Lune

ACL Findings2021

Combining Static Word Embeddings and Contextual Representations for Bilingual Lexicon Induction

Jinpeng Zhang, Baijun Ji, Nini Xiao, Xiangyu Duan, Min Zhang, Yangbin Shi, Weihua Luo

摘要

Bilingual Lexicon Induction (BLI) aims to map words in one language to their translations in another, and are typically through learning linear projections to align monolingual word representation spaces. Two classes of word representations have been explored for BLI: static word embeddings and contextual representations, but there is no studies to combine both. In this paper, we propose a simple yet effective mechanism to combine the static word embeddings and the contextual representations to utilize the advantages of both paradigms. We test the combination mechanism on various language pairs under the supervised and unsupervised BLI benchmark settings. Experiments show that our mechanism consistently improves performances over robust BLI baselines on all language pairs by averagely improving 3.2 points in the supervised setting, and 3.1 points in the unsupervised setting 1 .

问 Lune

几分钟读透这篇 Paper,不用再花一下午。

Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。

已有 2 篇顶会 Paper 引用了它。别等审稿人问起,先弄清它们发现了什么。

可以从这些问题问起

Lune 可以查阅

全文 · 引用它的顶会 Paper · 相关的 Paper

获取答案

免费开始,无需绑卡

脉络

  • Improving Word Translation via Two-Stage Contrastive Learning 引用了 Bilingual Lexicon Induction via Unsupervised Bitext Construction and Word Alignment
  • Improving Word Translation via Two-Stage Contrastive Learning 引用了 LNMap: Departures from Isomorphic Assumption in Bilingual Lexicon Induction Through Non-Linear Mapping in Latent Space
  • Cross-lingual Alignment Methods for Multilingual BERT: A Comparative Study 引用了 Multilingual Alignment of Contextual Word Representations
  • On Bilingual Lexicon Induction with Large Language Models 引用了 Improving Word Translation via Two-Stage Contrastive Learning
  • On Bilingual Lexicon Induction with Large Language Models 引用了 LNMap: Departures from Isomorphic Assumption in Bilingual Lexicon Induction Through Non-Linear Mapping in Latent Space
它引用的引用它的从左到右按年份排列,引用越多,位置越高。

引用它的顶会 Paper2

  1. Improving Word Translation via Two-Stage Contrastive LearningYaoyiran Li, Fangyu Liu, Nigel Collier, Anna Korhonen 等ACL 2022 · 32 次引用
  2. On Bilingual Lexicon Induction with Large Language ModelsYaoyiran Li, Anna Korhonen, Ivan VulicEMNLP 2023 · 2 次引用

它引用的 Paper5

  1. Multilingual Alignment of Contextual Word RepresentationsSteven Cao, Nikita Kitaev, Dan KleinICLR 2020 · 211 次引用
  2. Cross-lingual Alignment vs Joint Training: A Comparative Study and A Simple Unified FrameworkZirui Wang, Jiateng Xie, Ruochen Xu, Yiming Yang 等ICLR 2020 · 84 次引用
  3. Cross-lingual Alignment Methods for Multilingual BERT: A Comparative StudySaurabh Kulshreshtha, José Luis Redondo García, Ching-Yun ChangEMNLP Findings 2020 · 37 次引用
  4. LNMap: Departures from Isomorphic Assumption in Bilingual Lexicon Induction Through Non-Linear Mapping in Latent SpaceTasnim Mohiuddin, M. Saiful Bari, Shafiq Rayhan JotyEMNLP 2020 · 13 次引用
  5. Bilingual Lexicon Induction via Unsupervised Bitext Construction and Word AlignmentHaoyue Shi, Luke Zettlemoyer, Sida I. WangACL 2021

相关 Paper

  1. Enhancing Bilingual Lexicon Induction via Bi-directional Translation Pair RetrievingQiuyu Ding, Hailong Cao, Tiejun ZhaoAAAI 2024 · 3 次引用
  2. DM-BLI: Dynamic Multiple Subspaces Alignment for Unsupervised Bilingual Lexicon InductionLing Hu, Yuemei XuACL 2024 · 3 次引用
  3. An Analysis of Euclidean vs. Graph-Based Framing for Bilingual Lexicon Induction from Word Embedding SpacesKelly Marchisio, Youngser Park, Ali Saad-Eldin, Anton Alyakin 等EMNLP Findings 2021 · 2 次引用
  4. Revisiting the Context Window for Cross-lingual Word EmbeddingsRyokan Ri, Yoshimasa TsuruokaACL 2020 · 4 次引用
  5. Beyond Offline Mapping: Learning Cross-lingual Word Embeddings through Context AnchoringAitor Ormazabal, Mikel Artetxe, Aitor Soroa, Gorka Labaka 等ACL 2021
黄昏的海面,两侧是细线勾勒的悬崖