Entities as Experts: Sparse Memory Access with Entity Supervision

• URL: http://arxiv.org/abs/2004.07202v2
• Date: Tue, 6 Oct 2020 19:00:27 GMT
• Title: Entities as Experts: Sparse Memory Access with Entity Supervision
• Abstract summary: We introduce a new model - Entities as Experts (EAE) - that can access distinct memories of the entities mentioned in a piece of text. We show that EAE's learned representations capture sufficient knowledge to answer TriviaQA questions.
• Score: 31.90630901747025
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We focus on the problem of capturing declarative knowledge about entities in the learned parameters of a language model. We introduce a new model - Entities as Experts (EAE) - that can access distinct memories of the entities mentioned in a piece of text. Unlike previous efforts to integrate entity knowledge into sequence models, EAE's entity representations are learned directly from text. We show that EAE's learned representations capture sufficient knowledge to answer TriviaQA questions such as "Which Dr. Who villain has been played by Roger Delgado, Anthony Ainley, Eric Roberts?", outperforming an encoder-generator Transformer model with 10x the parameters. According to the LAMA knowledge probes, EAE contains more factual knowledge than a similarly sized BERT, as well as previous approaches that integrate external sources of entity knowledge. Because EAE associates parameters with specific entities, it only needs to access a fraction of its parameters at inference time, and we show that the correct identification and representation of entities is essential to EAE's performance.

Related papers

• Uncovering Entity Identity Confusion in Multimodal Knowledge Editing [58.07263295190384]
  Multimodal knowledge editing aims to correct the internal knowledge of large vision-language models after deployment.<n>We identify a systemic failure mode in edited models, termed Entity Identity Confusion (EIC)
  arXiv  Detail & Related papers  (2026-05-07T12:14:54Z)
• Consistency-Aware Editing for Entity-level Unlearning in Language Models [53.522931419965424]
  We introduce a novel consistency-aware editing (CAE) framework for entity-level unlearning.<n>CAE aggregates a diverse set of prompts related to a target entity, including its attributes, relations, and adversarial paraphrases.<n>It then jointly learns a low-rank update guided by a consistency regularizer that aligns the editing directions across prompts.
  arXiv  Detail & Related papers  (2025-12-19T15:18:07Z)
• DERA: Dense Entity Retrieval for Entity Alignment in Knowledge Graphs [3.500936203815729]
  We propose a dense entity retrieval framework for Entity Alignment (EA) We leverage language models to uniformly encode various features of entities and facilitate nearest entity search across Knowledge Graphs (KGs) Our approach achieves state-of-the-art performance compared to existing EA methods.
  arXiv  Detail & Related papers  (2024-08-02T10:12:42Z)
• 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)
• GE-Blender: Graph-Based Knowledge Enhancement for Blender [3.8841367260456487]
  Unseen entities can have a large impact on the dialogue generation task. We construct a graph by extracting entity nodes in them, enhancing the representation of the context. We add the named entity tag prediction task to apply the problem that the unseen entity does not exist in the graph.
  arXiv  Detail & Related papers  (2023-01-30T13:00:20Z)
• A Multi-Format Transfer Learning Model for Event Argument Extraction via Variational Information Bottleneck [68.61583160269664]
  Event argument extraction (EAE) aims to extract arguments with given roles from texts. We propose a multi-format transfer learning model with variational information bottleneck. We conduct extensive experiments on three benchmark datasets, and obtain new state-of-the-art performance on EAE.
  arXiv  Detail & Related papers  (2022-08-27T13:52:01Z)
• Class-Specific Semantic Reconstruction for Open Set Recognition [101.24781422480406]
  Open set recognition enables deep neural networks (DNNs) to identify samples of unknown classes. We propose a novel method, called Class-Specific Semantic Reconstruction (CSSR), that integrates the power of auto-encoder (AE) and prototype learning. Results of experiments conducted on multiple datasets show that the proposed method achieves outstanding performance in both close and open set recognition.
  arXiv  Detail & Related papers  (2022-07-05T16:25:34Z)
• A Simple but Effective Pluggable Entity Lookup Table for Pre-trained Language Models [93.39977756450354]
  We propose to build a simple but effective Pluggable Entity Lookup Table (PELT) on demand. PELT can be compatibly plugged as inputs to infuse entity supplemental knowledge into pre-trained language models. Experiments on knowledge-related tasks demonstrate that our method, PELT, can flexibly and effectively transfer entity knowledge from related corpora into PLMs.
  arXiv  Detail & Related papers  (2022-02-27T16:30:22Z)
• KAT: A Knowledge Augmented Transformer for Vision-and-Language [56.716531169609915]
  We propose a novel model - Knowledge Augmented Transformer (KAT) - which achieves a strong state-of-the-art result on the open-domain multimodal task of OK-VQA. Our approach integrates implicit and explicit knowledge in an end to end encoder-decoder architecture, while still jointly reasoning over both knowledge sources during answer generation. An additional benefit of explicit knowledge integration is seen in improved interpretability of model predictions in our analysis.
  arXiv  Detail & Related papers  (2021-12-16T04:37:10Z)
• Interpretable and Low-Resource Entity Matching via Decoupling Feature Learning from Decision Making [22.755892575582788]
  Entity Matching aims at recognizing entity records that denote the same real-world object. We propose a novel EM framework that consists of Heterogeneous Information Fusion (HIF) and Key Attribute Tree (KAT) Induction. Our method is highly efficient and outperforms SOTA EM models in most cases.
  arXiv  Detail & Related papers  (2021-06-08T08:27:31Z)
• LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention [37.111204321059084]
  We propose new pretrained contextualized representations of words and entities based on the bidirectional transformer. Our model is trained using a new pretraining task based on the masked language model of BERT. We also propose an entity-aware self-attention mechanism that is an extension of the self-attention mechanism of the transformer.
  arXiv  Detail & Related papers  (2020-10-02T15:38:03Z)
• Interpretability Analysis for Named Entity Recognition to Understand System Predictions and How They Can Improve [49.878051587667244]
  We examine the performance of several variants of LSTM-CRF architectures for named entity recognition. We find that context representations do contribute to system performance, but that the main factor driving high performance is learning the name tokens themselves. We enlist human annotators to evaluate the feasibility of inferring entity types from the context alone and find that, while people are not able to infer the entity type either for the majority of the errors made by the context-only system, there is some room for improvement.
  arXiv  Detail & Related papers  (2020-04-09T14:37:12Z)

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.