- *TAREQ AL-MOSLMI, MARC GALLOFRÉ OCAÑA, ANDREAS L. OPDAHL, AND CSABA VERES* - 2020, IEEE Access, Volume 8 ## OVERVIEW - Named Entity Extraction (NEE) involves recognising the mention of the named entity in the text (NER), disambiguating its possible references (NED), and linking the named entity to an object in a knowledge base (NEL) ## NAMED ENTITY DISAMBIGUATION - Independent approaches \[13\], \[50\] use semantic similarity techniques to rank candidate entities solely according to their lexical similarity and/or empirical co-occurrence with mentions. - Collective approaches \[19\], \[52\]–\[54\] also rely on semantic similarity, but they take into account that what is mentioned in the same (part of a) text tends to be about the same topic and that co-occurring entities should therefore often be semantically related \[19\], \[27\]. - A well-matched entity group can be identified using either random walks \[56\], Pagerank \[54\], \[57\], or dense sub-graph computations. Although the collective approaches perform more robustly than the independent ones, computation costs grow rapidly as the numbers of mentions and the lengths of documents increase. \[58\], \[59\] proposes a simplified collective pair-linking approach, which resolves the candidate entities pair-by-pair in order to decrease computational cost and complexity. - *\[57\] M. Pershina, Y. He, and R. Grishman, ‘‘Personalized page rank for named entity disambiguation,’’ in Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol., 2015, pp. 238–243* - *\[59\] M. C. Phan, A. Sun, Y. Tay, J. Han, and C. Li, ‘‘Pair-linking for collective entity disambiguation: Two could be better than all,’’ IEEE Trans. Knowl.* *Data Eng., vol. 31, no. 7, pp. 1383–1396, Jul. 2019.* ## NAMED ENTITY LINKING - Entity Extraction and Linking (EEL) \[20\] is an OpenIE-based approach that employs thematic roles to link relation phrases with known properties used on the semantic web by integrating an ensemble of alternative NER and NEL systems. EEL handles both cases where entities are duplicated because they have the same text fragment and IRI and cases where two or more entities are overlapping because they share the same text fragment \[20\]. -  - recent examples include NN-based end-to-end linking models such as \[97\], \[98\] - *\[97\] P. Le and I. Titov, ‘‘Improving entity linking by modeling latent relations between mentions,’’ in Proc. 56th Annu. Meeting Assoc. Comput. Linguistics, vol. 1, 2018, pp. 1595–1604.* *\[98\] N. Kolitsas, O.-E. Ganea, and T. Hofmann, ‘‘End-to-end neural entity linking,’’ in Proc. 22nd Conf. Comput. Natural Lang. Learn., 2018, pp. 519–529.* - Reference \[98\] proposed the first NN-based end-to-end linking system - Their model reaches SOTA results on the AIDA/CoNLL dataset and, when combined with Stanford NER, it generalizes well to other datasets with different characteristics - One issue is that their accuracy drops dramatically when trained on or applied to small datasets \[98\], so that extensive datasets are required for robust models - *\[108\] O.-E. Ganea, M. Ganea, A. Lucchi, C. Eickhoff, and T. Hofmann, ‘‘Probabilistic bag-of-hyperlinks model for entity linking,’’ in Proc. 25th Conf.* *WWW, 2016, pp. 927–938* -  ## DISCUSSION Reference \[120\] discusses several NEL issues. One is that gold standards can contain wrong annotations (such as U.K instead of UK) and missing annotation links. Another concern is that KBs can contain bad redirects. Moreover, most NEL tools confuse regions and cities that have the same names (e.g., New York State or New York City, and Valencia the region, province, or city). - *\[120\] A. Weichselbraun, P. Kuntschik, and A. M. Braşoveanu, ‘‘Mining and leveraging background knowledge for improving named entity linking,’’in Proc. 8th Int. Conf. Web Intell., Mining Semantics, 2018, p. 27.* ## MINDMAP