Marko Robnik-Sikonja , Kristjan Reba , Igor Mozetic

Word alignment over parallel corpora has a wide variety of applications, including learning translation lexicons, cross-lingual transfer of language processing tools, and automatic evaluation or analysis of translation outputs. The great…

计算与语言 · 计算机科学 2021-08-13 Zi-Yi Dou , Graham Neubig

Multilingual generative models obtain remarkable cross-lingual in-context learning capabilities through pre-training on large-scale corpora. However, they still exhibit a performance bias toward high-resource languages and learn isolated…

计算与语言 · 计算机科学 2024-06-13 Chong Li , Shaonan Wang , Jiajun Zhang , Chengqing Zong

Cross-lingual representations of words enable us to reason about word meaning in multilingual contexts and are a key facilitator of cross-lingual transfer when developing natural language processing models for low-resource languages. In…

计算与语言 · 计算机科学 2019-10-08 Sebastian Ruder , Ivan Vulić , Anders Søgaard

Multilingual pre-trained language models, such as mBERT and XLM-R, have shown impressive cross-lingual ability. Surprisingly, both of them use multilingual masked language model (MLM) without any cross-lingual supervision or aligned data.…

计算与语言 · 计算机科学 2022-03-17 Yuan Chai , Yaobo Liang , Nan Duan

State-of-the-art contextual embeddings are obtained from large language models available only for a few languages. For others, we need to learn representations using a multilingual model. There is an ongoing debate on whether multilingual…

计算与语言 · 计算机科学 2021-09-13 Tomasz Limisiewicz , David Mareček

We introduce a novel analysis that leverages linguistic minimal pairs to probe the internal linguistic representations of Large Language Models (LLMs). By measuring the similarity between LLM activation differences across minimal pairs, we…

计算与语言 · 计算机科学 2024-12-16 Xinyu Zhou , Delong Chen , Samuel Cahyawijaya , Xufeng Duan , Zhenguang G. Cai

Large Language Models (LLMs) have achieved remarkable success in Natural Language Processing (NLP), yet their cross-lingual performance consistency remains a significant challenge. This paper introduces a novel methodology for efficiently…

计算与语言 · 计算机科学 2025-05-27 Zixiang Xu , Yanbo Wang , Yue Huang , Xiuying Chen , Jieyu Zhao , Meng Jiang , Xiangliang Zhang

While cross-lingual word embeddings have been studied extensively in recent years, the qualitative differences between the different algorithms remain vague. We observe that whether or not an algorithm uses a particular feature set…

计算与语言 · 计算机科学 2017-01-11 Omer Levy , Anders Søgaard , Yoav Goldberg

Multilingual Large Language Models (LLMs) achieve remarkable levels of zero-shot cross-lingual transfer performance. We speculate that this is predicated on their ability to align languages without explicit supervision from parallel…

计算与语言 · 计算机科学 2024-06-21 Hetong Wang , Pasquale Minervini , Edoardo M. Ponti

Multilingual BERT (mBERT) has shown reasonable capability for zero-shot cross-lingual transfer when fine-tuned on downstream tasks. Since mBERT is not pre-trained with explicit cross-lingual supervision, transfer performance can further be…

计算与语言 · 计算机科学 2020-10-01 Saurabh Kulshreshtha , José Luis Redondo-García , Ching-Yun Chang
‹ 上一页 1 2 3 10 下一页 ›