Lune

ACL Findings2022

How Can Cross-lingual Knowledge Contribute Better to Fine-Grained Entity Typing?

Hailong Jin, Tiansi Dong, Lei Hou, Juanzi Li, Hui Chen, Zelin Dai, Yincen Qu

Abstract

Cross-lingual Entity Typing (CLET) aims at improving the quality of entity type prediction by transferring semantic knowledge learned from rich-resourced languages to low-resourced languages. In this paper, by utilizing multilingual transfer learning via the mixture-of-experts approach, our model dynamically capture the relationship between target language and each source language, and effectively generalize to predict types of unseen entities in new languages. Extensive experiments on multilingual datasets show that our method significantly outperforms multiple baselines and can robustly handle negative transfer. We questioned the relationship between language similarity and the performance of CLET. With a series of experiments, we refute the commonsense that the more source the better, and propose the Similarity Hypothesis for CLET.

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

  • DA-Net: A Disentangled and Adaptive Network for Multi-Source Cross-Lingual Transfer Learning cites Single-/Multi-Source Cross-Lingual NER via Teacher-Student Learning on Unlabeled Data in Target Language
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. DA-Net: A Disentangled and Adaptive Network for Multi-Source Cross-Lingual Transfer LearningLing Ge, Chunming Hu, Guanghui Ma, Jihong Liu et al.AAAI 2024 · 3 citations

Builds on7

  1. Fine-Grained Entity Typing for Domain Independent Entity LinkingYasumasa Onoe, Greg DurrettAAAI 2020 · 94 citations
  2. Improving Entity Linking by Modeling Latent Entity Type InformationShuang Chen, Jinpeng Wang, Feng Jiang, Chin-Yew LinAAAI 2020 · 71 citations
  3. Single-/Multi-Source Cross-Lingual NER via Teacher-Student Learning on Unlabeled Data in Target LanguageQianhui Wu, Zijia Lin, Börje Karlsson, Jianguang Lou et al.ACL 2020 · 59 citations
  4. Hierarchical Entity Typing via Multi-level Learning to RankTongfei Chen, Yunmo Chen, Benjamin Van DurmeACL 2020 · 51 citations
  5. LATTE: Latent Type Modeling for Biomedical Entity LinkingMing Zhu, Busra Celikkaya, Parminder Bhatia, Chandan K. ReddyAAAI 2020 · 41 citations

Related papers

  1. Cross-Lingual Contrastive Learning for Fine-Grained Entity Typing for Low-Resource LanguagesXu Han, Yuqi Luo, Weize Chen, Zhiyuan Liu et al.ACL 2022
  2. An Unsupervised Multiple-Task and Multiple-Teacher Model for Cross-lingual Named Entity RecognitionZhuoran Li, Chunming Hu, Xiaohui Guo, Junfan Chen et al.ACL 2022 · 23 citations
  3. Cross-Lingual Transfer in Zero-Shot Cross-Language Entity LinkingElliot Schumacher, James Mayfield, Mark DredzeACL Findings 2021 · 4 citations
  4. CROP: Zero-shot Cross-lingual Named Entity Recognition with Multilingual Labeled Sequence TranslationJian Yang, Shaohan Huang, Shuming Ma, Yuwei Yin et al.EMNLP Findings 2022 · 21 citations
  5. Enhanced Meta-Learning for Cross-Lingual Named Entity Recognition with Minimal ResourcesQianhui Wu, Zijia Lin, Guoxin Wang, Hui Chen et al.AAAI 2020 · 72 citations
Dusk over the sea between two cliffs drawn in fine vertical lines