In Search of Semantic Compositionality in Vector Spaces
ICCS '09 Proceedings of the 17th International Conference on Conceptual Structures: Conceptual Structures: Leveraging Semantic Technologies
EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Computing semantic compositionality in distributional semantics
IWCS '11 Proceedings of the Ninth International Conference on Computational Semantics
Algebraic approaches to compositional distributional semantics
IWCS '11 Proceedings of the Ninth International Conference on Computational Semantics
(Linear) maps of the impossible: capturing semantic anomalies in distributional space
DiSCo '11 Proceedings of the Workshop on Distributional Semantics and Compositionality
Distributed structures and distributional meaning
DiSCo '11 Proceedings of the Workshop on Distributional Semantics and Compositionality
QI'11 Proceedings of the 5th international conference on Quantum interaction
GEMS '11 Proceedings of the GEMS 2011 Workshop on GEometrical Models of Natural Language Semantics
Experimenting with transitive verbs in a DisCoCat
GEMS '11 Proceedings of the GEMS 2011 Workshop on GEometrical Models of Natural Language Semantics
Exploring supervised lda models for assigning attributes to adjective-noun phrases
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Experimental support for a categorical compositional distributional model of meaning
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Entailment above the word level in distributional semantics
EACL '12 Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics
Evaluating distributional models of semantics for syntactically invariant inference
EACL '12 Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics
Domain and function: a dual-space model of semantic relations and compositions
Journal of Artificial Intelligence Research
Distributional techniques for philosophical enquiry
LaTeCH '12 Proceedings of the 6th Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities
First-order vs. higher-order modification in distributional semantics
EMNLP-CoNLL '12 Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning
Parallels between machine and brain decoding
BI'12 Proceedings of the 2012 international conference on Brain Informatics
Unsupervised feature adaptation for cross-domain NLP with an application to compositionality grading
CICLing'13 Proceedings of the 14th international conference on Computational Linguistics and Intelligent Text Processing - Volume Part I
| Hi-index | 0.00 |
In this paper we explore the computational modelling of compositionality in distributional models of semantics. In particular, we model the semantic composition of pairs of adjacent English Adjectives and Nouns from the British National Corpus. We build a vector-based semantic space from a lemmatised version of the BNC, where the most frequent A-N lemma pairs are treated as single tokens. We then extrapolate three different models of compositionality: a simple additive model, a pointwise-multiplicative model and a Partial Least Squares Regression (PLSR) model. We propose two evaluation methods for the implemented models. Our study leads to the conclusion that regression-based models of compositionality generally out-perform additive and multiplicative approaches, and also show a number of advantages that make them very promising for future research.