Abstract
We present a system for analyzing conversational data. The system includes state-of-the-art natural language processing components that have been modified to accommodate the unique nature of conversational data. In addition, we leverage the added richness of conversational data by analyzing various aspects of the participants and their relationships to each other. Our tool provides users with the ability to easily identify topics or persons of interest, including who talked to whom, when, entities that were discussed, etc. Using this tool, one can also isolate more complex networks of information: individuals who may have discussed the same topics but never talked to each other. The tool includes a UI that plots information over time, and a semantic graph that highlights relationships of interest.
| Original language | English |
|---|---|
| Pages | 50-57 |
| Number of pages | 8 |
| State | Published - 2006 |
| Externally published | Yes |
| Event | 2006 HLT-NAACL Workshop on Analyzing Conversations in Text and Speech, ACTS 2006 - New York City, United States Duration: Jun 8 2006 → … |
Conference
| Conference | 2006 HLT-NAACL Workshop on Analyzing Conversations in Text and Speech, ACTS 2006 |
|---|---|
| Country/Territory | United States |
| City | New York City |
| Period | 06/8/06 → … |