The good, the bad, and the unknown: morphosyllabic sentiment tagging of unseen words
HLT-Short '08 Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies: Short Papers
| Hi-index | 0.00 |
This paper investigates a little-studied class of adjectives that we refer to as 'complex adjectives', i.e., operationally, adjectives constituted of at least two word tokens separated by a hyphen. We study the properties of these adjectives using two very large text collections: a portion of Wikipedia and a Web corpus. We consider three corpus-based measures of morphological productivity, and we investigate how productivity rankings based on them correlate with each other under different conditions, thus providing different angles both on the morphological productivity of complex adjectives, and on the productivity measures themselves.