Summary of the paper
| Title | Bootstrapping Named Entity Extraction for the Creation of Mobile Services |
|---|---|
| Authors | Joseph Polifroni, Imre Kiss and Mark Adler |
| Abstract | As users become more accustomed to using their mobile devices to organize andschedule their lives, there is more of a demand for applications that can make that process easier. Automatic speech recognition technology has already beendeveloped to enable essentially unlimited vocabulary in a mobile setting. Understanding the words that are spoken is the next challenge. In thispaper,we describe efforts to develop a dataset and classifier to recognize namedentities in speech. Using sets of both real and simulated data, in conjunctionwith a very large set of real named entities, we created a challenging corpusof training and test data. We use these data to develop a classifier toidentify names and locations on a word-by-word basis. In this paper, wedescribe the process of creating the data and determining a set of features touse for named entity recognition. We report on our classification performanceon these data, as well as point to future work in improving all aspects of thesystem. |
| Language | Speech Recognition/Understanding |
| Topics | Named Entity recognition, Statistical and machine learning methods, Speech Recognition/Understanding |
Full paper  |
Bootstrapping Named Entity Extraction for the Creation of Mobile Services |
| Bibtex | @InProceedings{POLIFRONI10.280, author = {Joseph Polifroni, Imre Kiss and Mark Adler}, title = {Bootstrapping Named Entity Extraction for the Creation of Mobile Services}, 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} } |