Review of New Types of Relation Extraction Methods

Review of Relation Extraction Methods:
What Is New Out There?
Natalia Konstantinova(B)
University of Wolverhampton, Wolverhampton, UK
[e-mail]

Abstract. Relation extraction is a part of Information Extraction and an established task in Natural Language Processing. This paper presents an overview of the main directions of research and recent advances in the field. It reviews various techniques used for relation extraction including knowledge-based, supervised and self-supervised methods. We also mention applications of relation extraction and identify current trends in the way the field is developing.

Keywords: Relation extraction language processing · Review

1

·

Information extraction

·

Natural

Introduction

The modern world is rapidly developing and, in order to keep up-to-date, people must process large volume of information every day. Not only is the amount of this information is constantly increasing but the type of information is changing all the time. As a consequence of the sheer volume and heterogeneous nature of the information it is becoming impossible to analyse this data manually and new techniques are being used to automate this process. The field of Natural
Language Processing (NLP) addresses this issue by analysing texts written in natural language and trying to understand them and extract valuable information. The problem of obtaining structured information from the text is dealt by
Information Extraction (IE), a field of NLP. In this paper we mainly focus on one stage of IE – Relation Extraction (RE).
This paper is organised in the following way: Sect. 2 describes in more detail the field of Information Extraction and provides background on all its stages,
Sect. 3 introduces the task of Relation Extraction, Sect. 4 presents knowledgebased methods, Sect. 5 describes supervised methods and Sect. 6 provides more details about the self-supervised approach. Section 7 introduces relation extraction as a part of joint modelling of

References: in large databases. In: Proceedings of the 1993 ACM SIGMOD International Conference on Management of Data, SIGMOD ’93, pp. 207–216. ACM, New York (1993) Andersen, P.M., Hayes, P.J., Huettner, A.K., Schmandt, L.M., Nirenburg, I.B., Weinstein, pp. 170–177 (1992) Auer, S., Bizer, C., Kobilarov, G., Lehmann, J., Cyganiak, R., Ives, Z.G.: DBpedia: 4825, pp. 722–735. Springer, Heidelberg (2007) Banko, M., Etzioni, O.: The tradeoffs between open and traditional relation extraction. In: Proceedings of ACL-08: HLT, pp. 28–36 (2008) Banko, M., Cafarella, M.J., Soderland, S., Broadhead, M., Etzioni, O.: Open information extraction from the web (2007) Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation 3, 993–1022 (2003) Bollacker, K., Evans, C., Paritosh, P., Sturge, T., Taylor, J.: Freebase: a collaboratively 1247–1250. ACM, New York (2008) Brin, S.: Extracting patterns and relations from the world wide web of the First International Workshop on the Web and Databases, pp. 172–183 (1998) Review of Relation Extraction Methods: What Is New Out There? 18, pp. 171–178. MIT Press, Cambridge (2006) Cergani, E., Miettinen, P.: Discovering relations using matrix factorization methods. In: He, Q., Iyengar, A., Nejdl, W., Pei, J., Rastogi, R. (eds.) CIKM, pp. 1549–1552. ACM (2013) Collins, M., Dasgupta, S., Schapire, R.E.: A generalization of principal component Cowie, J., Lehnert, W.: Information extraction. Commun. ACM 39(1), 80–91 (1996) Culotta, A., McCallum, A., Betz, J.: Integrating probabilistic extraction models and Association for Computational Linguistics (2006) Etzioni, O., Cafarella, M., Downey, D., Popescu, A.M., Shaked, T., Soderland, S., Weld, D.S., Yates, A.: Unsupervised named-entity extraction from the web: an experimental study. Artif. Intell. 165, 91–134 (2005). (Elsevier Science Publishers Ltd., Essex, UK) (ed.) SCIE 1997. LNCS, vol. 1299, pp. 10–27. Springer, Heidelberg (1997) Grishman, R., Sundheim, B.: Message understanding conference-6: a brief history Association for Computational Linguistics, Morristown (1996) Hearst, M.A.: Automatic acquisition of hyponyms from large text corpora for Computational Linguistics, Morristown (1992) Hoffart, J., Suchanek, F.M., Berberich, K., Lewis-Kelham, E., de Melo, G., Weikum, on World Wide Web, WWW ’11, pp. 229–232. ACM, New York (2011) Hoffmann, R., Zhang, C., Ling, X., Zettlemoyer, L., Weld, D.S.: Knowledge-based weak Linguistics, Stroudsburg (2011) 26 Linguistics, Morristown (2009) Humphreys, K., Gaizauskas, R., Azzam, S., Huyck, C., Mitchell, B., Cunningham, H., Prentice-Hall Inc., Upper Saddle River (2009) Kambhatla, N.: Combining lexical, syntactic, and semantic features with maximum Knowledge Discovery and Data Mining, KDD ’08, pp. 426–434. ACM, New York (2008) 39–43. Association for Computational Linguistics, Stroudsburg (2012) Kozareva, Z., Hovy, E.: Learning arguments and supertypes of semantic relations using