# Detection, Disambiguation, Re-ranking: Autoregressive Entity Linking as a Multi-Task Problem arXiv: https://arxiv.org/abs/2204.05990 ยท HTML: https://mlsanity.com/paper/2204.05990/ ## Key facts - Cited by 11 papers in the map (data through 14 Oct 2026). - Builds on 29 of its 55 references that are in the map. - First posted on arXiv 12 Apr 2022. ## Builds on (most cited first, 29 of 29) - [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018) - [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019) - [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019) - [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016) - [KILT: a Benchmark for Knowledge Intensive Language Tasks](https://mlsanity.com/paper/2009.02252/) (2020) - [Multi-Task Deep Neural Networks for Natural Language Understanding](https://mlsanity.com/paper/1901.11504/) (2019) - [Autoregressive Entity Retrieval](https://mlsanity.com/paper/2010.00904/) (2020) - [Knowledge Enhanced Contextual Word Representations](https://mlsanity.com/paper/1909.04164/) (2019) - [Self-Alignment Pretraining for Biomedical Entity Representations](https://mlsanity.com/paper/2010.11784/) (2020) - [Entities as Experts: Sparse Memory Access with Entity Supervision](https://mlsanity.com/paper/2004.07202/) (2020) - [E-BERT: Efficient-Yet-Effective Entity Embeddings for BERT](https://mlsanity.com/paper/1911.03681/) (2019) - [Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders](https://mlsanity.com/paper/2104.08027/) (2021) - [End-to-End Neural Entity Linking](https://mlsanity.com/paper/1808.07699/) (2018) - [Scalable Zero-shot Entity Linking with Dense Entity Retrieval](https://mlsanity.com/paper/1911.03814/) (2019) - [Deep Joint Entity Disambiguation with Local Neural Attention](https://mlsanity.com/paper/1704.04920/) (2017) - [REL: An Entity Linker Standing on the Shoulders of Giants](https://mlsanity.com/paper/2006.01969/) (2020) - [COMETA: A Corpus for Medical Entity Linking in the Social Media](https://mlsanity.com/paper/2010.03295/) (2020) - [Multilingual Autoregressive Entity Linking](https://mlsanity.com/paper/2103.12528/) (2021) - [Investigating Entity Knowledge in BERT with Simple Neural End-To-End Entity Linking](https://mlsanity.com/paper/2003.05473/) (2020) - [Improved Neural Relation Detection for Knowledge Base Question Answering](https://mlsanity.com/paper/1704.06194/) (2017) - [Joint Learning of Named Entity Recognition and Entity Linking](https://mlsanity.com/paper/1907.08243/) (2019) - [Highly Parallel Autoregressive Entity Linking with Discriminative Correction](https://mlsanity.com/paper/2109.03792/) (2021) - [EARL: Joint Entity and Relation Linking for Question Answering over Knowledge Graphs](https://mlsanity.com/paper/1801.03825/) (2018) - [Neural Cross-Lingual Entity Linking](https://mlsanity.com/paper/1712.01813/) (2017) - [Capturing Semantic Similarity for Entity Linking with Convolutional Neural Networks](https://mlsanity.com/paper/1604.00734/) (2016) - [CHOLAN: A Modular Approach for Neural Entity Linking on Wikipedia and Wikidata](https://mlsanity.com/paper/2101.09969/) (2021) - [BERT might be Overkill: A Tiny but Effective Biomedical Entity Linker based on Residual Convolutional Neural Networks](https://mlsanity.com/paper/2109.02237/) (2021) - [Zero-shot Medical Entity Retrieval without Annotation: Learning From Rich Knowledge Graph Semantics](https://mlsanity.com/paper/2105.12682/) (2021) - [Towards Explaining STEM Document Classification using Mathematical Entity Linking](https://mlsanity.com/paper/2109.00954/) (2021) ## Built on by (most cited first, 11 of 11) - [Instructed Language Models with Retrievers Are Powerful Entity Linkers](https://mlsanity.com/paper/2311.03250/) (2023) - [A Review on Knowledge Graphs for Healthcare: Resources, Applications, and Promises](https://mlsanity.com/paper/2306.04802/) (2023) - [Grounding Language Models for Visual Entity Recognition](https://mlsanity.com/paper/2402.18695/) (2024) - [SpEL: Structured Prediction for Entity Linking](https://mlsanity.com/paper/2310.14684/) (2023) - [Benchmarking Diverse-Modal Entity Linking with Generative Models](https://mlsanity.com/paper/2305.17337/) (2023) - [Medical Question Understanding and Answering with Knowledge Grounding and Semantic Self-Supervision](https://mlsanity.com/paper/2209.15301/) (2022) - [CONTRASTE: Supervised Contrastive Pre-training With Aspect-based Prompts For Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2310.15577/) (2023) - [Unified Examination of Entity Linking in Absence of Candidate Sets](https://mlsanity.com/paper/2404.11061/) (2024) - [Argument-Aware Approach To Event Linking](https://mlsanity.com/paper/2403.15097/) (2024) - [Mapping the Past: Geographically Linking an Early 20th Century Swedish Encyclopedia with Wikidata](https://mlsanity.com/paper/2406.17903/) (2024) - [Enriching Social Science Research via Survey Item Linking](https://mlsanity.com/paper/2412.15831/) (2024) ## Abstract (arXiv) 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.