Cross-lingual and cross-domain discourse segmentation of entire documents
This addresses the problem of limited discourse segmentation tools for researchers and practitioners in NLP, though it is incremental as it extends existing methods to new languages and domains.
The paper tackled the lack of discourse segmenters for multiple languages and domains by proposing statistical models that do not rely on gold pre-annotations, achieving 89.5% F1 for English newswire with slight drops in other domains.
Discourse segmentation is a crucial step in building end-to-end discourse parsers. However, discourse segmenters only exist for a few languages and domains. Typically they only detect intra-sentential segment boundaries, assuming gold standard sentence and token segmentation, and relying on high-quality syntactic parses and rich heuristics that are not generally available across languages and domains. In this paper, we propose statistical discourse segmenters for five languages and three domains that do not rely on gold pre-annotations. We also consider the problem of learning discourse segmenters when no labeled data is available for a language. Our fully supervised system obtains 89.5% F1 for English newswire, with slight drops in performance on other domains, and we report supervised and unsupervised (cross-lingual) results for five languages in total.