Lune

ACL Findings2022

Graph Neural Networks for Multiparallel Word Alignment

Ayyoob Imani, Lütfi Kerem Senel, Masoud Jalili Sabet, François Yvon, Hinrich Schütze

Abstract

After a period of decrease, interest in word alignments is increasing again for their usefulness in domains such as typological research, cross-lingual annotation projection and machine translation. Generally, alignment algorithms only use bitext and do not make use of the fact that many parallel corpora are multiparallel. Here, we compute high-quality word alignments between multiple language pairs by considering all language pairs together. First, we create a multiparallel word alignment graph, joining all bilingual word alignment pairs in one graph. Next, we use graph neural networks (GNNs) to exploit the graph structure. Our GNN approach (i) utilizes information about the meaning, position and language of the input words, (ii) incorporates information from multiple parallel sentences, (iii) adds and removes edges from the initial alignments, and (iv) yields a prediction model that can generalize beyond the training sentences. We show that community detection provides valuable information for multiparallel word alignment. Our method outperforms previous work on three word alignment datasets and on a downstream task.

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.

1 top-tier paper has 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

  • Graph-Based Multilingual Label Propagation for Low-Resource Part-of-Speech Tagging cites Graph Convolutional Networks with Markov Random Field Reasoning for Social Spammer Detection
  • Graph-Based Multilingual Label Propagation for Low-Resource Part-of-Speech Tagging cites Unsupervised Cross-lingual Representation Learning at Scale
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. Graph-Based Multilingual Label Propagation for Low-Resource Part-of-Speech TaggingAyyoob Imani, Silvia Severini, Masoud Jalili Sabet, François Yvon et al.EMNLP 2022 · 8 citations

Builds on9

  1. LightGCN: Simplifying and Powering Graph Convolution Network for RecommendationXiangnan He, Kuan Deng, Xiang Wang, Yan Li et al.SIGIR 2020 · 4,448 citations
  2. Unsupervised Cross-lingual Representation Learning at ScaleAlexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary et al.ACL 2020 · 539 citations
  3. Graph Convolutional Networks with Markov Random Field Reasoning for Social Spammer DetectionYongji Wu, Defu Lian, Yiheng Xu, Le Wu et al.AAAI 2020 · 194 citations
  4. Semantic Graphs for Generating Deep QuestionsLiangming Pan, Yuxi Xie, Yansong Feng, Tat-Seng Chua et al.ACL 2020 · 79 citations
  5. Accurate Word Alignment Induction from Neural Machine TranslationYun Chen, Yang Liu, Guanhua Chen, Xin Jiang et al.EMNLP 2020 · 56 citations

Related papers

  1. Graph Algorithms for Multiparallel Word AlignmentAyyoob Imani, Masoud Jalili Sabet, Lutfi Kerem Senel, Philipp Dufter et al.EMNLP 2021 · 2 citations
  2. SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized EmbeddingsMasoud Jalili Sabet, Philipp Dufter, François Yvon, Hinrich SchützeEMNLP Findings 2020 · 45 citations
  3. Third-Party Aligner for Neural Word AlignmentsJinpeng Zhang, Chuanqi Dong, Xiangyu Duan, Yuqi Zhang et al.EMNLP Findings 2022
  4. PMI-Align: Word Alignment With Point-Wise Mutual Information Without Requiring Parallel Training DataFatemeh Azadi, Heshaam Faili, Mohammad Javad DoustiACL Findings 2023 · 4 citations
  5. Cross-Network Learning with Partially Aligned Graph Convolutional NetworksMeng JiangKDD 2021 · 9 citations
Dusk over the sea between two cliffs drawn in fine vertical lines