1 |
Text+: Language- and text-based Research Data Infrastructure ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Text+: Language- and text-based Research Data Infrastructure ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Text+: Language- and text-based Research Data Infrastructure ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Komponenten-basierte Metadatenschemata und Facetten-basierte Suche ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Komponenten-basierte Metadatenschemata und Facetten-basierte Suche ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
All that glitters is not gold : a gold standard of adjective-noun collocations for German
|
|
|
|
BASE
|
|
Show details
|
|
7 |
No Word is an Island -- A Transformation Weighting Model for Semantic Composition ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Composition Models for the Representation and Semantic Interpretation of Nominal Compounds
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Semantic modelling of adjective-noun collocations using FrameNet
|
|
|
|
BASE
|
|
Show details
|
|
10 |
No Word is an Island—A Transformation Weighting Model for Semantic Composition
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 7, Pp 437-451 (2019) (2019)
|
|
Abstract:
Composition models of distributional semantics are used to construct phrase representations from the representations of their words. Composition models are typically situated on two ends of a spectrum. They either have a small number of parameters but compose all phrases in the same way, or they perform word-specific compositions at the cost of a far larger number of parameters. In this paper we propose transformation weighting (TransWeight), a composition model that consistently outperforms existing models on nominal compounds, adjective-noun phrases, and adverb-adjective phrases in English, German, and Dutch. TransWeight drastically reduces the number of parameters needed compared with the best model in the literature by composing similar words in the same way.
|
|
Keyword:
Computational linguistics. Natural language processing; P98-98.5
|
|
URL: https://doaj.org/article/08acce0ec06c4b0e849eda29accf60e5 https://doi.org/10.1162/tacl_a_00275
|
|
BASE
|
|
Hide details
|
|
11 |
Digitale Forschungsinfrastrukturen für die Sprachwissenschaften
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Connecting Resources: Which Issues Have to be Solved to Integrate CMC Corpora from Heterogeneous Sources and for Different Languages?
|
|
|
|
In: 5th Conference on CMC and Social Media Corpora for the Humanities (cmccorpora17) ; https://hal.archives-ouvertes.fr/hal-01918880 ; 5th Conference on CMC and Social Media Corpora for the Humanities (cmccorpora17), Oct 2017, Bolzano, Italy. pp.52-55 ; https://doi.org/10.5281/zenodo.1040713 (2017)
|
|
BASE
|
|
Show details
|
|
14 |
Connecting Resources: Which Issues Have To Be Solved To Integrate Cmc Corpora From Heterogeneous Sources And For Different Languages? ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Connecting Resources: Which Issues Have To Be Solved To Integrate Cmc Corpora From Heterogeneous Sources And For Different Languages? ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Integrating optical character recognition and machine translation of historical documents
|
|
|
|
In: Afli, Haithem orcid:0000-0002-7449-4707 and Way, Andy orcid:0000-0001-5736-5930 (2016) Integrating optical character recognition and machine translation of historical documents. In: COLING, the 26th International Conference on Computational Linguistics, 13-16 Dec 2016, Osaka, Japan. (2016)
|
|
BASE
|
|
Show details
|
|
17 |
Language Technology Resources and Tools for Digital Humanities (LT4DH) : proceedings of the workshop : December 11-16, 2016, Osaka, Japan : LT4DH 2016
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Introduction to the Special Issue [Computational, cognitive, and linguistic approaches to the analysis of compounds and collocations]
|
|
|
|
BASE
|
|
Show details
|
|
|
|