When the whole is less than the sum of its parts: How composition affects PMI values in distributional semantic vectors

Computational Linguistics

Volumn 42, Issue 2, 2016, Pages 345-350

  Paperno, Denis ^a   Baroni, Marco ^a  

^a UNIVERSITY OF TRENTO   (Italy)

Author keywords

[No Author keywords available]

Indexed keywords

SEMANTICS;

CO-OCCURRENCE; COMPOSITION MODEL; DISTRIBUTIONAL MODELS; INTERNAL COHESION; POINTWISE MUTUAL INFORMATION; SEMANTIC MODEL; SEMANTIC VECTORS; WORD REPRESENTATIONS;

VECTORS;

EID: 84975042556     PISSN: 08912017     EISSN: 15309312     Source Type: Journal    
DOI: 10.1162/COLI_a_00250     Document Type: Article

References (5)

1. Bullinaria, John and Joseph Levy. 2012. Extracting semantic representations from word co-occurrence statistics: Stop-lists, stemming and SVD. Behavior Research Methods, 44:890–907.
2. Church, Kenneth and Peter Hanks. 1990. Word association norms, mutual information, and lexicography. Computational Linguistics, 16(1):22–29.
3. Dinu, Georgiana, Nghia The Pham, and Marco Baroni. 2013. General estimation and evaluation of compositional distributional semantic models. In Proceedings of ACL Workshop on Continuous Vector Space Models and their Compositionality, pages 50–58, Sofia.
4. Mitchell, Jeff and Mirella Lapata. 2010. Composition in distributional models of semantics. Cognitive Science, 34(8):1388–1429.
5. Turney, Peter and Patrick Pantel. 2010. From frequency to meaning: Vector space models of semantics. Journal of Artificial Intelligence Research, 37:141–188.