DiscSense: Automated Semantic Analysis of Discourse Markers
This work offers a data-driven resource for researchers in computational linguistics and NLP to study discourse markers, but it is incremental as it builds on existing prediction models and datasets.
The authors tackled the problem of linking discourse markers to semantic relations by using a model to predict markers between sentence pairs with known relations, creating a bottom-up dataset called DiscSense. This approach provides an automated characterization of hundreds of discourse markers in English, addressing limitations of handcrafted mappings and competing taxonomies.
Discourse markers ({\it by contrast}, {\it happily}, etc.) are words or phrases that are used to signal semantic and/or pragmatic relationships between clauses or sentences. Recent work has fruitfully explored the prediction of discourse markers between sentence pairs in order to learn accurate sentence representations, that are useful in various classification tasks. In this work, we take another perspective: using a model trained to predict discourse markers between sentence pairs, we predict plausible markers between sentence pairs with a known semantic relation (provided by existing classification datasets). These predictions allow us to study the link between discourse markers and the semantic relations annotated in classification datasets. Handcrafted mappings have been proposed between markers and discourse relations on a limited set of markers and a limited set of categories, but there exist hundreds of discourse markers expressing a wide variety of relations, and there is no consensus on the taxonomy of relations between competing discourse theories (which are largely built in a top-down fashion). By using an automatic rediction method over existing semantically annotated datasets, we provide a bottom-up characterization of discourse markers in English. The resulting dataset, named DiscSense, is publicly available.