Tags

Type your tag names separated by a space and hit enter

Affixation in semantic space: Modeling morpheme meanings with compositional distributional semantics.
Psychol Rev 2015; 122(3):485-515PR

Abstract

The present work proposes a computational model of morpheme combination at the meaning level. The model moves from the tenets of distributional semantics, and assumes that word meanings can be effectively represented by vectors recording their co-occurrence with other words in a large text corpus. Given this assumption, affixes are modeled as functions (matrices) mapping stems onto derived forms. Derived-form meanings can be thought of as the result of a combinatorial procedure that transforms the stem vector on the basis of the affix matrix (e.g., the meaning of nameless is obtained by multiplying the vector of name with the matrix of -less). We show that this architecture accounts for the remarkable human capacity of generating new words that denote novel meanings, correctly predicting semantic intuitions about novel derived forms. Moreover, the proposed compositional approach, once paired with a whole-word route, provides a new interpretative framework for semantic transparency, which is here partially explained in terms of ease of the combinatorial procedure and strength of the transformation brought about by the affix. Model-based predictions are in line with the modulation of semantic transparency on explicit intuitions about existing words, response times in lexical decision, and morphological priming. In conclusion, we introduce a computational model to account for morpheme combination at the meaning level. The model is data-driven, theoretically sound, and empirically supported, and it makes predictions that open new research avenues in the domain of semantic processing. (PsycINFO Database Record

Authors+Show Affiliations

Center for Mind/Brain Sciences, University of Trento.Center for Mind/Brain Sciences, University of Trento.

Pub Type(s)

Journal Article
Research Support, Non-U.S. Gov't

Language

eng

PubMed ID

26120909

Citation

Marelli, Marco, and Marco Baroni. "Affixation in Semantic Space: Modeling Morpheme Meanings With Compositional Distributional Semantics." Psychological Review, vol. 122, no. 3, 2015, pp. 485-515.
Marelli M, Baroni M. Affixation in semantic space: Modeling morpheme meanings with compositional distributional semantics. Psychol Rev. 2015;122(3):485-515.
Marelli, M., & Baroni, M. (2015). Affixation in semantic space: Modeling morpheme meanings with compositional distributional semantics. Psychological Review, 122(3), pp. 485-515. doi:10.1037/a0039267.
Marelli M, Baroni M. Affixation in Semantic Space: Modeling Morpheme Meanings With Compositional Distributional Semantics. Psychol Rev. 2015;122(3):485-515. PubMed PMID: 26120909.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Affixation in semantic space: Modeling morpheme meanings with compositional distributional semantics. AU - Marelli,Marco, AU - Baroni,Marco, PY - 2015/6/30/entrez PY - 2015/6/30/pubmed PY - 2016/12/15/medline SP - 485 EP - 515 JF - Psychological review JO - Psychol Rev VL - 122 IS - 3 N2 - The present work proposes a computational model of morpheme combination at the meaning level. The model moves from the tenets of distributional semantics, and assumes that word meanings can be effectively represented by vectors recording their co-occurrence with other words in a large text corpus. Given this assumption, affixes are modeled as functions (matrices) mapping stems onto derived forms. Derived-form meanings can be thought of as the result of a combinatorial procedure that transforms the stem vector on the basis of the affix matrix (e.g., the meaning of nameless is obtained by multiplying the vector of name with the matrix of -less). We show that this architecture accounts for the remarkable human capacity of generating new words that denote novel meanings, correctly predicting semantic intuitions about novel derived forms. Moreover, the proposed compositional approach, once paired with a whole-word route, provides a new interpretative framework for semantic transparency, which is here partially explained in terms of ease of the combinatorial procedure and strength of the transformation brought about by the affix. Model-based predictions are in line with the modulation of semantic transparency on explicit intuitions about existing words, response times in lexical decision, and morphological priming. In conclusion, we introduce a computational model to account for morpheme combination at the meaning level. The model is data-driven, theoretically sound, and empirically supported, and it makes predictions that open new research avenues in the domain of semantic processing. (PsycINFO Database Record SN - 1939-1471 UR - https://www.unboundmedicine.com/medline/citation/26120909/Affixation_in_semantic_space:_Modeling_morpheme_meanings_with_compositional_distributional_semantics_ L2 - http://content.apa.org/journals/rev/122/3/485 DB - PRIME DP - Unbound Medicine ER -