Paper: Deriving Adjectival Scales from Continuous Space Word Representations

ACL ID D13-1169
Title Deriving Adjectival Scales from Continuous Space Word Representations
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2013
Authors

Continuous space word representations ex- tracted from neural network language mod- els have been used effectively for natural lan- guage processing, but until recently it was not clear whether the spatial relationships of such representations were interpretable. Mikolov et al. (2013) show that these representations do capture syntactic and semantic regularities. Here, we push the interpretation of continuous space word representations further by demon- strating that vector offsets can be used to de- rive adjectival scales (e.g., okay < good < ex- cellent). We evaluate the scales on the indirect answers to yes/no questions corpus (de Marn- effe et al., 2010). We obtain 72.8% accuracy, which outperforms previous results (?60%) on this corpus and highlights the quality of the scales extracte...