<html><head><style type="text/css"><!-- DIV {margin:0px;} --></style></head><body><div style="font-family:times new roman, new york, times, serif;font-size:12pt"><DIV>Hello!</DIV>
<DIV>I am working on Adverbials in Pakistani English for my M.Phil thesis. The idea is to prove Pakistani English as an independent variety. For this purpose i have tagged corpus of Pakistani Written English. I want to get this data parsed. can you help me in this regard?</DIV>
<DIV>Plz reply and comment.</DIV>
<DIV> </DIV>
<DIV>Nasir Ali</DIV>
<DIV>M.Phil Scholar</DIV>
<DIV>Dept. Applied Linguistics</DIV>
<DIV>G.C University Faisalabad.</DIV>
<DIV> </DIV>
<DIV>Lecturer English </DIV>
<DIV>Depatrment of Humanities and Social Sciences</DIV>
<DIV>National Textile University Faisalabad</DIV>
<DIV>Pakistan<BR></DIV>
<DIV style="FONT-FAMILY: times new roman, new york, times, serif; FONT-SIZE: 12pt"><BR>
<DIV style="FONT-FAMILY: arial, helvetica, sans-serif; FONT-SIZE: 13px"><FONT size=2 face=Tahoma>
<HR SIZE=1>
<B><SPAN style="FONT-WEIGHT: bold">From:</SPAN></B> "corpora-request@uib.no" <corpora-request@uib.no><BR><B><SPAN style="FONT-WEIGHT: bold">To:</SPAN></B> corpora@uib.no<BR><B><SPAN style="FONT-WEIGHT: bold">Sent:</SPAN></B> Wed, September 29, 2010 3:00:01 PM<BR><B><SPAN style="FONT-WEIGHT: bold">Subject:</SPAN></B> Corpora Digest, Vol 39, Issue 31<BR></FONT><BR>Today's Topics:<BR><BR> 1. 3 Research Internships at FBK-irst (Marcello Federico)<BR> 2. Job announcement (Stefanie Dipper)<BR> 3. Re: Help Regarding Cognates Identification (chris brew)<BR> 4. A word of advice needed on Pakistani English (Ahmad Ahmad)<BR> 5. Release of SemEval2010-Task1 datasets (Coreference<BR> Resolution in Multiple Languages) (Marta Recasens)<BR> 6. thesis / internship in MT inquiry for a student speaking<BR> Polish (native) English, French, Spanish, and basic
Swedish<BR> (Sandra Weiss)<BR> 7. Re: Looking for toolkit for verb tense detection<BR> (Amaç Herda?delen)<BR> 8. Re: Looking for toolkit for verb tense detection (Alexander Yeh)<BR> 9. Re: Looking for toolkit for verb tense detection<BR> (<A href="mailto:liqiearth@gmail.com" ymailto="mailto:liqiearth@gmail.com">liqiearth@gmail.com</A>)<BR> 10. Re: Looking for toolkit for verb tense detection<BR> (<A href="mailto:liqiearth@gmail.com" ymailto="mailto:liqiearth@gmail.com">liqiearth@gmail.com</A>)<BR> 11. Phonemic variations across languages (Yuri Tambovtsev)<BR><BR><BR>----------------------------------------------------------------------<BR><BR>Message: 1<BR>Date: Tue, 28 Sep 2010 14:32:59 +0000<BR>From: Marcello Federico <<A href="mailto:federico@fbk.eu"
ymailto="mailto:federico@fbk.eu">federico@fbk.eu</A>><BR>Subject: [Corpora-List] 3 Research Internships at FBK-irst<BR>To: "<A href="mailto:corpora@uib.no" ymailto="mailto:corpora@uib.no">corpora@uib.no</A>" <<A href="mailto:corpora@uib.no" ymailto="mailto:corpora@uib.no">corpora@uib.no</A>><BR><BR><BR>The ?Human Language Technologies? Research Unit of Bruno Kessler Foundation (FBK) is seeking <BR>candidates for three research internship positions:<BR><BR>- two in the field of Statistical Machine Translation <BR>- one in the field of Content Processing. <BR><BR>The internship are intended to provide a strong theoretical and experimental background to graduate <BR>students interested in applying later for a PhD scholarship.<BR><BR>Requirements, salary, and application procedure are specified in:<BR><A href="http://risorseumane.fbk.eu/sites/risorseumane.fbk.eu/files/Call%20HLT_INTERNSHIP2010.pdf"
target=_blank>http://risorseumane.fbk.eu/sites/risorseumane.fbk.eu/files/Call%20HLT_INTERNSHIP2010.pdf</A><BR><BR>Closing date: 12 October 2010<BR><BR><BR><BR><BR><BR><BR><BR><BR><BR>------------------------------<BR><BR>Message: 2<BR>Date: Tue, 28 Sep 2010 18:12:49 +0200 (CEST)<BR>From: Stefanie Dipper <<A href="mailto:dipper@linguistics.rub.de" ymailto="mailto:dipper@linguistics.rub.de">dipper@linguistics.rub.de</A>><BR>Subject: [Corpora-List] Job announcement<BR>To: <A href="mailto:Corpora@uib.no" ymailto="mailto:Corpora@uib.no">Corpora@uib.no</A><BR><BR>#########################<BR>University: Ruhr-University Bochum<BR>Department: Linguistics Department<BR>Job Rank: 2 Project researchers, salary scale 13 TV-L (65%, PhD positions)<BR>Specialty Areas: Computational Linguistics, Corpus Linguistics<BR>Application Deadline: 1-Nov-2010 (open until filled)<BR>Duration: Initial contract 2 years, with potential extension for an <BR>additional
year<BR>#########################<BR><BR>We are looking for two enthusiastic PhD students, prepared to collaborate <BR>in a team. The positions are within an interdisciplinary project group, <BR>funded by the DFG (German Research Foundation), which involve people from <BR>medieval studies, historical linguistics, and computational linguistics. <BR>The project deals with texts from Early New High German (14th-16th <BR>centuries).<BR><BR>The project has three main goals: (i) developing automatic methods for the <BR>analysis of historical language data (e.g. POS tagging, normalization, <BR>alignment); (ii) computing similarity of historical dialects (at different <BR>linguistic levels); (iii) adapting and extending an existing corpus tool <BR>for the data.<BR><BR>Applicants for both positions should have graduated from a master's <BR>program, or expect to graduate in the near future. They are supposed to <BR>pursue a PhD within the project context. Both
positions require a <BR>background in corpus and/or computational linguistics, and good <BR>programming skills (e.g. Java, Perl, Python; experience in software <BR>development on Linux systems is a plus). Knowledge of German is desirable, <BR>and interest in working with historical language data is indispensable.<BR><BR>Ideal candidates will have a strong background in two or more of the <BR>following areas:<BR><BR>- Development of corpus tools (annotation tools, search tools)<BR>- (Semi-)automatic annotation (POS tagging, chunking, alignment, etc.)<BR>- Data mining, clustering<BR>- Historical linguistics<BR><BR>The positions are at the rank of 'Wissenschaftliche Mitarbeiter'. The <BR>salary is determined by the pay scale for German public employees <BR>('Entgeltgruppe' TV-L E13, 65%). The initial contract length is two years, <BR>with a potential extension for an additional year.<BR><BR>Applications received by November 1, 2010 will receive full
consideration. <BR>However, the search will remain open until the positions are filled. <BR>Candidates should send:<BR><BR>- a short letter of interest<BR>- a detailed CV with a summary of research experiences/interests<BR>- one or two sample publications or a copy of the master thesis<BR>- the names and contact information of two referees<BR>- diploma copies.<BR><BR>Please submit PDF files only. Email address for inquiries and <BR>applications: dipper AT linguistics.rub.de<BR><BR>The Ruhr-University Bochum is an equal opportunity employer. Severely <BR>disabled persons with equal qualifications will be prioritized.<BR><BR>Jun.Prof. Dr. Stefanie Dipper<BR>Institute of Linguistics<BR>Ruhr-University Bochum<BR>D - 44780 Bochum<BR>Germany<BR><A href="http://www.linguistics.ruhr-uni-bochum.de/~dipper" target=_blank>http://www.linguistics.ruhr-uni-bochum.de/~dipper</A><BR><BR><BR><BR>------------------------------<BR><BR>Message: 3<BR>Date: Tue, 28 Sep 2010
08:41:59 -0400<BR>From: chris brew <<A href="mailto:cbrew@ling.osu.edu" ymailto="mailto:cbrew@ling.osu.edu">cbrew@ling.osu.edu</A>><BR>Subject: Re: [Corpora-List] Help Regarding Cognates Identification<BR>To: Padmini priyadharsini <<A href="mailto:padminipriyadharsini@gmail.com" ymailto="mailto:padminipriyadharsini@gmail.com">padminipriyadharsini@gmail.com</A>><BR>Cc: <A href="mailto:corpora@uib.no" ymailto="mailto:corpora@uib.no">corpora@uib.no</A><BR><BR>I understand the definition of "cognate" to be about the history of words,<BR>not just about<BR>similarities in the surface form. There are at least three ways that words<BR>can come to be<BR>similar across languages<BR><BR>1) words have a common ancestry: language A and language B have words that<BR>can be traced back to the same root word in some ancestor language. These<BR>cases can be interesting, like<BR>*étoile and star, *or routine, like night and nacht. In the interesting<BR>one,
a systematic process has happened that makes the letter before the t<BR>turn up as e-acute in French but s in English.<BR><BR>2) language A borrows the word from language B.<BR><BR>3) an accident happens. The words in language A and language B look the<BR>same, but there is<BR>no common ancestry and no borrowing.<BR><BR>Most people call pairs that fit under case (1) cognates, and the other two<BR>"false cognates".<BR>It is a very interesting problem to write programs to detect and take<BR>advantage of systematic sound correspondences like the star/etoile thing.<BR>Kondrak has worked on this extensively.<BR><BR>There was a good workshop on computational approaches to this stuff at ACL<BR>2007<BR><BR>@InProceedings{nerbonne-ellison-kondrak:2007:CompHistPhon,<BR> author = {Nerbonne, John and Ellison, T. Mark and Kondrak, Grzegorz},<BR> title = {Computing and Historical
Phonology},<BR> booktitle = {Proceedings of Ninth Meeting of the ACL Special<BR>Interest Group in Computational Morphology and Phonology},<BR> month = {June},<BR> year = {2007},<BR> address = {Prague, Czech Republic},<BR> publisher = {Association for Computational Linguistics},<BR> pages = {1--5},<BR> url = {<A href="http://www.aclweb.org/anthology/W/W07/W07-1301" target=_blank>http://www.aclweb.org/anthology/W/W07/W07-1301</A>}<BR>}<BR><BR>Personally, I wouldn't want to call borrowings cognates, and I would tend to<BR>see references to named entities as similar to borrowings, because very<BR>often the borrowed word is unchanged, or changed only as much as necessary<BR>to make it minimally acceptable phonologically, so the<BR>Japanese word "sekkusu" is just the way the language borrows the English<BR>word "sex", not<BR>the trace of some
historically exciting process.<BR><BR><BR>On Tue, Sep 28, 2010 at 1:23 AM, Padmini priyadharsini <<BR><A href="mailto:padminipriyadharsini@gmail.com" ymailto="mailto:padminipriyadharsini@gmail.com">padminipriyadharsini@gmail.com</A>> wrote:<BR><BR>> Hi All,<BR>><BR>> Kindly let me know the availeble tools and used techniques for<BR>> cognates identification.<BR>><BR>> I will be summarizing all the reply to the list.<BR>><BR>> Thanks,<BR>> Padmini<BR>><BR>> --<BR>> Life is beautiful and enjoy its simplicity :)<BR>><BR>> _______________________________________________<BR>> Corpora mailing list<BR>> <A href="mailto:Corpora@uib.no" ymailto="mailto:Corpora@uib.no">Corpora@uib.no</A><BR>> <A href="http://mailman.uib.no/listinfo/corpora" target=_blank>http://mailman.uib.no/listinfo/corpora</A><BR>><BR><BR><BR><BR>-- <BR>Chris Brew, Ohio State University<BR>-------------- next part --------------<BR>A
non-text attachment was scrubbed...<BR>Name: not available<BR>Type: text/html<BR>Size: 5584 bytes<BR>Desc: not available<BR>URL: <<A href="http://www.uib.no/mailman/public/corpora/attachments/20100928/76b9c631/attachment.txt" target=_blank>http://www.uib.no/mailman/public/corpora/attachments/20100928/76b9c631/attachment.txt</A>><BR><BR>------------------------------<BR><BR>Message: 4<BR>Date: Mon, 27 Sep 2010 05:36:58 -0800<BR>From: Ahmad Ahmad <<A href="mailto:escholer@gmail.com" ymailto="mailto:escholer@gmail.com">escholer@gmail.com</A>><BR>Subject: [Corpora-List] A word of advice needed on Pakistani English<BR>To: <A href="mailto:corpora@uib.no" ymailto="mailto:corpora@uib.no">corpora@uib.no</A><BR><BR>*Dear Fellows*<BR><BR>I am working on *vowels in Pakistani English* for my M Phil dissertation at<BR>GC University Faisalabad. The idea is to work on the vowels of PE to prove<BR>it an indigenous variety. It is a corpus based study using
PRAAT, finding<BR>Formant Values of the vowels of PE.<BR><BR><BR>Do comment if you can be of any help to me in this regard. Details of the<BR>proposal of dissertation may be shared.<BR><BR><BR>Regards<BR><BR><BR><BR>Hafiz Ahmad Bilal<BR><BR>M Phil Scholar<BR><BR>Dept of Applied Linguistics<BR><BR>GC University, Faisalabad<BR><BR><BR><BR>Lecturer, Dept of English<BR><BR>University of Sargodha<BR>-------------- next part --------------<BR>A non-text attachment was scrubbed...<BR>Name: not available<BR>Type: text/html<BR>Size: 2162 bytes<BR>Desc: not available<BR>URL: <<A href="http://www.uib.no/mailman/public/corpora/attachments/20100927/b07d2924/attachment.txt" target=_blank>http://www.uib.no/mailman/public/corpora/attachments/20100927/b07d2924/attachment.txt</A>><BR><BR>------------------------------<BR><BR>Message: 5<BR>Date: Tue, 28 Sep 2010 17:02:10 +0200<BR>From: Marta Recasens <<A href="mailto:mrecasens@ub.edu"
ymailto="mailto:mrecasens@ub.edu">mrecasens@ub.edu</A>><BR>Subject: [Corpora-List] Release of SemEval2010-Task1 datasets<BR> (Coreference Resolution in Multiple Languages)<BR>To: <A href="mailto:corpora@uib.no" ymailto="mailto:corpora@uib.no">corpora@uib.no</A><BR><BR>We are pleased to announce the release of the SemEval2010-Task1 datasets for coreference resolution in multiple languages including Catalan, Dutch, German, Italian, and Spanish. The English data will be released by LDC early 2011.<BR><BR>The data is now freely available for downloading from the task website, at <A href="http://stel.ub.edu/semeval2010-coref/download/" target=_blank>http://stel.ub.edu/semeval2010-coref/download/</A><BR><BR>General formatting is shared by all languages and is inspired by the previous CoNLL shared tasks (2008/2009 editions: <A href="http://ufal.mff.cuni.cz/conll2009-st" target=_blank>http://ufal.mff.cuni.cz/conll2009-st</A>). The data are
displayed in a uniform column-based format with information about coreference, lemma, PoS, morphological features, head, dependency relations, NEs, and semantic dependencies. Both gold-standard and automatically predicted information are provided (availability depending on the language). The existence of gold and automatic preprocessing as well as of already published results makes it an ideal resource for training and testing coreference resolution systems, especially when cross-language portability is to be achieved.<BR><BR>REFERENCE<BR>Marta Recasens, Lluís Màrquez, Emili Sapena, M. Antònia Martí, Mariona Taulé, Véronique Hoste, Massimo Poesio, and Yannick Versley. 2010. SemEval-2010 Task 1: Coreference Resolution in Multiple Languages. In Proceedings of the 5th International Workshop on Semantic Evaluation (SemEval-2010), ACL 2010, pages 1-8, Uppsala, Sweden.<BR><BR>We will be happy to publish your results or articles related to any of these
datasets on our website: <A href="http://stel.ub.edu/semeval2010-coref/posttask" target=_blank>http://stel.ub.edu/semeval2010-coref/posttask</A><BR>Please feel free to let us know.<BR><BR>ORGANIZERS<BR>* Marta Recasens, M. Antònia Martí, Mariona Taulé<BR> University of Barcelona<BR> {mrecasens,amarti,mtaule}@ub.edu<BR>* Lluís Màrquez, Emili Sapena<BR> Technical University of Catalonia<BR> {lluism,esapena}@lsi.upc.edu<BR>* Massimo Poesio<BR> University of Essex / University of Trento<BR>* Véronique Hoste<BR> University College Ghent<BR>* Yannick Versley<BR> University of Tübingen<BR><BR><BR>------------------------------<BR><BR>Message: 6<BR>Date: Tue, 28 Sep 2010 22:54:51 +0200<BR>From: Sandra Weiss <<A href="mailto:sandre17@gmail.com" ymailto="mailto:sandre17@gmail.com">sandre17@gmail.com</A>><BR>Subject: [Corpora-List] thesis / internship in MT inquiry for a<BR>
student speaking Polish (native) English, French, Spanish, and basic<BR> Swedish<BR>To: <A href="mailto:Corpora@uib.no" ymailto="mailto:Corpora@uib.no">Corpora@uib.no</A><BR><BR>**<BR>Dear Corpora members,<BR><BR>I am* a polish student* looking for *an internship related to Machine<BR>Translation* that could be the base for my master thesis.<BR>So far I have obtained a *BA in French and Spanish* at an english university<BR>which involved a lot of translation between the 2 languages plus into<BR>English.<BR>(including a year of *french-spanish translation and vice-versa, also into<BR>English* at a french university Jean Moulin 3 in Lyon).<BR>I have taken *courses in Machine Translation* where worked mainly on<BR>*pre-editing<BR>and post-editing* of texts run through *MT engines *plus worked with<BR>translation memory* WordFast.* I have also completed single courses in *General<BR>Linguistics*.<BR>I am now a second year student of
*Language and Culture in Europe master<BR>programme at the Linkoping's University in Sweden* plus I am in process of<BR>learning *C language* and *Perl*.<BR>I would like to work in the future in the feild of *MT* and that is why this<BR>semester I am preparing myself to take up a *master thesis* next semester<BR>hopefully *related to MT*.<BR><BR>*I am willing to take on any courses or training if required.*<BR><BR>Any help or information will be very appreciated,<BR><BR>kind regards,<BR><BR>*Sandra Weiss*<BR>*Master student of Language and Culture in Europe*<BR>*Linkoping, Sweden*<BR>*tel: *0046760812503<BR>-------------- next part --------------<BR>A non-text attachment was scrubbed...<BR>Name: not available<BR>Type: text/html<BR>Size: 2163 bytes<BR>Desc: not available<BR>URL: <<A href="http://www.uib.no/mailman/public/corpora/attachments/20100928/db71aad4/attachment.txt"
target=_blank>http://www.uib.no/mailman/public/corpora/attachments/20100928/db71aad4/attachment.txt</A>><BR><BR>------------------------------<BR><BR>Message: 7<BR>Date: Wed, 29 Sep 2010 00:44:01 +0200<BR>From: Amaç Herda?delen <<A href="mailto:amac@herdagdelen.com" ymailto="mailto:amac@herdagdelen.com">amac@herdagdelen.com</A>><BR>Subject: Re: [Corpora-List] Looking for toolkit for verb tense<BR> detection<BR>To: <A href="mailto:Corpora@uib.no" ymailto="mailto:Corpora@uib.no">Corpora@uib.no</A>, "Qi Li" <<A href="mailto:liqiearth@gmail.com" ymailto="mailto:liqiearth@gmail.com">liqiearth@gmail.com</A>><BR><BR>Hello Qi Li,<BR><BR>I think you might be interested in Nodebox's Linguistics Library: <A href="http://nodebox.net/code/index.php/Linguistics#verb_conjugation" target=_blank>http://nodebox.net/code/index.php/Linguistics#verb_conjugation</A> It provides a simple interface that does what you want (in
Python).<BR><BR>Here is the example from the documentation.<BR><BR>----<BR>print en.verb.is_tense("wasn't", "1st singular past", negated=True)<BR>print en.verb.is_present("does", person=1)<BR>print en.verb.is_present_participle("doing")<BR>print en.verb.is_past_participle("done")<BR>>>> True<BR>>>> False<BR>>>> True<BR>>>> True<BR>----<BR><BR>Cheers,<BR><BR>Amaç Herda?delen<BR><BR>On Mon, 27 Sep 2010 21:55:15 +0200, Qi Li <<A href="mailto:liqiearth@gmail.com" ymailto="mailto:liqiearth@gmail.com">liqiearth@gmail.com</A>> wrote:<BR><BR>> Hi Corpora members,<BR>><BR>> Does anyone know if there are some toolkits for word tense detection? I'm<BR>> doing research on IE system, and need tense of verbs as feature in<BR>> classifier. There are lot of papers mentioned word tense, but nobody said<BR>> how they got the tense, it seems easy to do and even get high performance.<BR>><BR>> Thanks much
for any help.<BR>><BR>> best,<BR>><BR>> Qi Li<BR>> ==========================<BR>> Department of Computer Sci.<BR>> Graduate Center, CUNY<BR>> Email: <A href="mailto:liqiearth@gmail.com" ymailto="mailto:liqiearth@gmail.com">liqiearth@gmail.com</A><BR><BR><BR><BR>------------------------------<BR><BR>Message: 8<BR>Date: Tue, 28 Sep 2010 19:20:09 -0400<BR>From: Alexander Yeh <<A href="mailto:asy@mitre.org" ymailto="mailto:asy@mitre.org">asy@mitre.org</A>><BR>Subject: Re: [Corpora-List] Looking for toolkit for verb tense<BR> detection<BR>To: Qi Li <<A href="mailto:liqiearth@gmail.com" ymailto="mailto:liqiearth@gmail.com">liqiearth@gmail.com</A>><BR>Cc: "<A href="mailto:Corpora@uib.no" ymailto="mailto:Corpora@uib.no">Corpora@uib.no</A>" <<A href="mailto:Corpora@uib.no" ymailto="mailto:Corpora@uib.no">Corpora@uib.no</A>><BR><BR>Qi Li wrote:<BR>> Hi Corpora members,<BR>><BR>> Does anyone
know if there are some toolkits for word tense detection?<BR>> I'm doing research on IE system, and need tense of verbs as feature in<BR>> classifier. There are lot of papers mentioned word tense, but nobody<BR>> said how they got the tense, it seems easy to do and even get high<BR>> performance.<BR><BR>Many part-of-speech (p-o-s) finders will differentiate between certain <BR>tenses of verbs.<BR><BR>For example, part-of-speech finders trained on the Penn Tree bank will <BR>try to distinguish between the following (from<BR><A href="http://www.ling.upenn.edu/courses/Fall_2003/ling001/penn_treebank_pos.html" target=_blank>http://www.ling.upenn.edu/courses/Fall_2003/ling001/penn_treebank_pos.html</A>):<BR><BR>27. VB Verb, base form<BR>28. VBD Verb, past tense<BR>29. VBG Verb, gerund or present participle<BR>30.
VBN Verb, past participle<BR>31. VBP Verb, non-3rd person singular present<BR>32. VBZ Verb, 3rd person singular present<BR><BR>Hope this helps<BR>-Alex Yeh<BR><BR><BR><BR>><BR>> Thanks much for any help.<BR>><BR>> best,<BR>><BR>> Qi Li<BR>> ==========================<BR>> Department of Computer Sci.<BR>> Graduate Center, CUNY<BR>> Email: <A href="mailto:liqiearth@gmail.com" ymailto="mailto:liqiearth@gmail.com">liqiearth@gmail.com</A> <mailto:<A href="mailto:liqiearth@gmail.com" ymailto="mailto:liqiearth@gmail.com">liqiearth@gmail.com</A>><BR><BR><BR><BR><BR><BR>------------------------------<BR><BR>Message: 9<BR>Date: Tue, 28 Sep 2010 23:07:09 +0000<BR>From: <A href="mailto:liqiearth@gmail.com" ymailto="mailto:liqiearth@gmail.com">liqiearth@gmail.com</A><BR>Subject: Re: [Corpora-List] Looking for toolkit
for verb tense<BR> detection<BR>To: "=?utf-8?B?QW1hw6cgSGVyZGHEn2RlbGVu?=" <<A href="mailto:amac@herdagdelen.com" ymailto="mailto:amac@herdagdelen.com">amac@herdagdelen.com</A>>,<BR> <A href="mailto:Corpora@uib.no" ymailto="mailto:Corpora@uib.no">Corpora@uib.no</A><BR><BR>Hi,<BR>Thanks a lot, I'll check it, if there is java version, that would be great. I don't know why nobody mentioned it in papers, is it so simple to do and people always do it themselves?<BR><BR>Anyway, thanks again<BR><BR>Qi Li<BR>------Original Message------<BR>From: Amaç Herda?delen<BR>To: <A href="mailto:Corpora@uib.no" ymailto="mailto:Corpora@uib.no">Corpora@uib.no</A><BR>To: Qi Li<BR>Subject: Re: [Corpora-List] Looking for toolkit for verb tense detection<BR>Sent: Sep 28, 2010 18:44<BR><BR>Hello Qi Li,<BR><BR>I think you might be interested in Nodebox's Linguistics Library: <A
href="http://nodebox.net/code/index.php/Linguistics#verb_conjugation" target=_blank>http://nodebox.net/code/index.php/Linguistics#verb_conjugation</A> It provides a simple interface that does what you want (in Python).<BR><BR>Here is the example from the documentation.<BR><BR>----<BR>print en.verb.is_tense("wasn't", "1st singular past", negated=True)<BR>print en.verb.is_present("does", person=1)<BR>print en.verb.is_present_participle("doing")<BR>print en.verb.is_past_participle("done")<BR>>>> True<BR>>>> False<BR>>>> True<BR>>>> True<BR>----<BR><BR>Cheers,<BR><BR>Amaç Herda?delen<BR><BR>On Mon, 27 Sep 2010 21:55:15 +0200, Qi Li <<A href="mailto:liqiearth@gmail.com" ymailto="mailto:liqiearth@gmail.com">liqiearth@gmail.com</A>> wrote:<BR><BR>> Hi Corpora members,<BR>><BR>> Does anyone know if there are some toolkits for word tense detection? I'm<BR>> doing research on IE system, and need tense of
verbs as feature in<BR>> classifier. There are lot of papers mentioned word tense, but nobody said<BR>> how they got the tense, it seems easy to do and even get high performance.<BR>><BR>> Thanks much for any help.<BR>><BR>> best,<BR>><BR>> Qi Li<BR>> ==========================<BR>> Department of Computer Sci.<BR>> Graduate Center, CUNY<BR>> Email: <A href="mailto:liqiearth@gmail.com" ymailto="mailto:liqiearth@gmail.com">liqiearth@gmail.com</A><BR><BR>Qi<BR><BR>------------------------------<BR><BR>Message: 10<BR>Date: Wed, 29 Sep 2010 04:25:23 +0000<BR>From: <A href="mailto:liqiearth@gmail.com" ymailto="mailto:liqiearth@gmail.com">liqiearth@gmail.com</A><BR>Subject: Re: [Corpora-List] Looking for toolkit for verb tense<BR> detection<BR>To: "Alexander Yeh" <<A href="mailto:asy@mitre.org" ymailto="mailto:asy@mitre.org">asy@mitre.org</A>><BR>Cc: "<A href="mailto:Corpora@uib.no"
ymailto="mailto:Corpora@uib.no">Corpora@uib.no</A>" <<A href="mailto:Corpora@uib.no" ymailto="mailto:Corpora@uib.no">Corpora@uib.no</A>><BR><BR>That makes sense! Thanks a lot, POS tagger is more informative than I thought.<BR><BR>Best,<BR><BR>Qi Li<BR>------Original Message------<BR>From: Alexander Yeh<BR>To: Qi Li<BR>Cc: <A href="mailto:Corpora@uib.no" ymailto="mailto:Corpora@uib.no">Corpora@uib.no</A><BR>Subject: Re: [Corpora-List] Looking for toolkit for verb tense detection<BR>Sent: Sep 28, 2010 19:20<BR><BR>Qi Li wrote:<BR>> Hi Corpora members,<BR>><BR>> Does anyone know if there are some toolkits for word tense detection?<BR>> I'm doing research on IE system, and need tense of verbs as feature in<BR>> classifier. There are lot of papers mentioned word tense, but nobody<BR>> said how they got the tense, it seems easy to do and even get high<BR>> performance.<BR><BR>Many part-of-speech (p-o-s) finders will differentiate
between certain <BR>tenses of verbs.<BR><BR>For example, part-of-speech finders trained on the Penn Tree bank will <BR>try to distinguish between the following (from<BR><A href="http://www.ling.upenn.edu/courses/Fall_2003/ling001/penn_treebank_pos.html" target=_blank>http://www.ling.upenn.edu/courses/Fall_2003/ling001/penn_treebank_pos.html</A>):<BR><BR>27. VB Verb, base form<BR>28. VBD Verb, past tense<BR>29. VBG Verb, gerund or present participle<BR>30. VBN Verb, past participle<BR>31. VBP Verb, non-3rd person singular present<BR>32. VBZ Verb, 3rd person singular present<BR><BR>Hope this helps<BR>-Alex Yeh<BR><BR><BR><BR>><BR>> Thanks much for any help.<BR>><BR>> best,<BR>><BR>> Qi Li<BR>>
==========================<BR>> Department of Computer Sci.<BR>> Graduate Center, CUNY<BR>> Email: <A href="mailto:liqiearth@gmail.com" ymailto="mailto:liqiearth@gmail.com">liqiearth@gmail.com</A> <mailto:<A href="mailto:liqiearth@gmail.com" ymailto="mailto:liqiearth@gmail.com">liqiearth@gmail.com</A>><BR><BR><BR><BR>Qi<BR><BR>------------------------------<BR><BR>Message: 11<BR>Date: Wed, 29 Sep 2010 16:24:08 +0700<BR>From: "Yuri Tambovtsev" <<A href="mailto:yutamb@mail.ru" ymailto="mailto:yutamb@mail.ru">yutamb@mail.ru</A>><BR>Subject: [Corpora-List] Phonemic variations across languages<BR>To: <<A href="mailto:corpora@uib.no" ymailto="mailto:corpora@uib.no">corpora@uib.no</A>><BR><BR>Dear Corpora List members, do you use the coefficient of variation and Chi-square to study functioning of gerund, participle, phonemes or prepositions in language? In fact, the application of coefficient of variation and Chi-square to
investigate the variation of linguistic elements in language may stop endless debates about language variation problems because they can be sucessfully solved. I use the coefficient of variation and Chi-square all right. They proved quite useful. With their help I also studied variation of phomenes and groups of phonemes (labials, velars, sonorants, fricatives, etc.) across languages. Usually they were used to study the variation of phonemes in texts. I did that as well. I wonder if you read my publications? Who is researching in the same area? I call this area phonostatistical typology. We have also studied different texts of English, American, Russian and Ukrainian authors from the point of view of the use of different linguistic units. The results of the statistical study of the corpora were published by us. Looking forward to hearing from you soon to <A href="mailto:yutamb@mail.ru" ymailto="mailto:yutamb@mail.ru">yutamb@mail.ru</A> Yours sincerely
Yuri Tambovtsev, Novosibirsk, Russia<BR>-------------- next part --------------<BR>A non-text attachment was scrubbed...<BR>Name: not available<BR>Type: text/html<BR>Size: 1637 bytes<BR>Desc: not available<BR>URL: <<A href="http://www.uib.no/mailman/public/corpora/attachments/20100929/8c61f4d4/attachment.txt" target=_blank>http://www.uib.no/mailman/public/corpora/attachments/20100929/8c61f4d4/attachment.txt</A>><BR><BR>----------------------------------------------------------------------<BR>Send Corpora mailing list submissions to<BR> <A href="mailto:corpora@uib.no" ymailto="mailto:corpora@uib.no">corpora@uib.no</A><BR><BR>To subscribe or unsubscribe via the World Wide Web, visit<BR> <A href="http://mailman.uib.no/listinfo/corpora" target=_blank>http://mailman.uib.no/listinfo/corpora</A><BR>or, via email, send a message with subject or body 'help' to<BR> <A href="mailto:corpora-request@uib.no"
ymailto="mailto:corpora-request@uib.no">corpora-request@uib.no</A><BR><BR>You can reach the person managing the list at<BR> <A href="mailto:corpora-owner@uib.no" ymailto="mailto:corpora-owner@uib.no">corpora-owner@uib.no</A><BR><BR>When replying, please edit your Subject line so it is more specific<BR>than "Re: Contents of Corpora digest..."<BR><BR><BR>_______________________________________________<BR>Corpora mailing list<BR><A href="mailto:Corpora@uib.no" ymailto="mailto:Corpora@uib.no">Corpora@uib.no</A><BR><A href="http://mailman.uib.no/listinfo/corpora" target=_blank>http://mailman.uib.no/listinfo/corpora</A><BR><BR><BR>End of Corpora Digest, Vol 39, Issue 31<BR>***************************************<BR></DIV></DIV></div><br>
</body></html>