Neural Networks for Cross-lingual Negation Scope Detection
This addresses the challenge of applying negation scope detection to languages lacking annotations, though it is incremental as it builds on existing methods for English and Chinese.
The paper tackled the problem of detecting negation scope in languages without annotated data by developing neural models that use cross-lingual word embeddings or universal dependencies trained on English and tested on Chinese, achieving surprisingly good results with syntax modeling being helpful and cross-lingual embeddings providing little benefit.
Negation scope has been annotated in several English and Chinese corpora, and highly accurate models for this task in these languages have been learned from these annotations. Unfortunately, annotations are not available in other languages. Could a model that detects negation scope be applied to a language that it hasn't been trained on? We develop neural models that learn from cross-lingual word embeddings or universal dependencies in English, and test them on Chinese, showing that they work surprisingly well. We find that modelling syntax is helpful even in monolingual settings and that cross-lingual word embeddings help relatively little, and we analyse cases that are still difficult for this task.