ACL Findings2022
Detection, Disambiguation, Re-ranking: Autoregressive Entity Linking as a Multi-Task Problem
Khalil Mrini, Shaoliang Nie, Jiatao Gu, Sinong Wang, Maziar Sanjabi, Hamed Firooz
Abstract
We propose an autoregressive entity linking model, that is trained with two auxiliary tasks, and learns to re-rank generated samples at inference time. Our proposed novelties address two weaknesses in the literature. First, a recent method proposes to learn mention detection and then entity candidate selection, but relies on predefined sets of candidates. We use encoder-decoder autoregressive entity linking in order to bypass this need, and propose to train mention detection as an auxiliary task instead. Second, previous work suggests that re-ranking could help correct prediction errors. We add a new, auxiliary task, match prediction, to learn re-ranking. Without the use of a knowledge base or candidate sets, our model sets a new state of the art in two benchmark datasets of entity linking: COMETA in the biomedical domain, and AIDA-CoNLL in the news domain. We show through ablation studies that each of the two auxiliary tasks increases performance, and that re-ranking is an important factor to the increase. Finally, our low-resource experimental results suggest that performance on the main task benefits from the knowledge learned by the auxiliary tasks, and not just from the additional training data.
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.
3 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- BERT might be Overkill: A Tiny but Effective Biomedical Entity Linker based on Residual Convolutional Neural Networks cites Scalable Zero-shot Entity Linking with Dense Entity Retrieval
- SpEL: Structured Prediction for Entity Linking cites Scalable Zero-shot Entity Linking with Dense Entity Retrieval
- SpEL: Structured Prediction for Entity Linking cites E-BERT: Efficient-Yet-Effective Entity Embeddings for BERT
- Instructed Language Models with Retrievers Are Powerful Entity Linkers cites Entities as Experts: Sparse Memory Access with Entity Supervision
Cited by top-tier papers3
- SpEL: Structured Prediction for Entity LinkingHassan Shavarani, Anoop SarkarEMNLP 2023 · 8 citations
- Instructed Language Models with Retrievers Are Powerful Entity LinkersZilin Xiao, Ming Gong, Jie Wu, Xingyao Zhang et al.EMNLP 2023 · 7 citations
- End-to-End Entity Linking with Hierarchical Reinforcement LearningLihan Chen, Tinghui Zhu, Jingping Liu, Jiaqing Liang et al.AAAI 2023 · 5 citations
Builds on8
- Scalable Zero-shot Entity Linking with Dense Entity RetrievalLedell Wu, Fabio Petroni, Martin Josifoski, Sebastian Riedel et al.EMNLP 2020 · 336 citations
- E-BERT: Efficient-Yet-Effective Entity Embeddings for BERTNina Pörner, Ulli Waltinger, Hinrich SchützeEMNLP Findings 2020 · 146 citations
- Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence EncodersFangyu Liu, Ivan Vulic, Anna Korhonen, Nigel CollierEMNLP 2021 · 85 citations
- Entities as Experts: Sparse Memory Access with Entity SupervisionThibault Févry, Livio Baldini Soares, Nicholas FitzGerald, Eunsol Choi et al.EMNLP 2020 · 39 citations
- BERT might be Overkill: A Tiny but Effective Biomedical Entity Linker based on Residual Convolutional Neural NetworksTuan Manh Lai, Heng Ji, ChengXiang ZhaiEMNLP Findings 2021 · 25 citations
Related papers
- Improving Biomedical Entity Linking with Cross-Entity InteractionZhenran Xu, Yulin Chen, Baotian HuAAAI 2023 · 12 citations
- DeepType 2: Superhuman Entity Linking, All You Need Is Type InteractionsJonathan RaimanAAAI 2022 · 9 citations
- EntQA: Entity Linking as Question AnsweringWenzheng Zhang, Wenyue Hua, Karl StratosICLR 2022 · 64 citations
- Entity Disambiguation with Extreme Multi-label RankingJyun-Yu Jiang, Wei-Cheng Chang, Jiong Zhang, Cho-Jui Hsieh et al.WWW 2024 · 6 citations
- COMETA: A Corpus for Medical Entity Linking in the Social MediaMarco Basaldella, Fangyu Liu, Ehsan Shareghi, Nigel CollierEMNLP 2020 · 4 citations
