Entity Linking via Dual and Cross-Attention Encoders

• URL: http://arxiv.org/abs/2004.03555v1
• Date: Tue, 7 Apr 2020 17:28:28 GMT
• Title: Entity Linking via Dual and Cross-Attention Encoders
• Authors: Oshin Agarwal, Daniel M. Bikel
• Abstract summary: We propose a dual-encoder entity retrieval system that learns mention and entity representations in the same space. We then rerank the entities by using a cross-attention encoder over the target mention and each of the candidate entities. We achieve state-of-art results on TACKBP-2010 dataset, with 92.05% accuracy.
• Score: 16.23946458604865
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Entity Linking has two main open areas of research: 1) generate candidate entities without using alias tables and 2) generate more contextual representations for both mentions and entities. Recently, a solution has been proposed for the former as a dual-encoder entity retrieval system (Gillick et al., 2019) that learns mention and entity representations in the same space, and performs linking by selecting the nearest entity to the mention in this space. In this work, we use this retrieval system solely for generating candidate entities. We then rerank the entities by using a cross-attention encoder over the target mention and each of the candidate entities. Whereas a dual encoder approach forces all information to be contained in the small, fixed set of vector dimensions used to represent mentions and entities, a crossattention model allows for the use of detailed information (read: features) from the entirety of each <mention, context, candidate entity> tuple. We experiment with features used in the reranker including different ways of incorporating document-level context. We achieve state-of-the-art results on TACKBP-2010 dataset, with 92.05% accuracy. Furthermore, we show how the rescoring model generalizes well when trained on the larger CoNLL-2003 dataset and evaluated on TACKBP-2010.

Related papers

• OneNet: A Fine-Tuning Free Framework for Few-Shot Entity Linking via Large Language Model Prompting [49.655711022673046]
  OneNet is an innovative framework that utilizes the few-shot learning capabilities of Large Language Models (LLMs) without the need for fine-tuning. OneNet is structured around three key components prompted by LLMs: (1) an entity reduction processor that simplifies inputs by summarizing and filtering out irrelevant entities, (2) a dual-perspective entity linker that combines contextual cues and prior knowledge for precise entity linking, and (3) an entity consensus judger that employs a unique consistency algorithm to alleviate the hallucination in the entity linking reasoning.
  arXiv  Detail & Related papers  (2024-10-10T02:45:23Z)
• Entity Disambiguation via Fusion Entity Decoding [68.77265315142296]
  We propose an encoder-decoder model to disambiguate entities with more detailed entity descriptions. We observe +1.5% improvements in end-to-end entity linking in the GERBIL benchmark compared with EntQA.
  arXiv  Detail & Related papers  (2024-04-02T04:27:54Z)
• A Read-and-Select Framework for Zero-shot Entity Linking [33.15662306409253]
  We propose a read-and-select (ReS) framework by modeling the main components of entity disambiguation. Our method achieves the state-of-the-art performance on the established zero-shot entity linking dataset ZESHEL with a 2.55% micro-average accuracy gain.
  arXiv  Detail & Related papers  (2023-10-19T04:08:10Z)
• Towards Better Entity Linking with Multi-View Enhanced Distillation [30.554387215553238]
  This paper proposes a Multi-View Enhanced Distillation (MVD) framework for entity linking. MVD can effectively transfer knowledge of multiple fine-grained and mention-relevant parts within entities from cross-encoders to dual-encoders. Experiments show our method achieves state-of-the-art performance on several entity linking benchmarks.
  arXiv  Detail & Related papers  (2023-05-27T05:15:28Z)
• Modeling Entities as Semantic Points for Visual Information Extraction in the Wild [55.91783742370978]
  We propose an alternative approach to precisely and robustly extract key information from document images. We explicitly model entities as semantic points, i.e., center points of entities are enriched with semantic information describing the attributes and relationships of different entities. The proposed method can achieve significantly enhanced performance on entity labeling and linking, compared with previous state-of-the-art models.
  arXiv  Detail & Related papers  (2023-03-23T08:21:16Z)
• UnifieR: A Unified Retriever for Large-Scale Retrieval [84.61239936314597]
  Large-scale retrieval is to recall relevant documents from a huge collection given a query. Recent retrieval methods based on pre-trained language models (PLM) can be coarsely categorized into either dense-vector or lexicon-based paradigms. We propose a new learning framework, UnifieR which unifies dense-vector and lexicon-based retrieval in one model with a dual-representing capability.
  arXiv  Detail & Related papers  (2022-05-23T11:01:59Z)
• Improving Candidate Retrieval with Entity Profile Generation for Wikidata Entity Linking [76.00737707718795]
  We propose a novel candidate retrieval paradigm based on entity profiling. We use the profile to query the indexed search engine to retrieve candidate entities. Our approach complements the traditional approach of using a Wikipedia anchor-text dictionary.
  arXiv  Detail & Related papers  (2022-02-27T17:38:53Z)
• MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representations [28.28940043641958]
  We propose a novel approach for entity retrieval that constructs multi-view representations for entity descriptions and approximates the optimal view for mentions via a searching method. Our method achieves the state-of-the-art performance on ZESHEL and improves the quality of candidates on three standard Entity Linking datasets.
  arXiv  Detail & Related papers  (2021-09-13T05:51:45Z)
• RAGA: Relation-aware Graph Attention Networks for Global Entity Alignment [14.287681294725438]
  We propose a novel framework based on Relation-aware Graph Attention Networks to capture the interactions between entities and relations. Our framework adopts the self-attention mechanism to spread entity information to the relations and then aggregate relation information back to entities.
  arXiv  Detail & Related papers  (2021-03-01T06:30:51Z)
• Autoregressive Entity Retrieval [55.38027440347138]
  Entities are at the center of how we represent and aggregate knowledge. The ability to retrieve such entities given a query is fundamental for knowledge-intensive tasks such as entity linking and open-domain question answering. We propose GENRE, the first system that retrieves entities by generating their unique names, left to right, token-by-token in an autoregressive fashion.
  arXiv  Detail & Related papers  (2020-10-02T10:13:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.