Academia.eduAcademia.edu

Outline

Title
Abstract
Introduction
Qualitative Analysis of Offset Representations
Results
Related Work
Conclusion
References
All Topics
Computer Science

Improving Semantic Composition with Offset Inference

Profile image of Julie WeedsJulie Weeds

Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

https://doi.org/10.18653/V1/P17-2069
visibility

…

description

8 pages

link

1 file

Abstract

Count-based distributional semantic models suffer from sparsity due to unobserved but plausible co-occurrences in any text collection. This problem is amplified for models like Anchored Packed Trees (APTs), that take the grammatical type of a co-occurrence into account. We therefore introduce a novel form of distributional inference that exploits the rich type structure in APTs and infers missing data by the same mechanism that is used for semantic composition.

Related papers

SemEval-2014 Task 1: Evaluation of Compositional Distributional Semantic Models on Full Sentences through Semantic Relatedness and Textual Entailment
Roberto Zamparelli

Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), 2014

This paper presents the task on the evaluation of Compositional Distributional Semantics Models on full sentences organized for the first time within SemEval-2014. Participation was open to systems based on any approach. Systems were presented with pairs of sentences and were evaluated on their ability to predict human judgments on (i) semantic relatedness and (ii) entailment. The task attracted 21 teams, most of which participated in both subtasks. We received 17 submissions in the relatedness subtask (for a total of 66 runs) and 18 in the entailment subtask (65 runs).

View PDFchevron_right
Estimating linear models for compositional distributional semantics
Ioannis Korkontzelos

2010

Abstract In distributional semantics studies, there is a growing attention in compositionally determining the distributional meaning of word sequences. Yet, compositional distributional models depend on a large set of parameters that have not been explored. In this paper we propose a novel approach to estimate parameters for a class of compositional distributional models: the additive models. Our approach leverages on two main ideas. Firstly, a novel idea for extracting compositional distributional semantics examples.

View PDFchevron_right
Compositional Distributional Semantics Models in Chunk-based Smoothed Tree Kernels
Nghĩa Phạm

Proceedings of the Third Joint Conference on Lexical and Computational Semantics (*SEM 2014), 2014

The field of compositional distributional semantics has proposed very interesting and reliable models for accounting the distributional meaning of simple phrases. These models however tend to disregard the syntactic structures when they are applied to larger sentences. In this paper we propose the chunk-based smoothed tree kernels (CSTKs) as a way to exploit the syntactic structures as well as the reliability of these compositional models for simple phrases. We experiment with the recognizing textual entailment datasets. Our experiments show that our CSTKs perform better than basic compositional distributional semantic models (CDSMs) recursively applied at the sentence level, and also better than syntactic tree kernels.

View PDFchevron_right
A practical and linguistically-motivated approach to compositional distributional semantics
Nghĩa Phạm

Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2014

Distributional semantic methods to approximate word meaning with context vectors have been very successful empirically, and the last years have seen a surge of interest in their compositional extension to phrases and sentences. We present here a new model that, like those of Coecke et al. (2010) and Baroni and Zamparelli (2010), closely mimics the standard Montagovian semantic treatment of composition in distributional terms. However, our approach avoids a number of issues that have prevented the application of the earlier linguistically-motivated models to full-fledged, real-life sentences. We test the model on a variety of empirical tasks, showing that it consistently outperforms a set of competitive rivals.

View PDFchevron_right
A Generalisation of Lexical Functions for Composition in Distributional Semantics
Nicholas Asher

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 2015

Over the last two decades, numerous algorithms have been developed that successfully capture something of the semantics of single words by looking at their distribution in text and comparing these distributions in a vector space model. However, it is not straightforward to construct meaning representations beyond the level of individual words-i.e. the combination of words into larger units-using distributional methods. Our contribution is twofold. First of all, we carry out a largescale evaluation, comparing different composition methods within the distributional framework for the cases of both adjectivenoun and noun-noun composition, making use of a newly developed dataset. Secondly, we propose a novel method for composition, which generalises the approach by Baroni and Zamparelli (2010). The performance of our novel method is also evaluated on our new dataset and proves competitive with the best methods.

View PDFchevron_right
Dissecting the Practical Lexical Function Model for Compositional Distributional Semantics
Jason Utt, Abhijeet Gupta

The Practical Lexical Function model (PLF) is a recently proposed compositional distribu- tional semantic model which provides an el- egant account of composition, striking a bal- ance between expressiveness and robustness and performing at the state-of-the-art. In this paper, we identify an inconsistency in PLF be- tween the objective function at training and the prediction at testing which leads to an over- counting of the predicate’s contribution to the meaning of the phrase. We investigate two pos- sible solutions of which one (the exclusion of simple lexical vector at test time) improves per- formance significantly on two out of the three composition datasets.

View PDFchevron_right
How we BLESSed distributional semantic evaluation
Alessandro Lenci

We introduce BLESS, a data set specifically designed for the evaluation of distributional semantic models. BLESS contains a set of tuples instantiating different, explicitly typed semantic relations, plus a number of controlled random tuples. It is thus possible to assess the ability of a model to detect truly related word pairs, as well as to perform in-depth analyses of the types of semantic relations that a model favors. We discuss the motivations for BLESS, describe its construction and structure, and present examples of its usage in the evaluation of distributional semantic models.

View PDFchevron_right
Event Knowledge in Compositional Distributional Semantics
Ludovica Pannitto

Master Thesis, 2018

View PDFchevron_right
The role of syntactic dependencies in compositional distributional semantics
pablo gamallo

Corpus Linguistics and Linguistic Theory, 2017

This article provides a preliminary semantic framework for Dependency Grammar in which lexical words are semantically defined as contextual distributions (sets of contexts) while syntactic dependencies are compositional operations on word distributions. More precisely, any syntactic dependency uses the contextual distribution of the dependent word to restrict the distribution of the head, and makes use of the contextual distribution of the head to restrict that of the dependent word. The interpretation of composite expressions and sentences, which are analyzed as a tree of binary dependencies, is performed by restricting the contexts of words dependency by dependency in a left-to-right incremental way. Consequently, the meaning of the whole composite expression or sentence is not a single representation, but a list of contextualized senses, namely the restricted distributions of its constituent (lexical) words. We report the results of two large-scale corpus-based experiments on two...

View PDFchevron_right
DISSECT: DIStributional SEmantics Composition Toolkit
Nghĩa Phạm

We introduce DISSECT, a toolkit to build and explore computational models of word, phrase and sentence meaning based on the principles of distributional semantics. The toolkit focuses in particular on compositional meaning, and implements a number of composition methods that have been proposed in the literature. Furthermore, DISSECT can be useful to researchers and practitioners who need models of word meaning (without composition) as well, as it supports various methods to construct distributional semantic spaces, assessing similarity and even evaluating against benchmarks, that are independent of the composition infrastructure.

View PDFchevron_right

References (54)

  1. Paolo Annesi, Danilo Croce, and Roberto Basili. 2014. Semantic compositionality in tree ker- nels. In Proceedings of the 23rd ACM Inter- national Conference on Conference on Informa- tion and Knowledge Management. ACM, New York, NY, USA, CIKM '14, pages 1029-1038. https://doi.org/10.1145/2661829.2661955.
  2. Marco Baroni, Raffaella Bernardi, and Roberto Zam- parelli. 2014. Frege in space: A program for compo- sitional distributional semantics. Linguistic Issues in Language Technology 9(6):5-110.
  3. Marco Baroni, Silvia Bernardini, Adriano Fer- raresi, and Eros Zanchetta. 2009. The wacky wide web: a collection of very large linguis- tically processed web-crawled corpora.
  4. Lan- guage Resources and Evaluation 43(3):209-226. https://doi.org/10.1007/s10579-009-9081-4.
  5. Marco Baroni and Alessandro Lenci. 2010. Dis- tributional memory: A general framework for corpus-based semantics. Computational Linguistics 36(4):673-721.
  6. Marco Baroni and Roberto Zamparelli. 2010. Nouns are vectors, adjectives are matrices: Repre- senting adjective-noun constructions in seman- tic space. In Proceedings of the 2010 Con- ference on Empirical Methods in Natural Lan- guage Processing. Association for Computational Linguistics, Cambridge, MA, pages 1183-1193. http://www.aclweb.org/anthology/D10-1115.
  7. William Blacoe and Mirella Lapata. 2012. A com- parison of vector-based representations for seman- tic composition. In Proceedings of the 2012
  8. Joint Conference on Empirical Methods in Natu- ral Language Processing and Computational Natu- ral Language Learning. Association for Computa- tional Linguistics, Jeju Island, Korea, pages 546- 556. http://www.aclweb.org/anthology/D12-1050.
  9. Samuel R. Bowman, Jon Gauthier, Abhinav Ras- togi, Raghav Gupta, Christopher D. Manning, and Christopher Potts. 2016. A fast unified model for parsing and sentence understanding. In Pro- ceedings of the 54th Annual Meeting of the As- sociation for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Berlin, Germany, pages 1466-1477. http://www.aclweb.org/anthology/P16-1139.
  10. Bob Coecke, Mehrnoosh Sadrzadeh, and Stephen Clark. 2011. Mathematical foundations for a com- positional distributed model of meaning. Linguistic Analysis 36(1-4):345-384.
  11. Danilo Croce, Alessandro Moschitti, and Roberto Basili. 2011. Structured lexical similarity via convolution kernels on dependency trees. In Proceedings of the 2011 Conference on Em- pirical Methods in Natural Language Process- ing. Association for Computational Linguistics, Edinburgh, Scotland, UK., pages 1034-1046. http://www.aclweb.org/anthology/D11-1096.
  12. Ido Dagan, Shaul Marcus, and Shaul Markovitch. 1993. Contextual word similarity and estimation from sparse data. In Proceedings of the 31st An- nual Meeting on Association for Computational Lin- guistics. Association for Computational Linguistics, Stroudsburg, PA, USA, ACL '93, pages 164-171. https://doi.org/10.3115/981574.981596.
  13. Ido Dagan, Fernando Pereira, and Lillian Lee. 1994. Similarity-based estimation of word cooccurrence probabilities. In Proceedings of the 32nd Annual Meeting of the Association for Computational Lin- guistics. Association for Computational Linguistics, Las Cruces, New Mexico, USA, pages 272-278. https://doi.org/10.3115/981732.981770.
  14. Georgiana Dinu, Nghia The Pham, and Marco Baroni. 2013. General estimation and evaluation of compo- sitional distributional semantic models. In Proceed- ings of the Workshop on Continuous Vector Space Models and their Compositionality. Association for Computational Linguistics, Sofia, Bulgaria, pages 50-58. http://www.aclweb.org/anthology/W13- 3206.
  15. Katrin Erk and Sebastian Padó. 2008. A struc- tured vector space model for word meaning in context. In Proceedings of the 2008 Con- ference on Empirical Methods in Natural Lan- guage Processing. Association for Computational Linguistics, Honolulu, Hawaii, pages 897-906. http://www.aclweb.org/anthology/D08-1094.
  16. Katrin Erk and Sebastian Pado. 2010. Exemplar- based models for word meaning in context. In Proceedings of the ACL 2010 Conference Short Papers. Association for Computational Linguistics, Uppsala, Sweden, pages 92-97. http://www.aclweb.org/anthology/P10-2017.
  17. Pablo Gamallo and Martín Pereira-Fariña. 2017. Com- positional semantics using feature-based models from wordnet. In Proceedings of the 1st Work- shop on Sense, Concept and Entity Representa- tions and their Applications. Association for Com- putational Linguistics, Valencia, Spain, pages 1-11. http://www.aclweb.org/anthology/W17-1901.
  18. E. Grefenstette, G. Dinu, Y. Zhang, M. Sadrzadeh, and M. Baroni. 2013. Multi-step regression learning for compositional distributional seman- tics. In Proceedings of the 10th International Conference on Computational Semantics (IWCS 2013) -Long Papers. Association for Computa- tional Linguistics, Potsdam, Germany, pages 131- 142. http://www.aclweb.org/anthology/W13-0112.
  19. Edward Grefenstette and Mehrnoosh Sadrzadeh. 2011. Experimental support for a categorical compo- sitional distributional model of meaning. In Proceedings of the 2011 Conference on Em- pirical Methods in Natural Language Process- ing. Association for Computational Linguistics, Edinburgh, Scotland, UK., pages 1394-1404. http://www.aclweb.org/anthology/D11-1129.
  20. Edward Grefenstette, Mehrnoosh Sadrzadeh, Stephen Clark, Bob Coecke, and Stephen Pulman. 2011. Concrete sentence spaces for compositional distri- butional models of meaning. Proceedings of the 9th International Conference on Computational Seman- tics (IWCS 2011) pages 125-134.
  21. Emiliano Guevara. 2010. A regression model of adjective-noun compositionality in distribu- tional semantics. In Proceedings of the 2010
  22. Workshop on GEometrical Models of Natural Language Semantics. Association for Computa- tional Linguistics, Uppsala, Sweden, pages 33-37. http://www.aclweb.org/anthology/W10-2805.
  23. Emiliano Guevara. 2011. Computing semantic com- positionality in distributional semantics. In Pro- ceedings of the Ninth International Conference on Computational Semantics. Association for Compu- tational Linguistics, Stroudsburg, PA, USA, IWCS '11, pages 135-144.
  24. Kazuma Hashimoto, Pontus Stenetorp, Makoto Miwa, and Yoshimasa Tsuruoka. 2014. Jointly learning word representations and composition functions using predicate-argument structures. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Pro- cessing (EMNLP). Association for Computational Linguistics, Doha, Qatar, pages 1544-1555. http://www.aclweb.org/anthology/D14-1163.
  25. Karl Moritz Hermann and Phil Blunsom. 2013. The role of syntax in vector space models of composi- tional semantics. In Proceedings of the 51st Annual Meeting of the Association for Computational Lin- guistics (Volume 1: Long Papers). Association for Computational Linguistics, Sofia, Bulgaria, pages 894-904. http://www.aclweb.org/anthology/P13- 1088.
  26. Felix Hill, KyungHyun Cho, Anna Korho- nen, and Yoshua Bengio. 2016. Learning to understand phrases by embedding the dictionary. Transactions of the Associa- tion for Computational Linguistics 4:17-30. http://www.aclweb.org/anthology/Q/Q16/Q16- 1002.pdf.
  27. Dimitri Kartsaklis and Mehrnoosh Sadrzadeh. 2014. A study of entanglement in a categorical framework of natural language. In Proceedings of the 11th Work- shop on Quantum Physics and Logic (QPL).
  28. Douwe Kiela, Felix Hill, Anna Korhonen, and Stephen Clark. 2014. Improving multi-modal representa- tions using image dispersion: Why less is sometimes more. In Proceedings of the 52nd Annual Meet- ing of the Association for Computational Linguistics (Volume 2: Short Papers). Association for Computa- tional Linguistics, Baltimore, Maryland, pages 835- 841. http://www.aclweb.org/anthology/P14-2135.
  29. Thomas Kober, Julie Weeds, Jeremy Reffin, and David Weir. 2016. Improving sparse word rep- resentations with distributional inference for se- mantic composition. In Proceedings of the 2016 Conference on Empirical Methods in Natu- ral Language Processing. Association for Computa- tional Linguistics, Austin, Texas, pages 1691-1702. https://aclweb.org/anthology/D16-1175.
  30. Omer Levy and Yoav Goldberg. 2014a. Dependency- based word embeddings. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Association for Computational Lin- guistics, Baltimore, Maryland, pages 302-308. http://www.aclweb.org/anthology/P14-2050.
  31. Omer Levy and Yoav Goldberg. 2014b. Neural word embedding as implicit matrix factorization. In Z. Ghahramani, M. Welling, C. Cortes, N.D. Lawrence, and K.Q. Weinberger, editors, Advances in Neural Information Processing Systems 27, Cur- ran Associates, Inc., pages 2177-2185.
  32. Jeff Mitchell and Mirella Lapata. 2008. Vector-based models of semantic composition. In Proceed- ings of ACL-08: HLT. Association for Computa- tional Linguistics, Columbus, Ohio, pages 236-244. http://www.aclweb.org/anthology/P/P08/P08-1028.
  33. Jeff Mitchell and Mirella Lapata. 2010. Com- position in distributional models of seman- tics. Cognitive Science 34(8):1388-1429. https://doi.org/10.1111/j.1551-6709.2010.01106.x.
  34. Lili Mou, Hao Peng, Ge Li, Yan Xu, Lu Zhang, and Zhi Jin. 2015. Discriminative neural sentence mod- eling by tree-based convolution. In Proceedings of the 2015 Conference on Empirical Methods in Nat- ural Language Processing. Association for Compu- tational Linguistics, Lisbon, Portugal, pages 2315- 2325. http://aclweb.org/anthology/D15-1279.
  35. Joakim Nivre, Johan Hall, and Jens Nilsson. 2006. Maltparser: A data-driven parser-generator for de- pendency parsing. Technical report, Växjö Univer- sity.
  36. Sebastian Padó and Mirella Lapata. 2007. Dependency-based construction of semantic space models. Computational Linguistics 33(2):161-199. https://doi.org/10.1162/coli.2007.33.2.161.
  37. Denis Paperno, Nghia The Pham, and Marco Baroni. 2014. A practical and linguistically-motivated ap- proach to compositional distributional semantics. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Vol- ume 1: Long Papers). Association for Computa- tional Linguistics, Baltimore, Maryland, pages 90- 99. http://www.aclweb.org/anthology/P14-1009.
  38. Hinrich Schütze. 1992. Dimensions of mean- ing. In Proceedings of ACM/IEEE Con- ference on Supercomputing. IEEE Com- puter Society Press, pages 787-796.
  39. Hinrich Schütze. 1998. Automatic word sense discrim- ination. Computational Linguistics 24(1):97-123.
  40. Richard Socher, Brody Huval, Christopher D. Man- ning, and Andrew Y. Ng. 2012. Semantic compositionality through recursive matrix-vector spaces. In Proceedings of the 2012 Joint Con- ference on Empirical Methods in Natural Lan- guage Processing and Computational Natural Lan- guage Learning. Association for Computational Linguistics, Jeju Island, Korea, pages 1201-1211. http://www.aclweb.org/anthology/D12-1110.
  41. Richard Socher, Andrej Karpathy, Quoc Le, Christo- pher Manning, and Andrew Ng. 2014. Grounded compositional semantics for finding and describing images with sentences. Transactions of the Associa- tion for Computational Linguistics 2:207-218.
  42. James H Steiger. 1980. Tests for comparing ele- ments of a correlation matrix. Psychological Bul- letin 87(2):245.
  43. Stefan Thater, Hagen Fürstenau, and Manfred Pinkal. 2010. Contextualizing semantic representations us- ing syntactically enriched vector models. In Pro- ceedings of the 48th Annual Meeting of the Associa- tion for Computational Linguistics. Association for Computational Linguistics, Uppsala, Sweden, pages 948-957. http://www.aclweb.org/anthology/P10- 1097.
  44. Stefan Thater, Hagen Fürstenau, and Manfred Pinkal. 2011. Word meaning in context: A simple and ef- fective vector model. In Proceedings of 5th Interna- tional Joint Conference on Natural Language Pro- cessing. Asian Federation of Natural Language Pro- cessing, Chiang Mai, Thailand, pages 1134-1143. http://www.aclweb.org/anthology/I11-1127.
  45. Ran Tian, Naoaki Okazaki, and Kentaro Inui. 2016. Learning semantically and additively composi- tional distributional representations. In Proceed- ings of the 54th Annual Meeting of the As- sociation for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Berlin, Germany, pages 1277-1287. http://www.aclweb.org/anthology/P16-1121.
  46. Peter D. Turney. 2012. Domain and function: A dual-space model of semantic relations and compo- sitions. Journal of Artificial Intelligence Research 44(1):533-585.
  47. Tim Van de Cruys, Thierry Poibeau, and Anna Korho- nen. 2013. A tensor-based factorization model of se- mantic compositionality. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computa- tional Linguistics, Atlanta, Georgia, pages 1142- 1151. http://www.aclweb.org/anthology/N13-1134.
  48. Julie Weeds, Thomas Kober, Jeremy Reffin, and David Weir. 2017. When a red herring in not a red herring: Using compositional methods to detect non-compositional phrases. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Vol- ume 2, Short Papers. Association for Computa- tional Linguistics, Valencia, Spain, pages 529-534. http://www.aclweb.org/anthology/E17-2085.
  49. Julie Weeds, David Weir, and Jeremy Reffin. 2014. Distributional composition using higher-order de- pendency vectors. In Proceedings of the 2nd Work- shop on Continuous Vector Space Models and their Compositionality (CVSC). Association for Compu- tational Linguistics, Gothenburg, Sweden, pages 11-20. http://www.aclweb.org/anthology/W14- 1502.
  50. David Weir, Julie Weeds, Jeremy Reffin, and Thomas Kober. 2016. Aligning packed dependency trees: a theory of composition for distributional semantics. Computational Linguistics, special issue on Formal Distributional Semantics 42(4):727-761.
  51. John Wieting, Mohit Bansal, Kevin Gimpel, and Karen Livescu. 2015. From paraphrase database to compositional paraphrase model and back. Transactions of the Association for Computational Linguistics 3:345-358.
  52. Mo Yu and Mark Dredze. 2015. Learning composition models for phrase embeddings. Transactions of the Association for Computational Linguistics 3:227- 242. http://aclweb.org/anthology/Q/Q15/Q15- 1017.pdf.
  53. Fabio Massimo Zanzotto and Lorenzo Dell'Arciprete. 2012. Distributed tree kernels. In John Lang- ford and Joelle Pineau, editors, Proceedings of the 29th International Conference on Machine Learning (ICML-12). Omnipress, New York, NY, USA, ICML '12, pages 193-200.
  54. Fabio Massimo Zanzotto, Ioannis Korkontzelos, Francesca Fallucchi, and Suresh Manandhar. 2010. Estimating linear models for compositional distribu- tional semantics. In Proceedings of Coling. pages 1263-1271. http://www.aclweb.org/anthology/C10- 1142.

Related papers

Aligning Packed Dependency Trees: a theory of composition for distributional semantics
Julie Weeds

Computational Linguistics, 2016

We present a new framework for compositional distributional semantics in which the distributional contexts of lexemes are expressed in terms of anchored packed dependency trees. We show that these structures have the potential to capture the full sentential contexts of a lexeme and provide a uniform basis for the composition of distributional knowledge in a way that captures both mutual disambiguation and generalization.

View PDFchevron_right
Improving Sparse Word Representations with Distributional Inference for Semantic Composition
Julie Weeds

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

Distributional models are derived from cooccurrences in a corpus, where only a small proportion of all possible plausible cooccurrences will be observed. This results in a very sparse vector space, requiring a mechanism for inferring missing knowledge. Most methods face this challenge in ways that render the resulting word representations uninterpretable, with the consequence that semantic composition becomes hard to model. In this paper we explore an alternative which involves explicitly inferring unobserved co-occurrences using the distributional neighbourhood. We show that distributional inference improves sparse word representations on several word similarity benchmarks and demonstrate that our model is competitive with the state-of-the-art for adjectivenoun, noun-noun and verb-object compositions while being fully interpretable.

View PDFchevron_right
A SICK cure for the evaluation of compositional distributional semantic models
Roberto Zamparelli, Stefano Menini, Luisa Bentivogli

Shared and internationally recognized benchmarks are fundamental for the development of any computational system. We aim to help the research community working on compositional distributional semantic models (CDSMs) by providing SICK (Sentences Involving Compositional Knowldedge), a large size English benchmark tailored for them. SICK consists of about 10,000 English sentence pairs that include many examples of the lexical, syntactic and semantic phenomena that CDSMs are expected to account for, but do not require dealing with other aspects of existing sentential data sets (idiomatic multiword expressions, named entities, telegraphic language) that are not within the scope of CDSMs. By means of crowdsourcing techniques, each pair was annotated for two crucial semantic tasks: relatedness in meaning (with a 5-point rating scale as gold score) and entailment relation between the two elements (with three possible gold labels: entailment, contradiction, and neutral). The SICK data set was used in SemEval-2014 Task 1, and it freely available for research purposes.

View PDFchevron_right
BUAP: evaluating compositional distributional semantic models on full sentences through semantic relatedness and textual entailment
David Pinto

The results obtained by the BUAP team at Task 1 of SemEval 2014 are presented in this paper. The run submitted is a supervised version based on two classification models: 1) We used logistic regression for determining the semantic relatedness between a pair of sentences, and 2) We employed support vector machines for identifying textual entailment degree between the two sentences. The behaviour for the second subtask (textual entailment) obtained much better performance than the one evaluated at the first subtask (relatedness), ranking our approach in the 7th position of 18 teams that participated at the competition. This work is licensed under a Creative Commons Attribution 4.0 International Licence.

View PDFchevron_right
Compositional Distributional Semantics with Syntactic Dependencies and Selectional Preferences
pablo gamallo

2021

This article describes a compositional model based on syntactic dependencies which has been designed to build contextualized word vectors, by following linguistic principles related to the concept of selectional preferences. The compositional strategy proposed in the current work has been evaluated on a syntactically controlled and multilingual dataset, and compared with Transformer BERT-like models, such as Sentence BERT, the state-of-the-art in sentence similarity. For this purpose, we created two new test datasets for Portuguese and Spanish on the basis of that defined for the English language, containing expressions with noun-verb-noun transitive constructions. The results we have obtained show that the linguistic-based compositional approach turns out to be competitive with Transformer models.

View PDFchevron_right

Related topics

  • Computer Science
    • 580 California St., Suite 400
    San Francisco, CA, 94104
    © 2025 Academia. All rights reserved