Summary of the paper
| Title | Speech Grammars for Textual Entailment Patterns in Multimodal Question Answering |
|---|---|
| Authors | Daniel Sonntag and Bogdan Sacaleanu |
| Abstract | Over the last several years, speech-based question answering (QA) has becomevery popular in contrast to pure search engine based approaches on a desktop.Open-domain QA systems are now much more powerful and precise, and they can beused in speech applications. Speech-based question answering systems often relyon predefined grammars for speech understanding. In order to improve thecoverage of such complex AI systems, we reused speech patterns used to generatetextual entailment patterns. These can make multimodal question understandingmore robust. We exemplify this in the context of a domain-specific dialoguescenario. As a result, written text input components (e.g., in a textual inputfield) can deal with more flexible input according to the derived textualentailment patterns. A multimodal QA dialogue spanning over several domains ofinterest, i.e., personal address book entries, questions about the music domainand politicians and other celebrities, demonstrates how the textual input modecan be used in a multimodal dialogue shell. |
| Language | Dialogue |
| Topics | Question Answering, Semantic Web, Dialogue |
Full paper  |
Speech Grammars for Textual Entailment Patterns in Multimodal Question Answering |
| Bibtex | @InProceedings{SONNTAG10.911, author = {Daniel Sonntag and Bogdan Sacaleanu}, title = {Speech Grammars for Textual Entailment Patterns in Multimodal Question Answering}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |