TY - GEN
T1 - Associative and semantic features extracted fromweb-harvested corpora
AU - Iosif, Elias
AU - Giannoudaki, Maria
AU - Fosler-Lussier, Eric
AU - Potamianos, Alexandros
N1 - Funding Information:
Elias Iosif and Maria Giannoudaki were partially funded by the Basic Research Programme, Technical University of Crete, Project Number 99637: “Unsupervised Semantic Relationship Acquisition by Humans and Machines: Application to Automatic Ontology Creation”.
PY - 2012
Y1 - 2012
N2 - We address the problem of automatic classification of associative and semantic relations between words, and particularly those that hold between nouns. Lexical relations such as synonymy, hypernymy/hyponymy, constitute the fundamental types of semantic relations. Associative relations are harder to define, since they include a long list of diverse relations, e.g., "Cause-Effect", "Instrument-Agency". Motivated by findings from the literature of psycholinguistics and corpus linguistics, we propose features that take advantage of general linguistic properties. For evaluation we merged three datasets assembled and validated by cognitive scientists. A proposed priming coefficient that measures the degree of asymmetry in the order of appearance of the words in text achieves the best classification results, followed by context-based similarity metrics. The web-based features achieve classification accuracy that exceeds 85%.
AB - We address the problem of automatic classification of associative and semantic relations between words, and particularly those that hold between nouns. Lexical relations such as synonymy, hypernymy/hyponymy, constitute the fundamental types of semantic relations. Associative relations are harder to define, since they include a long list of diverse relations, e.g., "Cause-Effect", "Instrument-Agency". Motivated by findings from the literature of psycholinguistics and corpus linguistics, we propose features that take advantage of general linguistic properties. For evaluation we merged three datasets assembled and validated by cognitive scientists. A proposed priming coefficient that measures the degree of asymmetry in the order of appearance of the words in text achieves the best classification results, followed by context-based similarity metrics. The web-based features achieve classification accuracy that exceeds 85%.
KW - Associative relations
KW - Priming
KW - Semantic relations
UR - http://www.scopus.com/inward/record.url?scp=85037162049&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85037162049
T3 - Proceedings of the 8th International Conference on Language Resources and Evaluation, LREC 2012
SP - 2991
EP - 2998
BT - Proceedings of the 8th International Conference on Language Resources and Evaluation, LREC 2012
A2 - Dogan, Mehmet Ugur
A2 - Mariani, Joseph
A2 - Moreno, Asuncion
A2 - Goggi, Sara
A2 - Choukri, Khalid
A2 - Calzolari, Nicoletta
A2 - Odijk, Jan
A2 - Declerck, Thierry
A2 - Maegaard, Bente
A2 - Piperidis, Stelios
A2 - Mazo, Helene
A2 - Hamon, Olivier
PB - European Language Resources Association (ELRA)
T2 - 8th International Conference on Language Resources and Evaluation, LREC 2012
Y2 - 21 May 2012 through 27 May 2012
ER -