A comparison of vector-based representations for semantic composition

Authors:
William Blacoe;Mirella Lapata
Affiliations:
University of Edinburgh, Edinburgh;University of Edinburgh, Edinburgh
Venue:
EMNLP-CoNLL '12 Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning
Year:
2012

Citing 20
Cited 0

Tensor product variable binding and the representation of symbolic structures in connectionist systems

Artificial Intelligence - On connectionist symbol processing
Placing search in context: the concept revisited

Proceedings of the 10th international conference on World Wide Web
Explorations in Automatic Thesaurus Discovery

Explorations in Automatic Thesaurus Discovery
Automatic word sense discrimination

Computational Linguistics - Special issue on word sense disambiguation
Accurate unlexicalized parsing

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Similarity of Semantic Relations

Computational Linguistics
Unsupervised construction of large paraphrase corpora: exploiting massively parallel news sources

COLING '04 Proceedings of the 20th international conference on Computational Linguistics
A unified architecture for natural language processing: deep neural networks with multitask learning

Proceedings of the 25th international conference on Machine learning
LIBLINEAR: A Library for Large Linear Classification

The Journal of Machine Learning Research
Corpus-based and knowledge-based measures of text semantic similarity

AAAI'06 Proceedings of the 21st national conference on Artificial intelligence - Volume 1
Paraphrase recognition via dissimilarity significance classification

EMNLP '06 Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing
Paraphrase identification as probabilistic quasi-synchronous recognition

ACL '09 Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 1 - Volume 1
Word representations: a simple and general method for semi-supervised learning

ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Nouns are vectors, adjectives are matrices: representing adjective-noun constructions in semantic space

EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Distributional memory: A general framework for corpus-based semantics

Computational Linguistics
A context-theoretic framework for compositionality in distributional semantics

Computational Linguistics
Experimenting with transitive verbs in a DisCoCat

GEMS '11 Proceedings of the GEMS 2011 Workshop on GEometrical Models of Natural Language Semantics
Semi-supervised recursive autoencoders for predicting sentiment distributions

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
Holographic reduced representations

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we address the problem of modeling compositional meaning for phrases and sentences using distributional methods. We experiment with several possible combinations of representation and composition, exhibiting varying degrees of sophistication. Some are shallow while others operate over syntactic structure, rely on parameter learning, or require access to very large corpora. We find that shallow approaches are as good as more computationally intensive alternatives with regards to two particular tests: (1) phrase similarity and (2) paraphrase detection. The sizes of the involved training corpora and the generated vectors are not as important as the fit between the meaning representation and compositional method.