Semi Supervised Preposition-Sense Disambiguation using Multilingual Data
This addresses the challenge of small annotated corpora for a critical NLP task, offering an incremental improvement for language understanding.
The paper tackles the problem of preposition-sense disambiguation by using unannotated multilingual data to improve supervised models, resulting in consistent performance gains on two datasets.
Prepositions are very common and very ambiguous, and understanding their sense is critical for understanding the meaning of the sentence. Supervised corpora for the preposition-sense disambiguation task are small, suggesting a semi-supervised approach to the task. We show that signals from unannotated multilingual data can be used to improve supervised preposition-sense disambiguation. Our approach pre-trains an LSTM encoder for predicting the translation of a preposition, and then incorporates the pre-trained encoder as a component in a supervised classification system, and fine-tunes it for the task. The multilingual signals consistently improve results on two preposition-sense datasets.