• Refine your search:
  • 
    Keyword
  • 
    Creator / Publisher:
    
    • Stevenson, Mark (30)
    • Stevenson, Mark [Herausgeber] (15)
    • Biber, Hanno [Herausgeber] (12)
    • Clematide, Simon [Herausgeber] (12)
    • Mariani, John [Herausgeber] (12)
    • Sick, Theresa [Herausgeber] (12)
    • Bański, Piotr [Herausgeber] (11)
    • Breiteneder, Evelyn [Herausgeber] (11)
    • Lüngen, Harald [Herausgeber] (11)
    • Rayson, Paul [Herausgeber] (11)
    •   more
  • 
    Year
  • 
    Medium
  • 
    Type
  • 
    BLLDB-Access:
    • free (47)
    • subject to license (1)

Search in the Catalogues and Directories

All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year Sort by creator [A → Z]' creator [Z → A]' publishing year ↑ (asc)' publishing year ↓ (desc)' title [A → Z]' title [Z → A]' Simple Search Page: 1 2 3 Hits 1 – 20 of 47 1 Cross-Lingual Word Embedding Refinement by $\ell_{1}$ Norm Optimisation ... Peng, Xutan; Lin, Chenghua; Stevenson, Mark. - : arXiv, 2021 Abstract: Cross-Lingual Word Embeddings (CLWEs) encode words from two or more languages in a shared high-dimensional space in which vectors representing words with similar meaning (regardless of language) are closely located. Existing methods for building high-quality CLWEs learn mappings that minimise the $\ell_{2}$ norm loss function. However, this optimisation objective has been demonstrated to be sensitive to outliers. Based on the more robust Manhattan norm (aka. $\ell_{1}$ norm) goodness-of-fit criterion, this paper proposes a simple post-processing step to improve CLWEs. An advantage of this approach is that it is fully agnostic to the training process of the original CLWEs and can therefore be applied widely. Extensive experiments are performed involving ten diverse languages and embeddings trained on different corpora. Evaluation results based on bilingual lexicon induction and cross-lingual transfer for natural language inference tasks show that the $\ell_{1}$ refinement substantially outperforms four ... : To appear at NAACL 2021 ... Keyword: Computation and Language cs.CL; FOS Computer and information sciences; Machine Learning cs.LG; Machine Learning stat.ML URL: https://dx.doi.org/10.48550/arxiv.2104.04916 https://arxiv.org/abs/2104.04916 BASE Hide details 2 Cross-Lingual Word Embedding Refinement by $\ell_{1}$ Norm Optimisation ... NAACL 2021 2021; Lin, Chenghua; Peng , Xutan. - : Underline Science Inc., 2021 BASE Show details 3 SciBabel : a system for crowd-sourced validation of automatic translations of scientific texts Soares, Felipe; Rebechi, Rozane Rodrigues; Stevenson, Mark. - 2020 BASE Show details 4 A word sense disambiguation corpus for Urdu Saeed, Ali; Nawab, Rao Muhammad Adeel; Stevenson, Mark. - 2019 BASE Show details 5 A Sense Annotated Corpus for All-Words Urdu Word Sense Disambiguation Saeed, Ali; Nawab, Rao Muhammad Adeel; Stevenson, Mark. - 2019 BASE Show details 6 A word sense disambiguation corpus for Urdu [<Journal>] Saeed, Ali [Verfasser]; Nawab, Rao Muhammad Adeel [Verfasser]; Stevenson, Mark [Verfasser]. DNB Subject Category Language Show details 7 Accelerating corpus search using multiple cores Rábara, Radoslav [Verfasser]; Rychlý, Pavel [Verfasser]; Herman, Ondřej [Verfasser]. - Mannheim : Institut für Deutsche Sprache, Bibliothek, 2017 DNB Subject Category Language Show details 8 Are web corpora inferior? The Case of Czech and Slovak Benko, Vladimír [Verfasser]; Bański, Piotr [Herausgeber]; Kupietz, Marc [Herausgeber]. - Mannheim : Institut für Deutsche Sprache, Bibliothek, 2017 DNB Subject Category Language Show details 9 Creating CorCenCC (Corpws Cenedlaethol Cymraeg Cyfoes - The National Corpus of Contemporary Welsh) Knight, Dawn Verfasser]. - Mannheim : Institut für Deutsche Sprache, Bibliothek, 2017 DNB Subject Category Language Show details 10 EuReCo - Joining Forces for a European Reference Corpus as a sustainable base for cross-linguistic research Kupietz, Marc [Verfasser] [Herausgeber]; Witt, Andreas [Verfasser]; Bański, Piotr [Verfasser] [Herausgeber]. - Mannheim : Institut für Deutsche Sprache, Bibliothek, 2017 DNB Subject Category Language Show details 11 CMC Corpora in DeReKo Lüngen, Harald [Verfasser] [Herausgeber]; Kupietz, Marc [Verfasser] [Herausgeber]; Bański, Piotr [Herausgeber]. - Mannheim : Institut für Deutsche Sprache, Bibliothek, 2017 DNB Subject Category Language Show details 12 From ICE to ICC: The new International Comparable Corpus Kirk, John [Verfasser]; Čermáková, Anna [Verfasser]; Bański, Piotr [Herausgeber]. - Mannheim : Institut für Deutsche Sprache, Bibliothek, 2017 DNB Subject Category Language Show details 13 Intra-connecting an exemplary literary corpus with semantic web technologies for exploratory literary studies Dittrich, Andreas [Verfasser]; Bański, Piotr [Herausgeber]; Kupietz, Marc [Herausgeber]. - Mannheim : Institut für Deutsche Sprache, Bibliothek, 2017 DNB Subject Category Language Show details 14 Keeping Properties with the Data CL-MetaHeaders - An Open Specification Vidler, John [Verfasser]; Wattam, Stephen [Verfasser]; Bański, Piotr [Herausgeber]. - Mannheim : Institut für Deutsche Sprache, Bibliothek, 2017 DNB Subject Category Language Show details 15 Removing spam from web corpora through supervised learning using FastText Suchomel, Vít [Verfasser]; Bański, Piotr [Herausgeber]; Kupietz, Marc [Herausgeber]. - Mannheim : Institut für Deutsche Sprache, Bibliothek, 2017 DNB Subject Category Language Show details 16 Organizing corpora at the Stanford Literary Lab. Balancing simplicity and flexibility in metadata management McClure, David [Verfasser]; Algee-Hewitt, Mark [Verfasser]; Douris, Steele [Verfasser]. - Mannheim : Institut für Deutsche Sprache, Bibliothek, 2017 DNB Subject Category Language Show details 17 Proceedings of the Workshop on Challenges in the Management of Large Corpora and Big Data and Natural Language Processing (CMLC-5+BigNLP) 2017 including the papers from the Web-as-Corpus (WAC-XI) guest section. Birmingham, 24 July 2017 Bański, Piotr [Herausgeber]; Kupietz, Marc [Herausgeber]; Lüngen, Harald [Herausgeber]. - Mannheim : Institut für Deutsche Sprache, Bibliothek, 2017 DNB Subject Category Language Show details 18 Web corpora - the best possible solution for tracking rare phenomena in underresourced languages: clitics in Bosnian, Croatian and Serbian Lüngen, Harald [Herausgeber]; Hansen, Björn [Verfasser]; Breiteneder, Evelyn [Herausgeber]. - Mannheim : Institut für Deutsche Sprache, Bibliothek, 2017 DNB Subject Category Language Show details 19 Improving distant supervision using inference learning ... Roller, Roland; Agirre, Eneko; Soroa, Aitor. - : arXiv, 2015 BASE Show details 20 Exploring relation types for literature-based discovery Preiss, Judita; Stevenson, Mark; Gaizauskas, Robert. - : Oxford University Press, 2015 BASE Show details Page: 1 2 3

Mobile view All Catalogues UB Frankfurt Linguistik 4 IDS Mannheim 1 OLC Linguistik 3 UB Frankfurt Retrokatalog 0 DNB Subject Category Language 16 Institut für Empirische Sprachwissenschaft 0 Leibniz-Centre General Linguistics (ZAS) 1 Bibliographies BLLDB 10 BDSL 0 IDS Bibliografie zur deutschen Grammatik 0 IDS Bibliografie zur Gesprächsforschung 0 IDS Konnektoren im Deutschen 0 IDS Präpositionen im Deutschen 0 IDS OBELEX meta 0 MPI-SHH Linguistics Collection 0 MPI for Psycholinguistics 3 Linked Open Data catalogues Annohub 0 Online resources Link directory 0 Journal directory 0 Database directory 0 Dictionary directory 0 Open access documents BASE 15 Linguistik-Repository 0 IDS Publikationsserver 0 Online dissertations 0 Language Description Heritage 0