Domain-Specific Entity Discovery and Linking Task

Yang, Tao; Zhang, Feng; Li, Xiao; Jia, Qianghuai

doi:10.1007/978-981-10-3168-7_21

Cited by 1 publication

(5 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(1) The joint EDL model proposed in [7]: This method is implemented in [33] with 56 features for entity detection and 17 features for entity linking. (2) The ensemble joint EDL model introduced in [33]: They introduce ensemble classifiers into the joint architecture proposed in [7].…”

Section: Comparison With Other Methodsmentioning

confidence: 99%

“…(2) The ensemble joint EDL model introduced in [33]: They introduce ensemble classifiers into the joint architecture proposed in [7]. (3) The pipeline architecture used in [39]: A CRF model and learning to rank method is adopted in entity detection and entity linking respectively.…”

Section: Comparison With Other Methodsmentioning

confidence: 99%

“…(1) The joint EDL model proposed in [7]: This method is implemented in [33] with 56 features for entity detection and 17 features for entity linking; (2) The ensemble joint EDL model introduced in [33]: They introduce ensemble classifiers into the joint architecture proposed in [7]; (3) The pipeline architecture used in [39]: A CRF model and learning to rank method is adopted in entity detection and entity linking respectively. The last two methods are the top two systems in the DSEDL evaluation task of CCKS2016.…”

Section: Comparison With Other Methodsmentioning

confidence: 99%

“…Li et al [32] mines additional contextual words for each concerned entity type, but the context is limited to words before and after the mention. A CRF model is utilized to infer the entity type in [33]; but training data is insufficient for the complex model, and feature engineering is inevitable.…”

Section: Feature Representationmentioning

confidence: 99%

“…However, links in some DSKBs are very sparse. The works in [7,33] incorporate the link structure of encyclopedias by mapping entities in the DSKB to encyclopedias. Li et al [8] mines word-level disambiguation evidence from the entity description text in the KB.…”

Section: Feature Representationmentioning

confidence: 99%

See 4 more Smart Citations

A Two-Stage Joint Model for Domain-Specific Entity Detection and Linking Leveraging an Unlabeled Corpus

Zhang

Huang

et al. 2017

Information

View full text Add to dashboard Cite

Abstract:The intensive construction of domain-specific knowledge bases (DSKB) has posed an urgent demand for researches about domain-specific entity detection and linking (DSEDL). Joint models are usually adopted in DSEDL tasks, but data imbalance and high computational complexity exist in these models. Besides, traditional feature representation methods are insufficient for domain-specific tasks, due to problems such as lack of labeled data, link sparseness in DSKBs, and so on. In this paper, a two-stage joint (TSJ) model is proposed to solve the data imbalance problem by discriminatively processing entity mentions with different degrees of ambiguity. In addition, three novel methods are put forward to generate effective features by incorporating an unlabeled corpus. One crucial feature involving entity detection is the mention type, extracted by a long short-term memory (LSTM) model trained on automatically annotated data. The other two types of features mainly involve entity linking, including the inner-document topical coherence, which is measured based on entity co-occurring relationships in the corpus, and the cross-document entity coherence evaluated using similar documents. An overall 74.26% F1 value is obtained on a dataset of real-world movie comments, demonstrating the effectiveness of the proposed approach and indicating its potentiality to be used in real-world domain-specific applications.

show abstract