Reimers, Nils ; Gurevych, Iryna (2017)
Reporting Score Distributions Makes a Difference: Performance Study of LSTM-networks for Sequence Tagging.
Copenhagen, Denmark
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
In this paper we show that reporting a single performance score is insufficient to compare non-deterministic approaches. We demonstrate this for common sequence tagging tasks that the seed value for the random number generator can result in statistically significant (p < 10^{-4}) differences for state-of-the-art systems. For two recent systems for NER, we observe an absolute difference of one percentage point F1-score depending on the selected seed value, making these systems perceived either as state-of-the-art or mediocre. Instead of publishing and reporting single performance scores, we propose to compare score distributions based on multiple executions. Based on the evaluation of 50.000 LSTM-networks for five sequence tagging tasks, we present network architectures that perform superior as well as produce results with higher stability on unseen data.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2017 |
| Autor(en): | Reimers, Nils ; Gurevych, Iryna |
| Art des Eintrags: | Bibliographie |
| Titel: | Reporting Score Distributions Makes a Difference: Performance Study of LSTM-networks for Sequence Tagging |
| Sprache: | Englisch |
| Publikationsjahr: | September 2017 |
| Buchtitel: | Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP) |
| Veranstaltungsort: | Copenhagen, Denmark |
| URL / URN: | http://aclweb.org/anthology/D17-1035 |
| Zugehörige Links: | |
| Kurzbeschreibung (Abstract): | In this paper we show that reporting a single performance score is insufficient to compare non-deterministic approaches. We demonstrate this for common sequence tagging tasks that the seed value for the random number generator can result in statistically significant (p < 10^{-4}) differences for state-of-the-art systems. For two recent systems for NER, we observe an absolute difference of one percentage point F1-score depending on the selected seed value, making these systems perceived either as state-of-the-art or mediocre. Instead of publishing and reporting single performance scores, we propose to compare score distributions based on multiple executions. Based on the evaluation of 50.000 LSTM-networks for five sequence tagging tasks, we present network architectures that perform superior as well as produce results with higher stability on unseen data. |
| ID-Nummer: | TUD-CS-2017-0150 |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung DFG-Graduiertenkollegs DFG-Graduiertenkollegs > Graduiertenkolleg 1994 Adaptive Informationsaufbereitung aus heterogenen Quellen |
| Hinterlegungsdatum: | 04 Jul 2017 09:53 |
| Letzte Änderung: | 24 Jan 2020 12:03 |
| PPN: | |
| Zugehörige Links: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum