Cross-Lingual Transfer of Semantic Roles: From Raw Text to Semantic Roles
This addresses the challenge of cross-lingual NLP for low-resource languages, offering a more accessible approach without relying on supervised features.
The paper tackles the problem of semantic role labeling for languages lacking supervised linguistic resources by proposing a transfer method using only word and character features, outperforming a state-of-the-art method on 6 out of 7 languages in the Universal Proposition Bank.
We describe a transfer method based on annotation projection to develop a dependency-based semantic role labeling system for languages for which no supervised linguistic information other than parallel data is available. Unlike previous work that presumes the availability of supervised features such as lemmas, part-of-speech tags, and dependency parse trees, we only make use of word and character features. Our deep model considers using character-based representations as well as unsupervised stem embeddings to alleviate the need for supervised features. Our experiments outperform a state-of-the-art method that uses supervised lexico-syntactic features on 6 out of 7 languages in the Universal Proposition Bank.