Schnober, Carsten ; Eger, Steffen ; Do Dinh, Erik-Lân ; Gurevych, Iryna (2016)
Still not there? Comparing Traditional Sequence-to-Sequence Models to Encoder-Decoder Neural Networks on Monotone String Translation Tasks.
Osaka, Japan
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
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 \textit{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.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2016 |
| Autor(en): | Schnober, Carsten ; Eger, Steffen ; Do Dinh, Erik-Lân ; Gurevych, Iryna |
| Art des Eintrags: | Bibliographie |
| Titel: | Still not there? Comparing Traditional Sequence-to-Sequence Models to Encoder-Decoder Neural Networks on Monotone String Translation Tasks |
| Sprache: | Englisch |
| Publikationsjahr: | Dezember 2016 |
| Verlag: | The COLING 2016 Organizing Committee |
| Buchtitel: | Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers |
| Veranstaltungsort: | Osaka, Japan |
| URL / URN: | http://aclweb.org/anthology/C16-1160 |
| Kurzbeschreibung (Abstract): | 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 \textit{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. |
| Freie Schlagworte: | UKP-DIPF;UKP_reviewed;UKP_a_DLinNLP |
| ID-Nummer: | TUD-CS-2016-1450 |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung |
| Hinterlegungsdatum: | 31 Dez 2016 14:29 |
| Letzte Änderung: | 24 Jan 2020 12:03 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum