Exploring Neural Entity Representations for Semantic Information

Runge, Andrew; Hovy, Eduard

doi:10.18653/v1/2020.blackboxnlp-1.20

Cited by 7 publications

(5 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This progress has been accompanied by the creation of entity-driven datasets for tasks such as language modeling [1,37,59], question answering [32,34,42,71,87], fact checking [4,55,73] and information extraction [85,89], to name a few. Yet, recent findings [18,24,41,64,70,76] suggest that entity representation and identification (i.e., identifying the correct entity that match a given text) are among the main challenges that should be solved to further increase performance on such datasets. We believe that TempEL can contribute to addressing these challenges by: (i) encouraging research on devising more robust methods to creating entity representations that are invariant to temporal changes; and (ii) improving entity identification for non-trivial scenarios involving ambiguous and uncommon mentions (e.g., linked to overshadowed entities as defined above).…”

Section: Entity-driven Datasetsmentioning

confidence: 99%

TempEL: Linking Dynamically Evolving and Newly Emerging Entities

Zaporojets¹,

Kaffee²,

Deleu³

et al. 2023

Preprint

View full text Add to dashboard Cite

In our continuously evolving world, entities change over time and new, previously non-existing or unknown, entities appear. We study how this evolutionary scenario impacts the performance on a well established entity linking (EL) task. For that study, we introduce TempEL, an entity linking dataset that consists of timestratified English Wikipedia snapshots from 2013 to 2022, from which we collect both anchor mentions of entities, and these target entities' descriptions. By capturing such temporal aspects, our newly introduced TempEL resource contrasts with currently existing entity linking datasets, which are composed of fixed mentions linked to a single static version of a target Knowledge Base (e.g., Wikipedia 2010 for CoNLL-AIDA). Indeed, for each of our collected temporal snapshots, TempEL contains links to entities that are continual, i.e., occur in all of the years, as well as completely new entities that appear for the first time at some point. Thus, we enable to quantify the performance of current state-of-the-art EL models for: (i) entities that are subject to changes over time in their Knowledge Base descriptions as well as their mentions' contexts, and (ii) newly created entities that were previously non-existing (e.g., at the time the EL model was trained). Our experimental results show that in terms of temporal performance degradation, (i) continual entities suffer a decrease of up to 3.1% EL accuracy, while (ii) for new entities this accuracy drop is up to 17.9%. This highlights the challenge of the introduced TempEL dataset and opens new research prospects in the area of time-evolving entity disambiguation. 1 1 TempEL dataset, code and models are made public at https://github.com/klimzaporojets/TempEL. 2 Some of the related work [19,38,72,88,90] distinguishes between entity disambiguation and entity linking tasks. This latter including mention detection and disambiguation in an end-to-end setting. In the current work, we follow a more conservative naming convention [44,54,61,62,80], and use the term entity linking and entity disambiguation interchangeably. 36th Conference on Neural Information Processing Systems (NeurIPS 2022) Track on Datasets and Benchmarks.

show abstract

Section: Entity-driven Datasetsmentioning

confidence: 99%

TempEL: Linking Dynamically Evolving and Newly Emerging Entities

Zaporojets¹,

Kaffee²,

Deleu³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…This progress has been accompanied by the creation of entity-driven datasets for tasks such as language modeling [238][239][240], question answering [241][242][243][244][245], fact checking [16,17,246] and information extraction [4,48], to name a few. Yet, recent findings [21,[247][248][249][250][251] identifying the correct entity that match a given text) are among the main challenges that should be solved to further increase performance on such datasets. We believe that TempEL can contribute to addressing these challenges by: (i) encouraging research on devising more robust methods to creating entity representations that are invariant to temporal changes; and (ii) improving entity identification for non-trivial scenarios involving ambiguous and uncommon mentions (e.g., linked to overshadowed entities as defined above).…”

Section: Entity-driven Datasetsmentioning

confidence: 99%

Towards Consistent Document-level Entity Linking: Joint Models for Entity Linking and Coreference Resolution

Zaporojets

Deleu²,

Demeester³

et al. 2022

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

View full text Add to dashboard Cite

We consider the task of document-level entity linking (EL), where it is important to make consistent decisions for entity mentions over the full document jointly. We aim to leverage explicit "connections" among mentions within the document itself: we propose to join EL and coreference resolution (coref) in a single structured prediction task over directed trees and use a globally normalized model to solve it. This contrasts with related works where two separate models are trained for each of the tasks and additional logic is required to merge the outputs. Experimental results on two datasets show a boost of up to +5% F1score on both coref and EL tasks, compared to their standalone counterparts. For a subset of hard cases, with individual mentions lacking the correct EL in their candidate entity list, we obtain a +50% increase in accuracy. 1

show abstract

“…A variety of embedding algorithms have been developed for learning representations of domain concepts and real-world entities from text, including weakly-supervised methods requiring only a terminology (Newman-Griffis et al, 2018); methods using pre-trained NER models for noisy annotation (De Vine et al, 2014;Chen et al, 2020); and methods leveraging explicit annotations of concept mentions (as in Wikipedia) (Yamada et al, 2020). 1 These algorithms capture valuable patterns about concept types and relationships that can inform corpus analysis (Runge and Hovy, 2020).…”

Section: From Words To Domain Conceptsmentioning

confidence: 99%

TextEssence: A Tool for Interactive Analysis of Semantic Shifts Between Corpora

Newman-Griffis¹,

Sivaraman²,

Perer³

et al. 2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

Embeddings of words and concepts capture syntactic and semantic regularities of language; however, they have seen limited use as tools to study characteristics of different corpora and how they relate to one another. We introduce TextEssence, an interactive system designed to enable comparative analysis of corpora using embeddings. TextEssence includes visual, neighbor-based, and similarity-based modes of embedding analysis in a lightweight, web-based interface. We further propose a new measure of embedding confidence based on nearest neighborhood overlap, to assist in identifying high-quality embeddings for corpus analysis. A case study on COVID-19 scientific literature illustrates the utility of the system. TextEssence can be found at https: //textessence.github.io.

show abstract

Exploring Neural Entity Representations for Semantic Information

Cited by 7 publications

References 37 publications

TempEL: Linking Dynamically Evolving and Newly Emerging Entities

TempEL: Linking Dynamically Evolving and Newly Emerging Entities

Towards Consistent Document-level Entity Linking: Joint Models for Entity Linking and Coreference Resolution

TextEssence: A Tool for Interactive Analysis of Semantic Shifts Between Corpora

Contact Info

Product

Resources

About