Detailansicht
Detailansicht Treffer
https://www.dipf.de/en/research/publications/publications-data-base/detail
https://www.dipf.de/@@site-logo/header_dipf_logo_2lines_de_2018.png
DIPF database of publications
Show results
Author
Schnober, Carsten;
Eger, Steffen;
Do Dinh, Erik-Lân;
Gurevych, Iryna:
Title:
Still not there? Comparing traditional sequence-to-sequence models to encoder-decoder neural networks on monotone string translation tasks
Source:
In: The COLING 2016 Organizing Committee (Hrsg.): Proceedings of the 26th International Conference on Computational Linguistics (COLING)
Osaka :
The COLING 2016 Organizing Committee
(2016)
, 1703-1714
URL of full text:
http://aclweb.org/anthology/C16-1160
Language:
Englisch
Document type
4. Beiträge in Sammelwerken; Tagungsband/Konferenzbeitrag/Proceedings
Schlagwörter:
Computerlinguistik,
Computerunterstütztes Verfahren,
Korrektur,
Rechtschreibung,
Text
Abstract(englisch):
We analyze the performance of encoder-decoder neural models and compare them with well-known established methods. The latter represent different classes of traditional approaches that are applied to the monotone sequence-to-sequence tasks OCR post-correction, spelling correction, grapheme-to-phoneme conversion, and lemmatization. Such tasks are of practical relevance for various higher-level research fields including digital humanities, automatic text correction, and speech recognition. We investigate how well generic deep-learning approaches adapt to these tasks, and how they perform in comparison with established and more specialized methods, including our own adaptation of pruned CRFs. (DIPF/Orig.)
DIPF-Departments:
Information Center for Education
Notes: