Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Tamara Polajnar"'
Publikováno v:
CoNLL
We present a new summarisation task, taking scientific articles and producing journal table-of-contents entries in the chemistry domain. These are one- or two-sentence author-written summaries that present the key findings of a paper. This is a first
Publikováno v:
Computational Linguistics. 42:661-701
This article introduces RELPRON, a large data set of subject and object relative clauses, for the evaluation of methods in compositional distributional semantics. RELPRON targets an intermediate level of grammatical complexity between content-word pa
Publikováno v:
Statistics and Computing. 20:317-334
Datasets that are subjectively labeled by a number of experts are becoming more common in tasks such as biological text annotation where class definitions are necessarily somewhat subjective. Standard classification and regression models are not suit
Publikováno v:
LSDSem@EMNLP
This paper investigates whether the wider context in which a sentence is located can contribute to a distributional representation of sentence meaning. We compare a vector space for sentences in which the features are words occurring within the sente
Publikováno v:
ACL (2)
Several compositional distributional semantic methods use tensors to model multi-way interactions between vectors. Unfortunately, the size of the tensors can make their use impractical in large-scale implementations. In this paper, we investigate whe
Autor:
Tamara Polajnar, Leif Azzopardi, Karl Gyllstrom, Frans van der Sluis, Sergio Duarte, Djoerd Hiemstra, Doug Dowie, Frea Kruisinga, Carsten Eickhoff, Richard Glassey, Kelly Ann Marshall, Franciska de Jong, Arjen P. de Vries, Sien Moens
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783642289965
ECIR
34th European Conference on Advances in Information Retrieval (ECIR 2012), 578-580
STARTPAGE=578;ENDPAGE=580;TITLE=34th European Conference on Advances in Information Retrieval (ECIR 2012)
Advances in Information Retrieval-34th European Conference on IR Research, ECIR 2012, Proceedings, 578-580
STARTPAGE=578;ENDPAGE=580;TITLE=Advances in Information Retrieval-34th European Conference on IR Research, ECIR 2012, Proceedings
ECIR
34th European Conference on Advances in Information Retrieval (ECIR 2012), 578-580
STARTPAGE=578;ENDPAGE=580;TITLE=34th European Conference on Advances in Information Retrieval (ECIR 2012)
Advances in Information Retrieval-34th European Conference on IR Research, ECIR 2012, Proceedings, 578-580
STARTPAGE=578;ENDPAGE=580;TITLE=Advances in Information Retrieval-34th European Conference on IR Research, ECIR 2012, Proceedings
The Emma Search (EmSe) demonstrator developed for the Emma Children's Hospital showcases the PuppyIR project and PuppyIR framework for building information services for children.
Publikováno v:
Evaluation of Simple Distributional Compositional Operations on Longer Texts.
Autor:
Tamara Polajnar, Stephen Clark
Publikováno v:
Improving Distributional Semantic Vectors through Context Selection and Normalisation.
Publikováno v:
UCAM-CORE: Incorporating structured distributional similarity into STS.
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783642369728
ECIR
ECIR
Explicit semantic analysis (ESA) is a technique for computing semantic relatedness between natural language texts. It is a document-based distributional model similar to latent semantic analysis (LSA), which is often built on the Wikipedia database w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ce3d09b0014556699a7aa8ab75e422e5
https://doi.org/10.1007/978-3-642-36973-5_49
https://doi.org/10.1007/978-3-642-36973-5_49