Zobrazeno 1 - 10
of 12
pro vyhledávání: '"Tejaswini Deoskar"'
Publikováno v:
Natural Language Engineering. :1-31
Latent semantic analysis (LSA) and correspondence analysis (CA) are two techniques that use a singular value decomposition for dimensionality reduction. LSA has been extensively used to obtain low-dimensional representations that capture relationship
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::15c3fea3dcee988721aebe27863c54f2
https://doi.org/10.1017/s1351324923000244
https://doi.org/10.1017/s1351324923000244
Publikováno v:
COLING
Standard image caption generation systems produce generic descriptions of images and do not utilize any contextual information or world knowledge. In particular, they are unable to generate captions that contain references to the geographic context o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::22d369cecd670882fff7ae1ed2f748ec
https://dspace.library.uu.nl/handle/1874/415593
https://dspace.library.uu.nl/handle/1874/415593
Publikováno v:
Ambati, B R, Deoskar, T & Steedman, M 2017, ' Hindi CCGbank: CCG Treebank from the Hindi Dependency Treebank ', Language Resources and Evaluation, pp. 1-34 . https://doi.org/10.1007/s10579-017-9379-6
Language Resources and Evaluation
Language Resources and Evaluation
In this paper, we present an approach for automatically creating a CombinatoryCategorial Grammar (CCG) treebank from a dependency treebank for the Subject-Object-Verb language Hindi. Rather than a direct conversion from dependency trees to CCG trees,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::87df5de034a303d3285c3791db311da1
https://doi.org/10.1007/s10579-017-9379-6
https://doi.org/10.1007/s10579-017-9379-6
Publikováno v:
RepL4NLP@ACL
We propose a novel application of self-attention networks towards grammar induction. We present an attention-based supertagger for a refined type-logical grammar, trained on constructing types inductively. In addition to achieving a high overall type
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c87847ac51ccb3ab6783e07af58d8d65
Publikováno v:
Requirements Engineering: Foundation for Software Quality ISBN: 9783030155377
REFSQ
REFSQ
[Context and motivation] In agile system development methods, product backlog items (or tasks) play a prominent role in the refinement process of software requirements. Tasks are typically defined manually to operationalize how to implement a user st
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fa082df8a1f2a261bb908cf7b8beccf9
https://doi.org/10.1007/978-3-030-15538-4_7
https://doi.org/10.1007/978-3-030-15538-4_7
Publikováno v:
Journal of Logic and Computation, 24(2), 433-453. Oxford University Press
This article uses semi-supervised Expectation Maximization (EM) to learn lexico-syntactic dependencies, i.e. associations between words and the structures that occur with them. Due to Zipfian distributions in language, such dependencies are extremely
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8bddbd26b1efef648753df6dc962c8ec
https://doi.org/10.1093/logcom/exs062
https://doi.org/10.1093/logcom/exs062
Publikováno v:
HLT-NAACL
Ambati, B R, Deoskar, T, Johnson, M & Steedman, M 2015, An Incremental Algorithm for Transition-based CCG Parsing . in Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies . Denver, Colorado, pp. 53-63 . < http://www.aclweb.org/anthology/N15-1006 >
Ambati, B R, Deoskar, T, Johnson, M & Steedman, M 2015, An Incremental Algorithm for Transition-based CCG Parsing . in Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies . Denver, Colorado, pp. 53-63 . < http://www.aclweb.org/anthology/N15-1006 >
Incremental parsers have potential advantages for applications like language modeling for machine translation and speech recognition. We describe a new algorithm for incremental transition-based Combinatory Categorial Grammar parsing. As English CCGb
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3a72ecdbce577cbf7aac1027229ba8f4
https://doi.org/10.3115/v1/n15-1006
https://doi.org/10.3115/v1/n15-1006
Publikováno v:
EACL
Deoskar, T, Christodoulopoulos, C, Birch, A & Steedman, M 2014, Generalizing a Strongly Lexicalized Parser using Unlabeled Data . in Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics . Gothenburg, Sweden, pp. 126-134 . < http://www.aclweb.org/anthology/E14-1014 >
Scopus-Elsevier
Deoskar, T, Christodoulopoulos, C, Birch, A & Steedman, M 2014, Generalizing a Strongly Lexicalized Parser using Unlabeled Data . in Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics . Gothenburg, Sweden, pp. 126-134 . < http://www.aclweb.org/anthology/E14-1014 >
Scopus-Elsevier
Statistical parsers trained on labeled data suffer from sparsity, both grammatical and lexical. For parsers based on strongly lexicalized grammar formalisms (such as CCG, which has complex lexical categories but simple combinatory rules), the problem
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d443f43cc7d48d35a6a0761ef13e6f5b
https://doi.org/10.3115/v1/e14-1014
https://doi.org/10.3115/v1/e14-1014
Publikováno v:
EACL
Ambati, B R, Deoskar, T & Steedman, M 2014, Improving Dependency Parsers using Combinatory Categorial Grammar . in Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, volume 2: Short Papers . Gothenburg, Sweden, pp. 159-163 . < http://www.aclweb.org/anthology/E14-4031 >
Ambati, B R, Deoskar, T & Steedman, M 2014, Improving Dependency Parsers using Combinatory Categorial Grammar . in Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, volume 2: Short Papers . Gothenburg, Sweden, pp. 159-163 . < http://www.aclweb.org/anthology/E14-4031 >
Subcategorization information is a useful feature in dependency parsing. In this paper, we explore a method of incorporating this information via Combinatory Categorial Grammar (CCG) categories from a supertagger. We experiment with two popular depen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a90007aad4f4ee93b0cf4a88c9ffd412
https://doi.org/10.3115/v1/e14-4031
https://doi.org/10.3115/v1/e14-4031