Polyglot Semantic Role Labeling
This addresses the challenge of leveraging cross-linguistic similarities for semantic parsing, offering a practical solution for multilingual NLP applications, though it is incremental in nature.
The paper tackled the problem of multilingual semantic role labeling by combining resources from language pairs without parallel data, resulting in improved SRL performance over monolingual baselines, particularly in lower-resource settings.
Previous approaches to multilingual semantic dependency parsing treat languages independently, without exploiting the similarities between semantic structures across languages. We experiment with a new approach where we combine resources from a pair of languages in the CoNLL 2009 shared task to build a polyglot semantic role labeler. Notwithstanding the absence of parallel data, and the dissimilarity in annotations between languages, our approach results in an improvement in SRL performance on multiple languages over a monolingual baseline. Analysis of the polyglot model shows it to be advantageous in lower-resource settings.