Scoring and Classifying Implicit Positive Interpretations: A Challenge of Class Imbalance
| Autor: | Son, C. M., Roser Morante Vallejo, Lora Aroyo, Vossen, P. T. J. M. |
|---|---|
| Přispěvatelé: | Network Institute, Language |
| Zdroj: | Vrije Universiteit Amsterdam Proceedings of the the International Conference on Computational Linguistics (COLING 2018), 2253-2264 STARTPAGE=2253;ENDPAGE=2264;TITLE=Proceedings of the the International Conference on Computational Linguistics (COLING 2018) |
| Popis: | This paper reports on a reimplementation of a system on detecting implicit positive meaning from negated statements. In the original regression experiment, different positive interpretations per negation are scored according to their likelihood. We convert the scores to classes and report our results on both the regression and classification tasks. We show that a baseline taking the mean score or most frequent class is hard to beat because of class imbalance in the dataset. Our error analysis indicates that an approach that takes the information structure into account (i.e. which information is new or contrastive) may be promising, which requires looking beyond the syntactic and semantic characteristics of negated statements. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|