DE eng

Search in the Catalogues and Directories

Hits 1 – 20 of 20

1
Learning the Ordering of Coordinate Compounds and Elaborate Expressions in Hmong, Lahu, and Chinese ...
BASE
Show details
2
AUTOLEX: An Automatic Framework for Linguistic Exploration ...
BASE
Show details
3
Evaluating the Morphosyntactic Well-formedness of Generated Texts ...
BASE
Show details
4
Tusom2021: A Phonetically Transcribed Speech Dataset from an Endangered Language for Universal Phone Recognition Experiments ...
BASE
Show details
5
Evaluating the Morphosyntactic Well-formedness of Generated Texts ...
BASE
Show details
6
Differentiable Allophone Graphs for Language-Universal Speech Recognition ...
BASE
Show details
7
AlloVera: A Multilingual Allophone Database ...
BASE
Show details
8
Towards Zero-shot Learning for Automatic Phonemic Transcription ...
BASE
Show details
9
Automatic Extraction of Rules Governing Morphological Agreement ...
BASE
Show details
10
Where New Words Are Born: Distributional Semantic Analysis of Neologisms and Their Semantic Neighborhoods ...
BASE
Show details
11
Universal Phone Recognition with a Multilingual Allophone System ...
BASE
Show details
12
Cross-Cultural Similarity Features for Cross-Lingual Transfer Learning of Pragmatically Motivated Tasks ...
BASE
Show details
13
Characterizing Sociolinguistic Variation in the Competing Vaccination Communities ...
BASE
Show details
14
Where New Words Are Born: Distributional Semantic Analysis of Neologisms and Their Semantic Neighborhoods
In: Proceedings of the Society for Computation in Linguistics (2020)
BASE
Show details
15
Using Interlinear Glosses as Pivot in Low-Resource Multilingual Machine Translation ...
BASE
Show details
16
Adapting Word Embeddings to New Languages with Morphological and Phonological Subword Representations ...
Abstract: Much work in Natural Language Processing (NLP) has been for resource-rich languages, making generalization to new, less-resourced languages challenging. We present two approaches for improving generalization to low-resourced languages by adapting continuous word representations using linguistically motivated subword units: phonemes, morphemes and graphemes. Our method requires neither parallel corpora nor bilingual dictionaries and provides a significant gain in performance over previous methods relying on these resources. We demonstrate the effectiveness of our approaches on Named Entity Recognition for four languages, namely Uyghur, Turkish, Bengali and Hindi, of which Uyghur and Bengali are low resource languages, and also perform experiments on Machine Translation. Exploiting subwords with transfer learning gives us a boost of +15.2 NER F1 for Uyghur and +9.7 F1 for Bengali. We also show improvements in the monolingual setting where we achieve (avg.) +3 F1 and (avg.) +1.35 BLEU. ... : Accepted at EMNLP 2018 ...
Keyword: Computation and Language cs.CL; FOS Computer and information sciences
URL: https://arxiv.org/abs/1808.09500
https://dx.doi.org/10.48550/arxiv.1808.09500
BASE
Hide details
17
Lexical Prefixes and Tibeto-Burman Laryngeal Contrasts
In: Mortensen, David R. (2013). Lexical Prefixes and Tibeto-Burman Laryngeal Contrasts. Proceedings of the 37th Annual Meeting of the Berkeley Linguistics Society, 37(37), 272 - 286. Retrieved from: http://www.escholarship.org/uc/item/1229x8bj (2013)
BASE
Show details
18
The emergence of obstruents after high vowels
In: Diachronica. - Amsterdam [u.a.] : Benjamins 29 (2012) 4, 434-470
BLLDB
OLC Linguistik
Show details
19
A classification of compounds in American Sign Language: an evaluation of the Bisetto and Scalise framework
In: Morphology. - Heidelberg [u.a.] : Springer 22 (2012) 4, 545-579
BLLDB
OLC Linguistik
Show details
20
Lexical prefixes and Tibeto-Burman laryngeal contrasts
In: Annual Meeting of the Berkeley Linguistics Society; BLS 37: General Session and Parasession on Language, Gender, and Sexuality; 272-286 ; 2377-1666 ; 0363-2946 (2011)
BASE
Show details

Catalogues
0
0
2
0
0
0
0
Bibliographies
2
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
18
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern