On the Surprising Effectiveness of Name Matching Alone in Autoregressive Entity Linking (original) (raw)

Improving Entity Linking by Modeling Latent Relations between Mentions

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2018

Entity linking involves aligning textual mentions of named entities to their corresponding entries in a knowledge base. Entity linking systems often exploit relations between textual mentions in a document (e.g., coreference) to decide if the linking decisions are compatible. Unlike previous approaches, which relied on supervised systems or heuristics to predict these relations, we treat relations as latent variables in our neural entity-linking model. We induce the relations without any supervision while optimizing the entity-linking system in an end-to-end fashion. Our multirelational model achieves the best reported scores on the standard benchmark (AIDA-CoNLL) and substantially outperforms its relation-agnostic version. Its training also converges much faster, suggesting that the injected structural bias helps to explain regularities in the training data.

Joint Learning of Local and Global Features for Entity Linking via Neural Networks

2016

Previous studies have highlighted the necessity for entity linking systems to capture the local entity-mention similarities and the global topical coherence. We introduce a novel framework based on convolutional neural networks and recurrent neural networks to simultaneously model the local and global features for entity linking. The proposed model benefits from the capacity of convolutional neural networks to induce the underlying representations for local contexts and the advantage of recurrent neural networks to adaptively compress variable length sequences of predictions for global constraints. Our evaluation on multiple datasets demonstrates the effectiveness of the model and yields the state-of-the-art performance on such datasets. In addition, we examine the entity linking systems on the domain adaptation setting that further demonstrates the cross-domain robustness of the proposed model.

OPTIC: A Deep Neural Network Approach for Entity Linking using Word and Knowledge Embeddings

2020

Entity Linking (EL) for microblog posts is still a challenge because of their usually informal language and limited textual context. Most current EL approaches for microblog posts expand each post context by considering related posts, user interest information, spatial data, and temporal data. Thus, these approaches can be too invasive, compromising user privacy. It hinders data sharing and experimental reproducibility. Moreover, most of these approaches employ graph-based methods instead of state-of-the-art embedding-based ones. This paper proposes a knowledge-intensive EL approach for microblog posts called OPTIC. It relies on a jointly trained word and knowledge embeddings to represent contexts given by the semantics of words and entity candidates for mentions found in the posts. These embedded semantic contexts feed a deep neural network that exploits semantic coherence along with the popularity of the entity candidates for doing their disambiguation. Experiments using the benchmark system GERBIL shows that OPTIC outperforms most of the approaches on the NEEL challenge 2016 dataset. d

YELM: End-to-End Contextualized Entity Linking

ArXiv, 2019

We propose yet another entity linking model (YELM) which links words to entities instead of spans. This overcomes any difficulties associated with the selection of good candidate mention spans and makes the joint training of mention detection (MD) and entity disambiguation (ED) easily possible. Our model is based on BERT and produces contextualized word embeddings which are trained against a joint MD and ED objective. We achieve state-of-the-art results on several standard entity linking (EL) datasets.

Entity Linking via Joint Encoding of Types, Descriptions, and Context

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, 2017

For accurate entity linking, we need to capture various information aspects of an entity, such as its description in a KB, contexts in which it is mentioned, and structured knowledge. Additionally, a linking system should work on texts from different domains without requiring domain-specific training data or hand-engineered features. In this work we present a neural, modular entity linking system that learns a unified dense representation for each entity using multiple sources of information, such as its description, contexts around its mentions, and its fine-grained types. We show that the resulting entity linking system is effective at combining these sources, and performs competitively, sometimes out-performing current state-of-theart systems across datasets, without requiring any domain-specific training data or hand-engineered features. We also show that our model can effectively "embed" entities that are new to the KB, and is able to link its mentions accurately.

Context-Based Entity Linking – University of Amsterdam at TAC 2012

This paper describes our approach to the 2012 Text Analysis Conference (TAC) Knowledge Base Population (KBP) entity linking track. For this task, we turn to a state-of-the-art system for entity linking in microblog posts. Compared to the little context microblog posts provide, the documents in the TAC KBP track provide context of greater length and of a less noisy nature. In this paper, we adapt the entity linking system for microblog posts to the KBP task by extending it with approaches that explicitly rely on the query's context. We show that incorporating novel features that leverage the context on the entity-level can lead to improved performance in the TAC KBP task.

Word Embeddings for Unsupervised Named Entity Linking

2019

The huge amount of textual user-generated content on the Web has incredibly grown in the last decade, creating new relevant opportunities for different real-world applications and domains. In particular, microblogging platforms enables the collection of continuously and instantly updated information. The organization and extraction of valuable knowledge from these contents are fundamental for ensuring profitability and efficiency to companies and institutions. This paper presents an unsupervised model for the task of Named Entity Linking in microblogging environments. The aim is to link the named entity mentions in a text with their corresponding knowledge-base entries exploiting a novel heterogeneous representation space characterized by more meaningful similarity measures between words and named entities, obtained by Word Embeddings. The proposed model has been evaluated on different benchmark datasets proposed for Named Entity Linking challenges for English and Italian language. ...

BUAP_1: A Naïve Approach to the Entity Linking Task

In these notes we are reporting the obtained results by applying the Naïve Bayes classifier to the Entity Linking task of the Knowledge Base Population track at the Text Analysis Conference. Three different runs were submitted to the challenge, each with different ways of approaching the application of the above mentioned classifier. The obtained results were very low, and recent analyses showed that this issue was derived from errors at the pre-processing stage.

End-to-End Entity Linking and Disambiguation leveraging Word and Knowledge Graph Embeddings

ArXiv, 2020

Entity linking - connecting entity mentions in a natural language utterance to knowledge graph (KG) entities is a crucial step for question answering over KGs. It is often based on measuring the string similarity between the entity label and its mention in the question. The relation referred to in the question can help to disambiguate between entities with the same label. This can be misleading if an incorrect relation has been identified in the relation linking step. However, an incorrect relation may still be semantically similar to the relation in which the correct entity forms a triple within the KG; which could be captured by the similarity of their KG embeddings. Based on this idea, we propose the first end-to-end neural network approach that employs KG as well as word embeddings to perform joint relation and entity classification of simple questions while implicitly performing entity disambiguation with the help of a novel gating mechanism. An empirical evaluation shows that ...

Towards holistic Entity Linking: Survey and directions

Information Systems, 2021

Entity Linking (EL) empowers Natural Language Processing applications by linking relevant mentions found in raw textual data to precise information about what they supposedly stand for. However, EL approaches have mostly focused on particular kinds of inputs and frequently fail to properly handle texts from specific sources (e.g., microblogs) that have particularities such as grammatical errors, slangs, lack of contextual information and other problems, besides difficulties to exploit their associated data (e.g., time stamps, geographic indicators, authors' profile data). Some EL approaches have been devised to circumvent such challenges. They exploit several inputs, data features, and EL methods in a synergetic process for more powerful and robust collective EL. This paper reviews recent works that employ such holistic strategies for EL, discusses their limitations, and proposes directions for further advancing holistic EL approaches.