A Joint-BERT Method for Knowledge Base Question Answering

Zhang, Tianyu; Chen, Zhiyun

doi:10.1145/3578741.3578749

Cited by 3 publications

(11 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Entity linking datasets Most current state-of-the-art EL models [9,10,56,83,90] report on datasets from predominantly the news domain such as AIDA [26], KORE50 [26], AQUAINT [49], ACE 2004, MSNBC [63], N 3 [66], DWIE [89], VoxEL [69], and TAC-KBP 2010-2015 [29,30]. Other frequently used datasets include the web-based IITB [39] and OKE 15/16 [52], as well as the tweet-based Derczynski [13].…”

Section: Related Workmentioning

confidence: 99%

“…Finally, as a baseline, we finetune and evaluate the bi-encoder component of the BLINK model [80] on the various temporal snapshots of our newly introduced TempEL dataset. The bi-encoder is widely used in state-of-the-art entity linking models [80,90] to retrieve the top K (in this work we experiment with K = 64) candidate target entities for a given anchor mention context. Furthermore, its straightforward finetuning and fast retrieval performance on millions of candidate entities [33], make it an ideal choice to test on TempEL.…”

Section: Introductionmentioning

confidence: 99%

“…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.…”

mentioning

confidence: 99%

See 2 more Smart Citations

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: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

TempEL: Linking Dynamically Evolving and Newly Emerging Entities

Zaporojets¹,

Kaffee²,

Deleu³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…We categorize GENRE as simultaneous-generate EL. EntQA (Zhang et al, 2022) provides a novel framework by first finding probable concepts in texts and then treating each extracted concept as queries to detect corresponding mentions in a question-answering fashion which is categorized as NED-NER in our frame-work. Simultaneous-generate and NED-NER fashion are not widely examined in biomedical EL, and they interest us to examine their performances for biomedical EL and partial KB inferences.…”

Section: Related Workmentioning

confidence: 99%

“…This work reviews and evaluates current stateof-the-art EL methods under the partial KB inference scenario. To be specific, we evaluate three paradigms: (1) NER-NED (Yuan et al, 2021(Yuan et al, , 2022c, (2) NED-NER (Zhang et al, 2022), (3) simultaneous generation (Cao et al, 2021a). The first two paradigms are pipeline methods, whose difference is the order of NER and NED.…”

Section: Introductionmentioning

confidence: 99%

Exploring Partial Knowledge Base Inference in Biomedical Entity Linking

Yuan¹,

Lu²,

Zheng³

2023

Preprint

View full text Add to dashboard Cite

Biomedical entity linking (EL) consists of named entity recognition (NER) and named entity disambiguation (NED). EL models are trained on corpora labeled by a predefined KB. However, it is a common scenario that only entities within a subset of the KB are precious to stakeholders. We name this scenario partial knowledge base inference: training an EL model with one KB and inferring on the part of it without further training. In this work, we give a detailed definition and evaluation procedures for this practically valuable but significantly understudied scenario and evaluate methods from three representative EL paradigms. We construct partial KB inference benchmarks and witness a catastrophic degradation in EL performance due to dramatically precision drop. Our findings reveal these EL paradigms can not correctly handle unlinkable mentions (NIL), so they are not robust to partial KB inference. We also propose two simple-and-effective redemption methods to combat the NIL issue with little computational overhead.

show abstract

End-to-End Entity Linking with Hierarchical Reinforcement Learning

Chen

Zhu

Liu

et al. 2023

AAAI

View full text Add to dashboard Cite

Entity linking (EL) is the task of linking the text segments to the referring entities in the knowledge graph, typically decomposed into mention detection, and entity disambiguation. Compared to traditional methods treating the two tasks separately, recent end-to-end entity linking methods exploit the mutual dependency between mentions and entities to achieve better performance. However, existing end-to-end EL methods have problems utilizing the dependency of mentions and entities in the task. To this end, we propose to model the EL task as a hierarchical decision-making process and design a hierarchical reinforcement learning algorithm to solve the problem. We conduct extensive experiments to show that the proposed method achieves state-of-the-art performance in several EL benchmark datasets. Our code is publicly available at https://github.com/lhlclhl/he2eel.

show abstract

A Joint-BERT Method for Knowledge Base Question Answering

Cited by 3 publications

References 5 publications

TempEL: Linking Dynamically Evolving and Newly Emerging Entities

TempEL: Linking Dynamically Evolving and Newly Emerging Entities

Exploring Partial Knowledge Base Inference in Biomedical Entity Linking

End-to-End Entity Linking with Hierarchical Reinforcement Learning

Contact Info

Product

Resources

About