From jim at well.com Sun Jul 8 05:41:59 2007 From: jim at well.com (jim stockford) Date: Sat, 7 Jul 2007 20:41:59 -0700 Subject: [PyOP] bayPIGgies meeting July 12: Natural Language Toolkit Message-ID: <4f203d54d61e68402c14f7b87abf9524@well.com> Thursday, July 12, 2007 Location: Google Agenda----------------------------- ..... 7:30 PM ........................... General hubbub, inventory end-of-meeting announcements, any first-minute announcements. ..... 7:35 PM to 8:45 PM ................ Topic: The Natural Language Toolkit (NLTK) Steven Bird, Ewan Klein, and Edward Loper Most human knowledge--and most human communication--is representedand expressed using language. Language technologies permit computers to process human language automatically; handheld computers support predictive text and handwriting recognition; web search engines give access to information locked up in unstructured text. By providing more natural human-machine interfaces and more sophisticated access to stored information, Natural Language Processing has come to play a central role in the multilingual information society. The Natural Language Toolkit is a suite of open source Python modules, data sets, and tutorials supporting research and development in Natural Language Processing. NLTK includes some 50k lines of Python, a 380-page book (80% complete), and 300Mb of test data, all freely downloadable from http://nltk.org/index.php. In this presentation, the developers of NLTK will introduce the field of Natural Language Processing, demonstrate the main features of NLTK, and describe ways for the Pythoncommunity to participate in the ongoing development effort. About the presenters: Steven Bird is Associate Professor in Computer Science at the University of Melbourne in Australia, and Senior Research Associate in the Linguistic Data Consortium at the University of Pennsylvania, specializing in R&D on models and tools for large databases of annotated text. Steven edits the book series "Cambridge Studies in Natural Language Processing," and was recently elected president of the Association for Computational Linguistics. Ewan Klein is Professor of Language Technology in the School of Informatics at the University of Edinburgh in Scotland. He has also been Research Manager for the Natural Language Research Group of Edify Corporation, Santa Clara, and was responsible for spoken dialogue processing. Ewan was the founding Coordinator of the European Network of Excellence in Human Language Technologies. He has lead numerous academic-industrial collaborative projects, most recently in biological text mining. Edward Loper is a doctoral student at the University of Pennsylvania, conducting research on machine learning in natural languageprocessing. In addition to NLTK, Edward has helped develop othermajor packages for documenting and testing Python software, epydoc and doctest. ..... 8:45 PM to 9:00 PM ................ Mapping/Random Access Mapping is a rapid-fire audience announcement of topics the announcers are interested in. Random Access follows immediately to allow follow up individually on topics of interest. ..... The August Meeting ................ The August meeting is Newbies' Night, Part 2, presenting the second half of Alex Martelli's Python for Programmers talk. From donnamsnow at gmail.com Mon Jul 9 06:22:57 2007 From: donnamsnow at gmail.com (Donna Snow) Date: Sun, 8 Jul 2007 21:22:57 -0700 Subject: [PyOP] bayPIGgies meeting July 12: Natural Language Toolkit In-Reply-To: <4f203d54d61e68402c14f7b87abf9524@well.com> References: <4f203d54d61e68402c14f7b87abf9524@well.com> Message-ID: site is updated.. Donna On 7/7/07, jim stockford wrote: > > > Thursday, July 12, 2007 > Location: Google > > > Agenda----------------------------- > > > ..... 7:30 PM ........................... > General hubbub, inventory end-of-meeting announcements, > any first-minute announcements. > > > ..... 7:35 PM to 8:45 PM ................ > Topic: The Natural Language Toolkit (NLTK) > Steven Bird, Ewan Klein, and Edward Loper > > Most human knowledge--and most human communication--is > representedand expressed using language. > Language technologies permit computers > to process human language automatically; handheld computers > support predictive text and handwriting recognition; web > search engines give access to information locked up in > unstructured text. > By providing more natural human-machine interfaces and > more sophisticated access to stored information, Natural > Language Processing has come to play a central role in the > multilingual information society. > The Natural Language Toolkit is a suite of open source > Python modules, data sets, and tutorials supporting research > and development in Natural Language Processing. NLTK > includes some 50k lines of Python, a 380-page book > (80% complete), and 300Mb of test data, all freely > downloadable from http://nltk.org/index.php. > In this presentation, the developers of NLTK will > introduce the field of Natural Language Processing, > demonstrate the main features of NLTK, and describe ways > for the Pythoncommunity to participate in the ongoing > development effort. > > About the presenters: > > Steven Bird is Associate Professor in Computer Science at the > University of Melbourne in Australia, and Senior Research Associate > in the Linguistic Data Consortium at the University of Pennsylvania, > specializing in R&D on models and tools for large databases of > annotated text. Steven edits the book series "Cambridge Studies in > Natural Language Processing," and was recently elected president of > the Association for Computational Linguistics. > > Ewan Klein is Professor of Language Technology in the School of > Informatics at the University of Edinburgh in Scotland. He has > also been Research Manager for the Natural Language Research Group > of Edify Corporation, Santa Clara, and was responsible for spoken > dialogue processing. Ewan was the founding Coordinator of the > European Network of Excellence in Human Language Technologies. > He has lead numerous academic-industrial collaborative projects, > most recently in biological text mining. > > Edward Loper is a doctoral student at the University of > Pennsylvania, conducting research on machine learning in natural > languageprocessing. In addition to NLTK, Edward has helped develop > othermajor packages for documenting and testing Python software, > epydoc and doctest. > > > ..... 8:45 PM to 9:00 PM ................ > Mapping/Random Access > > Mapping is a rapid-fire audience announcement of topics the announcers > are interested in. > > Random Access follows immediately to allow follow up individually on > topics of interest. > > > ..... The August Meeting ................ > The August meeting is Newbies' Night, Part 2, presenting the second > half of Alex Martelli's Python for Programmers talk. > >