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

Abstract

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 .

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Improving Word Translation via Two-Stage Contrastive Learning cites Bilingual Lexicon Induction via Unsupervised Bitext Construction and Word Alignment
  • Improving Word Translation via Two-Stage Contrastive Learning cites 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 cites Multilingual Alignment of Contextual Word Representations
  • On Bilingual Lexicon Induction with Large Language Models cites Improving Word Translation via Two-Stage Contrastive Learning
  • On Bilingual Lexicon Induction with Large Language Models cites LNMap: Departures from Isomorphic Assumption in Bilingual Lexicon Induction Through Non-Linear Mapping in Latent Space
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

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

Builds on5

  1. Multilingual Alignment of Contextual Word RepresentationsSteven Cao, Nikita Kitaev, Dan KleinICLR 2020 · 211 citations
  2. Cross-lingual Alignment vs Joint Training: A Comparative Study and A Simple Unified FrameworkZirui Wang, Jiateng Xie, Ruochen Xu, Yiming Yang et al.ICLR 2020 · 84 citations
  3. Cross-lingual Alignment Methods for Multilingual BERT: A Comparative StudySaurabh Kulshreshtha, José Luis Redondo García, Ching-Yun ChangEMNLP Findings 2020 · 37 citations
  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 citations
  5. Bilingual Lexicon Induction via Unsupervised Bitext Construction and Word AlignmentHaoyue Shi, Luke Zettlemoyer, Sida I. WangACL 2021

Related papers

  1. Enhancing Bilingual Lexicon Induction via Bi-directional Translation Pair RetrievingQiuyu Ding, Hailong Cao, Tiejun ZhaoAAAI 2024 · 3 citations
  2. DM-BLI: Dynamic Multiple Subspaces Alignment for Unsupervised Bilingual Lexicon InductionLing Hu, Yuemei XuACL 2024 · 3 citations
  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 et al.EMNLP Findings 2021 · 2 citations
  4. Revisiting the Context Window for Cross-lingual Word EmbeddingsRyokan Ri, Yoshimasa TsuruokaACL 2020 · 4 citations
  5. Beyond Offline Mapping: Learning Cross-lingual Word Embeddings through Context AnchoringAitor Ormazabal, Mikel Artetxe, Aitor Soroa, Gorka Labaka et al.ACL 2021
Dusk over the sea between two cliffs drawn in fine vertical lines