NAACL HLT 2009 Human Language Technologies : The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics

NAACL HLT 2009 Human Language Technologies : The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics

Creating Local Coherence: An Empirical Assessment

Two of the mechanisms for creating natural transitions between adjacent sentences in a text, resulting in local coherence, involve discourse relations and switches of focus of attention between discourse entities. These two aspects of local coherence have been traditionally discussed and studied separately. But some empirical studies have given strong evidence for the necessity of understanding...

Making Semantic Topicality Robust Through Term Abstraction

Micha Elsner and Eugene Charniak. You talking to me? A corpus and algorithm for conversation disentanglement. In The Association for Computational Linguistics: Human Language Technologies (ACL-HLT 2008), Columbus, Ohio, 2008. Michael Halliday and Ruqaiya Hasan. Cohesion in English. Longman Group, New York, 1976. Jacki O’Neill and David Martin. Text chat in action. In GROUP ‘03: Proceedings of t...

NAACL HLT 2010 Human Language Technologies : The 2010 Annual Conference of the North American Chapter of the Association for

Determining the correct structure of coordinating conjunctions and the syntactic constituents that they coordinate is a difficult task. This subtask of syntactic parsing is explored here for biomedical scientific literature. In particular, the intuition that sentences containing coordinating conjunctions can often be rephrased as two or more smaller sentences derived from the coordination struc...

NAACL HLT 2007 Human Language Technologies 2007 : The Conference of the North American Chapter of the Association for Computational Linguistics

In this paper we describe an automaticprosody labeling framework that exploitsboth language and speech information.We model the syntactic-prosodic informa-tion with a maximum entropy model thatachieves an accuracy of 85.2% and 91.5%for pitch accent and boundary tone la-beling on the Boston University RadioNews corpus. We model the acoustic-prosodic stream wit...