Moosavi, Nafise Sadat ; Utama, Prasetya ; Rücklé, Andreas ; Gurevych, Iryna (2019)
Improving Generalization by Incorporating Coverage in Natural Language Inference.
doi: 10.48550/arXiv.1909.08940
Report, Bibliographie
Kurzbeschreibung (Abstract)
The task of natural language inference (NLI) is to identify the relation between the given premise and hypothesis. While recent NLI models achieve very high performance on individual datasets, they fail to generalize across similar datasets. This indicates that they are solving NLI datasets instead of the task itself. In order to improve generalization, we propose to extend the input representations with an abstract view of the relation between the hypothesis and the premise, i.e., how well the individual words, or word n-grams, of the hypothesis are covered by the premise. Our experiments show that the use of this information considerably improves generalization across different NLI datasets without requiring any external knowledge or additional data. Finally, we show that using the coverage information is not only beneficial for improving the performance across different datasets of the same task. The resulting generalization improves the performance across datasets that belong to similar but not the same tasks.
| Typ des Eintrags: | Report |
|---|---|
| Erschienen: | 2019 |
| Autor(en): | Moosavi, Nafise Sadat ; Utama, Prasetya ; Rücklé, Andreas ; Gurevych, Iryna |
| Art des Eintrags: | Bibliographie |
| Titel: | Improving Generalization by Incorporating Coverage in Natural Language Inference |
| Sprache: | Englisch |
| Publikationsjahr: | 20 September 2019 |
| Verlag: | arXiv |
| Reihe: | Computation and Language |
| Auflage: | 1.Version |
| DOI: | 10.48550/arXiv.1909.08940 |
| URL / URN: | https://arxiv.org/abs/1909.08940 |
| Kurzbeschreibung (Abstract): | The task of natural language inference (NLI) is to identify the relation between the given premise and hypothesis. While recent NLI models achieve very high performance on individual datasets, they fail to generalize across similar datasets. This indicates that they are solving NLI datasets instead of the task itself. In order to improve generalization, we propose to extend the input representations with an abstract view of the relation between the hypothesis and the premise, i.e., how well the individual words, or word n-grams, of the hypothesis are covered by the premise. Our experiments show that the use of this information considerably improves generalization across different NLI datasets without requiring any external knowledge or additional data. Finally, we show that using the coverage information is not only beneficial for improving the performance across different datasets of the same task. The resulting generalization improves the performance across datasets that belong to similar but not the same tasks. |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung DFG-Graduiertenkollegs DFG-Graduiertenkollegs > Graduiertenkolleg 1994 Adaptive Informationsaufbereitung aus heterogenen Quellen |
| Hinterlegungsdatum: | 23 Sep 2019 05:37 |
| Letzte Änderung: | 17 Aug 2023 10:03 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum