81 |
A shared substrate between Greek and Italic
|
|
|
|
In: ISSN: 0019-7262 ; EISSN: 1613-0405 ; Indogermanische Forschungen ; https://hal.inria.fr/hal-01621467 ; Indogermanische Forschungen, De Gruyter, 2017, 122 (1), pp.29-60. ⟨10.1515/if-2017-0002⟩ (2017)
|
|
BASE
|
|
Show details
|
|
82 |
Improving neural tagging with lexical information
|
|
|
|
In: 15th International Conference on Parsing Technologies ; https://hal.inria.fr/hal-01592055 ; 15th International Conference on Parsing Technologies, Sep 2017, Pisa, Italy. pp.25-31 ; http://compling.ucdavis.edu/iwpt2017/ (2017)
|
|
BASE
|
|
Show details
|
|
83 |
Universal Dependencies 2.1
|
|
|
|
In: https://hal.inria.fr/hal-01682188 ; 2017 (2017)
|
|
BASE
|
|
Show details
|
|
84 |
Paris and Stanford at EPE 2017: Downstream Evaluation of Graph-based Dependency Representations
|
|
|
|
In: EPE 2017 - The First Shared Task on Extrinsic Parser Evaluation ; https://hal.inria.fr/hal-01592051 ; EPE 2017 - The First Shared Task on Extrinsic Parser Evaluation, Sep 2017, Pisa, Italy. pp.47-59 ; http://epe.nlpl.eu (2017)
|
|
BASE
|
|
Show details
|
|
85 |
Computational methods for descriptive and theoretical morphology: a brief introduction
|
|
|
|
In: ISSN: 1871-5621 ; EISSN: 1871-5656 ; Morphology ; https://hal.inria.fr/hal-01628253 ; Morphology, Springer Verlag, 2017, Computational methods for descriptive and theoretical morphology, 27 (4), pp.1-7. ⟨10.1017/CBO9781139248860⟩ (2017)
|
|
BASE
|
|
Show details
|
|
86 |
Annotating omission in statement pairs
|
|
|
|
In: 11th Linguistic Annotation Workshop ; https://hal.inria.fr/hal-01584035 ; 11th Linguistic Annotation Workshop, Apr 2017, Valencia, Spain. pp.41-45 (2017)
|
|
BASE
|
|
Show details
|
|
87 |
Speeding up corpus development for linguistic research: language documentation and acquisition in Romansh Tuatschin
|
|
|
|
In: Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature ; https://hal.inria.fr/hal-01570614 ; Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, Aug 2017, Vancouver, Canada. pp.89 - 94, ⟨10.18653/v1/W17-2212⟩ ; https://sighum.wordpress.com/events/latech-clfl-2017/ (2017)
|
|
BASE
|
|
Show details
|
|
88 |
Milk and the Indo-Europeans
|
|
|
|
In: Language Dispersal Beyond Farming ; https://hal.inria.fr/hal-01667476 ; Martine Robeets; Alexander Savalyev Language Dispersal Beyond Farming, John Benjamins Publishing Company, pp.291-311, 2017, 978 90 272 1255 9. ⟨10.1075/z.215.13gar⟩ (2017)
|
|
BASE
|
|
Show details
|
|
91 |
Milk and the Indo-Europeans
|
|
|
|
In: Language Dispersal Beyond Farming ; https://hal.inria.fr/hal-01667476 ; Martine Robeets; Alexander Savalyev Language Dispersal Beyond Farming, John Benjamins Publishing Company, pp.291-311, 2017, 978 90 272 1255 9. ⟨10.1075/z.215.13gar⟩ (2017)
|
|
BASE
|
|
Show details
|
|
92 |
From Noisy Questions to Minecraft Texts: Annotation Challenges in Extreme Syntax Scenarios
|
|
|
|
In: 2nd Workshop on Noisy User-generated Text (W-NUT) at CoLing 2016 ; https://hal.inria.fr/hal-01584054 ; 2nd Workshop on Noisy User-generated Text (W-NUT) at CoLing 2016, Dec 2016, Osaka, Japan (2016)
|
|
BASE
|
|
Show details
|
|
93 |
External Lexical Information for Multilingual Part-of-Speech Tagging ...
|
|
|
|
Abstract:
Morphosyntactic lexicons and word vector representations have both proven useful for improving the accuracy of statistical part-of-speech taggers. Here we compare the performances of four systems on datasets covering 16 languages, two of these systems being feature-based (MEMMs and CRFs) and two of them being neural-based (bi-LSTMs). We show that, on average, all four approaches perform similarly and reach state-of-the-art results. Yet better performances are obtained with our feature-based models on lexically richer datasets (e.g. for morphologically rich languages), whereas neural-based results are higher on datasets with less lexical variability (e.g. for English). These conclusions hold in particular for the MEMM models relying on our system MElt, which benefited from newly designed features. This shows that, under certain conditions, feature-based approaches enriched with morphosyntactic lexicons are competitive with respect to neural methods. ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.1606.03676 https://arxiv.org/abs/1606.03676
|
|
BASE
|
|
Hide details
|
|
94 |
Constructing a poor man’s wordnet in a resource-rich world
|
|
|
|
In: ISSN: 1574-020X ; EISSN: 1574-0218 ; Language Resources and Evaluation ; https://hal.inria.fr/hal-01174492 ; Language Resources and Evaluation, Springer Verlag, 2015, 49 (3), pp.601-635. ⟨10.1007/s10579-015-9295-6⟩ (2015)
|
|
BASE
|
|
Show details
|
|
95 |
Could Greek and Italic share a same Indo-European substratum?
|
|
|
|
In: 22nd International Conference on Historical Linguistics ; https://hal.inria.fr/hal-01256310 ; 22nd International Conference on Historical Linguistics, Jul 2015, Naples, Italy ; http://www.ichl22.unina.it (2015)
|
|
BASE
|
|
Show details
|
|
96 |
Developing a French FrameNet: Methodology and First results
|
|
|
|
In: LREC - The 9th edition of the Language Resources and Evaluation Conference ; https://hal.inria.fr/hal-01022385 ; LREC - The 9th edition of the Language Resources and Evaluation Conference, May 2014, Reykjavik, Iceland (2014)
|
|
BASE
|
|
Show details
|
|
97 |
A language-independent and fully unsupervised approach to lexicon induction and part-of-speech tagging for closely related languages
|
|
|
|
In: Language Resources and Evaluation Conference ; https://hal.inria.fr/hal-01022298 ; Language Resources and Evaluation Conference, European Language Resources Association, May 2014, Reykjavik, Iceland (2014)
|
|
BASE
|
|
Show details
|
|
98 |
Data-driven Synset Induction and Disambiguation for Wordnet Development
|
|
|
|
In: ISSN: 1574-020X ; EISSN: 1574-0218 ; Language Resources and Evaluation ; https://hal.inria.fr/hal-01088000 ; Language Resources and Evaluation, Springer Verlag, 2014, 48 (4), pp.655-677. ⟨10.1007/s10579-014-9291-2⟩ (2014)
|
|
BASE
|
|
Show details
|
|
99 |
Crowdsourcing for Language Resource Development: Criticisms About Amazon Mechanical Turk Overpowering Use
|
|
|
|
In: Human Language Technology Challenges for Computer Science and Linguistics ; https://hal.inria.fr/hal-01053047 ; Vetulani, Zygmunt and Mariani, Joseph. Human Language Technology Challenges for Computer Science and Linguistics, 8387, Springer International Publishing, pp.303-314, 2014, Lecture Notes in Computer Science, 978-3-319-08957-7. ⟨10.1007/978-3-319-08958-4_25⟩ (2014)
|
|
BASE
|
|
Show details
|
|
100 |
The CoMeRe corpus for French: structuring and annotating heterogeneous CMC genres
|
|
|
|
In: ISSN: 0175-1336 ; Journal for language technology and computational linguistics ; https://halshs.archives-ouvertes.fr/halshs-00953507 ; Journal for language technology and computational linguistics, GSCL (Gesellschaft für Sprachtechnologie und Computerlinguistik) 2014, 29 (2), pp.1-30 ; http://www.jlcl.org/2014_Heft2/Heft2-2014.pdf (2014)
|
|
BASE
|
|
Show details
|
|
|
|