Combining relational and attributional similarity for semantic relation classification

Preslav Nakov, Zornitsa Kozareva

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

We combine relational and attributional similarity for the task of identifying instances of semantic relations, such as PRODUCT-PRODUCER and ORIGINENTITY, between nominals in text. We use no pre-existing lexical resources, thus simulating a realistic real-world situation, where the coverage of any such resource is limited. Instead, we mine the Web to automatically extract patterns (verbs, prepositions and coordinating conjunctions) expressing the relationship between the relation arguments, as well as hypernyms and co-hyponyms of the arguments, which we use in instance-based classifiers. The evaluation on the dataset of SemEval-1 Task 4 shows an improvement over the state-of-the-art for the case where using manually annotated WordNet senses is not allowed.

Original languageEnglish
Title of host publicationInternational Conference Recent Advances in Natural Language Processing, RANLP
Pages323-330
Number of pages8
Publication statusPublished - 2011
Externally publishedYes
Event8th International Conference on Recent Advances in Natural Language Processing, RANLP 2011 - Hissar, Bulgaria
Duration: 12 Sep 201114 Sep 2011

Other

Other8th International Conference on Recent Advances in Natural Language Processing, RANLP 2011
CountryBulgaria
CityHissar
Period12/9/1114/9/11

Fingerprint

Classifiers
Semantics

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Software
  • Electrical and Electronic Engineering

Cite this

Nakov, P., & Kozareva, Z. (2011). Combining relational and attributional similarity for semantic relation classification. In International Conference Recent Advances in Natural Language Processing, RANLP (pp. 323-330)

Combining relational and attributional similarity for semantic relation classification. / Nakov, Preslav; Kozareva, Zornitsa.

International Conference Recent Advances in Natural Language Processing, RANLP. 2011. p. 323-330.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nakov, P & Kozareva, Z 2011, Combining relational and attributional similarity for semantic relation classification. in International Conference Recent Advances in Natural Language Processing, RANLP. pp. 323-330, 8th International Conference on Recent Advances in Natural Language Processing, RANLP 2011, Hissar, Bulgaria, 12/9/11.
Nakov P, Kozareva Z. Combining relational and attributional similarity for semantic relation classification. In International Conference Recent Advances in Natural Language Processing, RANLP. 2011. p. 323-330
Nakov, Preslav ; Kozareva, Zornitsa. / Combining relational and attributional similarity for semantic relation classification. International Conference Recent Advances in Natural Language Processing, RANLP. 2011. pp. 323-330
@inproceedings{c98b79d623c5410a94d0f1f45006aa37,
title = "Combining relational and attributional similarity for semantic relation classification",
abstract = "We combine relational and attributional similarity for the task of identifying instances of semantic relations, such as PRODUCT-PRODUCER and ORIGINENTITY, between nominals in text. We use no pre-existing lexical resources, thus simulating a realistic real-world situation, where the coverage of any such resource is limited. Instead, we mine the Web to automatically extract patterns (verbs, prepositions and coordinating conjunctions) expressing the relationship between the relation arguments, as well as hypernyms and co-hyponyms of the arguments, which we use in instance-based classifiers. The evaluation on the dataset of SemEval-1 Task 4 shows an improvement over the state-of-the-art for the case where using manually annotated WordNet senses is not allowed.",
author = "Preslav Nakov and Zornitsa Kozareva",
year = "2011",
language = "English",
pages = "323--330",
booktitle = "International Conference Recent Advances in Natural Language Processing, RANLP",

}

TY - GEN

T1 - Combining relational and attributional similarity for semantic relation classification

AU - Nakov, Preslav

AU - Kozareva, Zornitsa

PY - 2011

Y1 - 2011

N2 - We combine relational and attributional similarity for the task of identifying instances of semantic relations, such as PRODUCT-PRODUCER and ORIGINENTITY, between nominals in text. We use no pre-existing lexical resources, thus simulating a realistic real-world situation, where the coverage of any such resource is limited. Instead, we mine the Web to automatically extract patterns (verbs, prepositions and coordinating conjunctions) expressing the relationship between the relation arguments, as well as hypernyms and co-hyponyms of the arguments, which we use in instance-based classifiers. The evaluation on the dataset of SemEval-1 Task 4 shows an improvement over the state-of-the-art for the case where using manually annotated WordNet senses is not allowed.

AB - We combine relational and attributional similarity for the task of identifying instances of semantic relations, such as PRODUCT-PRODUCER and ORIGINENTITY, between nominals in text. We use no pre-existing lexical resources, thus simulating a realistic real-world situation, where the coverage of any such resource is limited. Instead, we mine the Web to automatically extract patterns (verbs, prepositions and coordinating conjunctions) expressing the relationship between the relation arguments, as well as hypernyms and co-hyponyms of the arguments, which we use in instance-based classifiers. The evaluation on the dataset of SemEval-1 Task 4 shows an improvement over the state-of-the-art for the case where using manually annotated WordNet senses is not allowed.

UR - http://www.scopus.com/inward/record.url?scp=84864744649&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864744649&partnerID=8YFLogxK

M3 - Conference contribution

SP - 323

EP - 330

BT - International Conference Recent Advances in Natural Language Processing, RANLP

ER -