This paper describes the Shallow Discourse Parser (SDP) submitted as a part of the Shared Task of CoNLL, 2016. The discourse parser takes newswire text as input and outputs relations between various components of the text. Our system is a pipeline of various sub-tasks which have been elaborated in the paper. We choose a data driven approach for each task and put a special focus on utilizing the resources allowed by the organizers for creating novel features. We also give details of various experiments with the dataset and the lexicon provided for the task.
Mapping local news coverage from textual content is a challenging problem that requires extracting precise location mentions from news articles. While traditional named entity taggers are able to extract geo-political entities and certain non geo-political entities, they cannot recognize precise location mentions such as addresses, streets and intersections that are required to accurately map the news article. We fine-tune a BERT-based language model for achieving high level of granularity in location extraction. We incorporate the model into an end-to-end tool that further geocodes the extracted locations for the broader objective of mapping news coverage.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.