Coherent Entity Disambiguation via Modeling Topic and Categorical Dependency

• URL: http://arxiv.org/abs/2311.03253v1
• Date: Mon, 6 Nov 2023 16:40:13 GMT
• Title: Coherent Entity Disambiguation via Modeling Topic and Categorical Dependency
• Authors: Zilin Xiao, Linjun Shou, Xingyao Zhang, Jie Wu, Ming Gong, Jian Pei, Daxin Jiang
• Abstract summary: Previous entity disambiguation (ED) methods adopt a discriminative paradigm, where prediction is made based on matching scores between mention context and candidate entities. We propose CoherentED, an ED system equipped with novel designs aimed at enhancing the coherence of entity predictions. We achieve new state-of-the-art results on popular ED benchmarks, with an average improvement of 1.3 F1 points.
• Score: 87.16283281290053
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Previous entity disambiguation (ED) methods adopt a discriminative paradigm, where prediction is made based on matching scores between mention context and candidate entities using length-limited encoders. However, these methods often struggle to capture explicit discourse-level dependencies, resulting in incoherent predictions at the abstract level (e.g. topic or category). We propose CoherentED, an ED system equipped with novel designs aimed at enhancing the coherence of entity predictions. Our method first introduces an unsupervised variational autoencoder (VAE) to extract latent topic vectors of context sentences. This approach not only allows the encoder to handle longer documents more effectively, conserves valuable input space, but also keeps a topic-level coherence. Additionally, we incorporate an external category memory, enabling the system to retrieve relevant categories for undecided mentions. By employing step-by-step entity decisions, this design facilitates the modeling of entity-entity interactions, thereby maintaining maximum coherence at the category level. We achieve new state-of-the-art results on popular ED benchmarks, with an average improvement of 1.3 F1 points. Our model demonstrates particularly outstanding performance on challenging long-text scenarios.

Related papers

• Entity-Aware Biaffine Attention Model for Improved Constituent Parsing with Reduced Entity Violations [0.0]
  We propose an entity-aware biaffine attention model for constituent parsing. This model incorporates entity information into the biaffine attention mechanism by using additional entity role vectors for potential phrases. We introduce a new metric, the Entity Violating Rate (EVR), to quantify the extent of entity violations in parsing results.
  arXiv  Detail & Related papers  (2024-09-01T05:59:54Z)
• 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)
• IDRNet: Intervention-Driven Relation Network for Semantic Segmentation [34.09179171102469]
  Co-occurrent visual patterns suggest that pixel relation modeling facilitates dense prediction tasks. Despite the impressive results, existing paradigms often suffer from inadequate or ineffective contextual information aggregation. We propose a novel textbfIntervention-textbfDriven textbfRelation textbfNetwork.
  arXiv  Detail & Related papers  (2023-10-16T18:37:33Z)
• Prototype-based Embedding Network for Scene Graph Generation [105.97836135784794]
  Current Scene Graph Generation (SGG) methods explore contextual information to predict relationships among entity pairs. Due to the diverse visual appearance of numerous possible subject-object combinations, there is a large intra-class variation within each predicate category. Prototype-based Embedding Network (PE-Net) models entities/predicates with prototype-aligned compact and distinctive representations. PL is introduced to help PE-Net efficiently learn such entitypredicate matching, and Prototype Regularization (PR) is devised to relieve the ambiguous entity-predicate matching.
  arXiv  Detail & Related papers  (2023-03-13T13:30:59Z)
• Context-aware Fine-tuning of Self-supervised Speech Models [56.95389222319555]
  We study the use of context, i.e., surrounding segments, during fine-tuning. We propose a new approach called context-aware fine-tuning. We evaluate the proposed approach using the SLUE and Libri-light benchmarks for several downstream tasks.
  arXiv  Detail & Related papers  (2022-12-16T15:46:15Z)
• Modeling Complex Dialogue Mappings via Sentence Semantic Segmentation Guided Conditional Variational Auto-Encoder [23.052838118122835]
  Complex dialogue mappings (CDM), including one-to-many and many-to-one mappings, tend to make dialogue models generate incoherent or dull responses. This paper proposes a Sentence Semantic textbfSegmentation guided textbfConditional textbfVariational textbfAuto-textbfEncoder (SegCVAE) method which can model and take advantages of the CDM data.
  arXiv  Detail & Related papers  (2022-12-01T02:31:10Z)
• End-to-End Entity Detection with Proposer and Regressor [6.25916397918329]
  nested entity recognition receives extensive attention for the widespread existence of the nesting scenario. An end-to-end entity detection approach with proposer and regressor is presented in this paper to tackle the issues. Our model achieves advanced performance in flat and nested NER, achieving a new state-of-the-art F1 score of 80.74 on the GENIA dataset and 72.38 on the WeiboNER dataset.
  arXiv  Detail & Related papers  (2022-10-19T02:42:46Z)
• Entity Disambiguation with Entity Definitions [50.01142092276296]
  Local models have recently attained astounding performances in Entity Disambiguation (ED) Previous works limited their studies to using, as the textual representation of each candidate, only its Wikipedia title. In this paper, we address this limitation and investigate to what extent more expressive textual representations can mitigate it. We report a new state of the art on 2 out of 6 benchmarks we consider and strongly improve the generalization capability over unseen patterns.
  arXiv  Detail & Related papers  (2022-10-11T17:46:28Z)
• Unsupervised Domain Adaptation in Semantic Segmentation: a Review [22.366638308792734]
  The aim of this paper is to give an overview of the recent advancements in the Unsupervised Domain Adaptation (UDA) of deep networks for semantic segmentation.
  arXiv  Detail & Related papers  (2020-05-21T20:10:38Z)
• Improve Variational Autoencoder for Text Generationwith Discrete Latent Bottleneck [52.08901549360262]
  Variational autoencoders (VAEs) are essential tools in end-to-end representation learning. VAEs tend to ignore latent variables with a strong auto-regressive decoder. We propose a principled approach to enforce an implicit latent feature matching in a more compact latent space.
  arXiv  Detail & Related papers  (2020-04-22T14:41:37Z)

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.