WordNet-Based Inference of Textual Cohesion and Coherence

In this paper I presents a computational method for the recognition of the cohesive and coherence structures of texts. A large lexical knowledge base built oil top of WordNet provides with the lexico-semantic information that needs to be mined. A path-finding algorithm returns the cohesive structure of a text with results that outperform previous approaches. The Iexical paths contained in the cohesive structures are used to (1) build patterns of association between cue phrases and coherence relations and (2) to find the lexical characterist.ics of coherence categories. Finally. the textual coherence structure is recognized by giving priority to the coherence constrains induced by cue phrases. The paper presents also the performance of building the coherence structure for several texts. Sanda M. Harabagiu WordNet-Based Inference of Textual Cohesion and Coherence WordNet-Based Inference of Textual Cohesion and Coherence ../../../Papers/FLAIRS/1998/FLAIRS98-051.pdf Sanda M. Harabagiu https://auld.aaai.org/Library/FLAIRS/1998/flairs98-053.php flairs-1998 01-all-papers 053 1998 FLAIRS A WordNet-Based Interface to Internet Search Engines Dan I. Moldovan ||Rada Mihalcea https://cdn.aaai.org/FLAIRS/1998/FLAIRS98-053.pdf In this paper we present a natural language interface system to a search engine and discuss some of the results obtained. Dan I. Moldovan and Rada Mihalcea A WordNet-Based Interface to Internet Search Engines A WordNet-Based Interface to Internet Search Engines ../../../Papers/FLAIRS/1998/FLAIRS98-053.pdf Dan I. Moldovan and Rada Mihalcea https://auld.aaai.org/Library/FLAIRS/1998/flairs98-054.php flairs-1998 01-all-papers 054 1998 FLAIRS Pronoun Resolution of They" and "Them"