ตามที่ได้เมล์มาจาก http://groups.google.com/group/thlta/browse_thread/thread/633acafdd560b738 มีบรรยายเรื่อง SMT ที่ CAS-ICT โดย Prof. Dr. LIU Qun วันนี้ก็ได้ไปฟังมาแล้ว ได้ความรู้มากกว่าที่คาดไว้อีก เรื่องแปลโดยใช้ Forest ผมโหลดไฟล์มาแล้ว แต่ยังไม่ได้อ่าน พอไปฟังแล้วก็จับประเด็นได้เลย ^_^

จัด 10 โมงเช้าเวลากำลังดีครับ แต่ก็อย่าที่ทราบกันว่า อุทยานวิทยาศาสตร์ ออกจะไกลสักหน่อย ผมก็เลยตื่นมาตั้งแต่ 6 โมงครึ่ง แล้วก็ไม่รู้ทำอะไรอยู่กว่าจะได้ออกจากบ้างก็ 8 โมง แต่ก็ไปทัน

ให้ดูว่าผมไปทันด้วย

ไม่นานนัก ดร.เทพชัย ก็เปิดงาน

เริ่มบรรยายแล้ว

ภาพของบนใช้โทรศัพท์มือถือถ่าย แต่ว่าสิ่งที่สนใจคือ มี Vauquois triangle บน slide ด้วย แต่ว่าเขียนมาเพื่อใช้อธิบาย SMT เวลานี้

Prof. Dr. LIU Qun แบ่งระดับการวิเคราะห์ที่ใช้ในการแปลเป็น 2 ระดับ คร่าวๆ คือ Phrase-based SMT และ Syntax-based SMT

Syntax-based SMT ยังแบ่งได้เป็น 2 ระดับย่อยๆ อีกคือ แบบที่ใช้ linguistic syntax กับ formal syntax แบบ linguistic syntax คือใช้ต้นไม้ที่อ้างอิงความรู้ทางภาษาศาสตร์ ส่วน formal syntax ก็ออกมาเป็น tree เหมือนกัน แต่ tree ที่สร้างไม่จำเป็นต้องเป็น tree ที่ถูกต้องตามหลักภาษาศาสตร์

SMT ที่แปลง tree แบบ linguistic syntax ไปเป็น อีกข้อความอีกภาษาเรียกว่า Tree-to-String SMT

ถ้าผมเข้าใจผิดก็ช่วยทักท้วงด้วยนะครับ

ตามธรรมเนียมก็มอบของที่ระลึกกันไป ขอโทษที่ไม่ชัดนะครับ

เสร็จงานแล้วผมก็นั่งรถเมล์ ปอ. 29 กลับมาจากธรรมศาสตร์ ศูนย์รังสิต ครับ 20 บาท ถ้วน ถูกกว่า 510 ขาไป 4 บาท ขากลับรถเมล์ก็มาจากจีนครับยี่ห้อ Sunlong

นอกจากเรื่องวิชาการแล้วแนวการทำงานวิจัย CAS-ICT ก็ดูเน้นทางวิทยาการคอมพิวเตอร์มากกว่าภาษาศาสตร์ ถ้าผมจำไม่ผิดที่นั่นมีนักศึกษาปริญญาเอก ประมาณ 10 คน ปริญญาโทอีกประมาณ 10 คน software engineer อีก 3 คน ไม่มีนักภาษาศาสตร์เลย แม้แต่คนเดียว ผมคิดว่าที่ทำแบบนี้ได้น่าจะเป็นเพราะภาษาจีนมีทรัพยากรณ์ทางภาษาเช่น คลังต้นไม้ (Treebank) และ คลังข้อความขนาน (Parallel corpus) มากพอ งานที่นักภาษาศาสตร์ก็อยู่ในคลังต้นไม้อยู่แล้ว

งานที่น่าสนใจอีกอย่าง เขาทำระบบแปลสิทธิบัตรด้วย ที่พิเศษคือผู้ใช้ สามารถสร้าง template ได้เอง template ก็คล้ายๆ กับเป็นกฎแบบหนึ่ง ลักษณะประมาณนี้

c1 c2 c3 $X c4 $Y c5 c6
e1 $Y e2 $X e3 e4

โดยที่ e1, e2, e3 … เป็นคำภาษาอังกฤษ และ c1, c2, c3 … เป็นคำภาษาจีน ส่วน $X และ $Y ก็เป็นตัวแปรที่จะเปลี่ยนไปได้เรื่อยๆ (ผมเขียนแบบนี้เพราะจำตัวอย่างชัดๆ ไม่ได้)

ทุกภาพในบันทึกนี้สามารถคลิกดูภาพใหญ่ได้ครับ ทุกภาพใช้สัญญาอนุญาตแบบ Attribution-Noncommercial-No Derivative Works 2.0 Generic (คร่าวแล้วก็คือเอาไปใช้ได้นั่นเองครับ ส่วนรายละเอียดสามารถตามลิงค์ไปอ่านได้)

Yorick Wilks 1939 an jaio zen. Adimen artifiziala irakasten du unibertsitatean. Lengua Naturalaren prozesamenduaren inguruan aritu da lanean. Yorick-ek Oxford eta Sheffield-eko unibertsitateetan lan egiten du.

Yorick Wilks-en lan garrantzitsuenetariko bat 70. hamarkadan egindako “Preference Semantics” izan da. Metodo algoritmiko bat da eta esaldi baten interpretazio koherenteena lortzeko aukera ematen du.

ERREFERENTZIAK

*Yorick Wilks (2009, urtarrilak 4). Wikipedia, Entziklopedia askea. Kontsultatua:uztailak 14, 2009 from: http://en.wikipedia.org/w/index.php?title=Yorick Wilks&oldid=261889889

*Lengoaia naturalen prozesamendua (2009, urtarrilak 28). Wikipedia, Entziklopedia askea. Kontsultatua: uztailak 14, 2009 from:  http://eu.wikipedia.org/w/index.php?title=Lengoaia_naturalen_prozesamendua&oldid=974697.

]]> http://1aicauso.wordpress.com/2009/07/14/parsing-eta-tagging/ Tue, 14 Jul 2009 11:43:12 +0000 Ainhoa Causo http://1aicauso.wordpress.com/2009/07/14/parsing-eta-tagging/

Parsing-a, sintaxiaren azterketa izenarekin ezagutzun duguna, informatika munduan erabiltzen den terminoa da. Alison Cawsey-ren arabera parsing-a oso garrantzitsua da programa informatikoen prozesamendurako,  programa informatiko guztiek azterketa bat behar duelako sintaktikoki zuzena den egiaztatzeko. Parsing-aren bidez token sekuentzia bat analizatu egiten da.

Horretaz gain, parsing-a beharrezkoa da lengoia naturalaren interpretaziorako.

Tag-a etiketa izenarekin ezagutzen dugu. Markaketa lengoaian esparru berezi bat zehazten du. zehaztapen prozesuari tagging deitzen diogu. Etiketa bat honako hau izan daiteke: <table>  –> taula bat txertatzeko adibidez.

ERREFERENTZIAK:

*Parsing (2009, apirilak 15). Wikipedia, Entziklopedia askea. Kontsultatua: uztailak 14, 2009 from: http://en.wikipedia.org/w/index.php?title=Parsing&oldid=283988668

*Etiqueta, lenguaje de marcado (2009, apirilak 4). Wikipedia, Entziklopedia askea. Kontsultatua: uztailak 14, 2009 from:  http://es.wikipedia.org/w/index.php?title=Etiqueta_(lenguaje_de_marcado)&oldid=25322664

*Tag HTML. W3C. Htmlquick. Kontsultatua: uztailak 14, 2009 from: http://www.htmlquick.com/es/reference/tags.html

*Alison Cawsey (1998, abuztuak 28). Parsing, String Processing Algorithms. Heriot Watt University.  Kontsultatua: uztailak 14, 2009 from: http://www.macs.hw.ac.uk/~alison/ds98/node70.html

]]> http://sircana.wordpress.com/2009/06/21/natural-language-interfaces/ Sun, 21 Jun 2009 21:34:37 +0000 Cristina http://sircana.wordpress.com/2009/06/21/natural-language-interfaces/

The communication betwen people that use a computer using natural language is a good idea. Despite, it’s very difficult t program a computer to chat across different domains, it’s much easier to program one to can understand comands in a restrictive environmnet. Before all this were known, it was marketed a spreadsheet  program that allowed people to communicate with the program using a natural language interface.

 Altought the intuitive appeal of a natural language interface,  some researches had said that some languages have a lot of ambiguities for be used to communicating with computers, but there is an experimental data suporting the efficacy of  a natural language interface, and some studies that have compared  natural language interfaces with other styles of interface.

This study compare the facility of learning a tradicional command/menu interface to a spreadsheet whit the simplicity  of  learning the natural language interface of Lotus HAL.

References:

•  Natural language interfaces. (March, 3, 2008)In Rice Virtual Lab. Retrieved: (June, 21, 2009).From http://www.ruf.rice.edu/~lane/case_studies/interface/index.html
• Natural language. (2009, June 9). In Wikipedia, The Free Encyclopedia. Retrieved 21:54, June 9, 2009, from http://en.wikipedia.org/w/index.php?title=Natural_language&oldid=295457792

Lengoaia naturalen prozesamendua (LNP, edo ingelesez, NLP – Natural Language Processing) adimen artifizialaren barne izanik, hizkuntzalaritza konputazionalean ingeniaritzari zuzendutako atala da. LNP lengoaia naturalen bidez pertsona eta makinen arteko komunikazioa era konputazionalean burutzea ikertzeaz arduratzen da. Eredu hauek ez dira lengoaiaren ulermenean bakarrik oinarritzen, baizik eta giza ezagutzaren aspektu orokor batzuetan eta memoriaren antolaketan ere.

Asko erabiltzen dira LNP teknikak Informazio Testualaren Berreskurapenaren arloan. Alde batetik dokumentuen edukiaren deskripzioa errazteko, eta beste aldetik, erabiltzailearen kontsultaren errepresentazioa egiteko. Modu honetan bi deskripzioak konparatu egiten dira eta erabiltzaileari gehien komeni zaiona aurkezten zaio.

Lengoai Naturala zer den hobeto ulertzeko, definizio hau eman genezake:

“Se denomina Lenguaje Natural a un lenguaje escrito o hablado usado por una comunidad que es precisamente lo contrario a un lenguaje para establecer comunicación con una computadora, mediante la entrada de datos, o la programación de su funcionamiento.” (Guzmán 1997).

Lengoaia Naturalaren ulermena eta ezagutza Adimen Artifizialaren arazo nagusienetakoak dira, giza hizketaren konplexutasunagatik, irregularitateagatik eta dibertsitateagatik; eta baita textu eta esaldien esanahiari lotutako arazo filosofiko eta psikologikoengatik.

Lengoai Naturalaren Prozesamenduak hainbat aplikazio ditu:

• Textu zuzenketa
• Itzulpengintza automatikoa.
• Informazioaren berreskurapena.
• Informazio eta Laburpen ateratzea.
• Dokumentuen Bilaketa.
• Entrenamendu eta Hezkuntzarako Sistema Inteligenteak.

Erreferentziak:

• “Procesamiento del lenguaje natural en la Inteligencia Artificial” (1998). Monografías.com.SA. 2009ko ekainak 21, 21:09. Orrialdea:http://www.monografias.com/trabajos17/lenguaje-natural/lenguaje-natural.shtml

• Adolfo Guzmán-Arenas. Hallando los temas principales en un artículo en español. Soluciones Avanzadas. Vol. 5, No. 45, p. 58, No. 49, p. 66, 1997. 2009ko ekainak 21, 21:12. Orrialdea: http://www.monografias.com/trabajos17/lenguaje-natural/lenguaje-natural.shtml

• Procesamiento de lenguajes naturales. (2009, 8  de abril). Wikipedia, La enciclopedia libre. Fecha de consulta: 19:11, junio 21, 2009 from http://es.wikipedia.org/w/index.php?title=Procesamiento_de_lenguajes_naturales&oldid=25434058.

        Question Answering (QA) system is a way of information retrieval by means of computing. It requires more complex natural language processing (NLP) techniques than other types of information retrieval such as information extraction.

        In the 1960s the first two QA systems were developped: LUNAR (it answered questions about the geological analysis of rocks returned by the Apollo moon missions) and BASEBALL (it answered questions about the US baseball league).

        A posed question in natural language (easily understandable) is answered by a machine. It retrieves the information in two different ways:

- By looking it up in a pre-structured database that lies inside it or a collection of articles that are also inside the system.

- By searching in a very open web, like the world wide web.

        The posed questions can belong to an open-domain (can refer to nearly everything) or to a closed-domain (refer to a specific subject, such as medicine or flowers, for example). The system looks for the answer by analysing the words of the question (key-word based techniques); but in some cases this way of finding the correct answer is not enough, and here different and complicated methods will be used: These techniques might include named-entity recognition, relation detection, coreference resolution, syntactic alternations, word sense disambiguation, logic form transformation, logical inferences (abduction) and commonsense reasoning, temporal or spatial reasoning…

          Ryan McCabe (University of Massachusetts, Amherst) and M. Chase Smith (Amherst College) have created a Question Answer web page, that explains the techniques used, its history, and  so much interesting information about QA.

       Some interesting QA systems are the ones that follow:

• Answers.com : it is a well-known open-domain QA system
• Ask.com: when a question is posed, this QA system redirects you to several pages that contain some of the items you asked on, so it works as a searcher more than as an advanced QA page.
• Semote: it also redirects the answerer to some different issues found on the internet when a question is posed, but the results are very accurated.
• Qualim: works the same way as Semote.
• Anna (in IKEA): it is a closed-domain QA that brings the answerer to the correct section, where what he/she needs can be found.

REFERENCES

- Question answering. (2009, June 13). In Wikipedia, The Free Encyclopedia. Retrieved 19:00, June 21, 2009, from http://en.wikipedia.org/w/index.php?title=Question_answering&oldid=296213100

- Question Answering. By Ryan McCabe (University of Massachusetts, Amherst) and M. Chase Smith (Amherst College). Retrieved 19:11, June 21, 2009, from http://ciir.cs.umass.edu/REU/2000/REUpres/QAFinal_files/frame.htm

- Learning surface text patterns for a Question Answering system (2001). Written by Deepak Ravichandran (University of Southern California, Marina del Rey, CA) and Eduard Hovy (University of Southern California, Marina del Rey, CA. Retrieved 20:22, June 21, 2009, from http://portal.acm.org/citation.cfm?id=1073092

- The TREC-8 question answering track report. By Ellen M. Voorhees (National Institute of Standards and Technology, Gaithersburg). Retrieved 20:36, June 21, 209, from http://66.102.1.104/scholar?hl=es&lr=&q=cache:eGBdGvbpDh4J:citeseerx.ist.psu.edu/viewdoc/download%3Fdoi%3D10.1.1.38.6392%26rep%3Drep1%26type%3Dpdf+question+answering

We place question answering in information retrieval. It automatically answers a question posed in natural language using a pre-structured database or a collection of natural language documents like the World Wide Web.

Question Answering has been very popular recently, but not in the multilingual research: It has been focused mainly on English. Multilingual QA has been created in the last few years as a complement, allowing users to interact with machines in their native languages to make the searching easier and faster. Also it makes the QA systems able to access information available only in one language.

Some relevant Question Answering engines are AskMeNow, BrainBoost, DeeperWeb, TeLQAS, True Knowledge and Wolfram Alpha.

Sources:

• Question answering. (2009, June 13). In Wikipedia, The Free Encyclopedia. Retrieved 14:02, June 21, 2009, from http://en.wikipedia.org/w/index.php?title=Question_answering&oldid=296213100

• Question answering. (2009). In the 11th Conference of the European Chapter of the Association for Computational Linguistics (EACL) website. Retrieved 14:11, June 21, 2009, from nlp.uned.es/MLQA06/

• Question answering. (2009). In the Text Retrieval Conference (TREC) website. Retrieved 14:09, June 21, 2009, from trec.nist.gov/pubs/trec9/papers/webclopedia.pdf

 Galderei Erantzutea (ingelesez Question Answering) informazioa berreskuratzeko mota bat da. Lengoaia Naturalaren Prozesamendua behar duen teknologia da, baina beste dokumentu-berreskurapen sistema batzuk baino konplexuagoa. Sistema honek hainbat galdera mota aztertzen saiatzen da: listak, definizioak, nola, non, noiz, zergatik, etab. barneratuz. Bilaketa hauek aldatu daitezke dokumentu lokalen kolekzio txiki batetik, web guztira.

Lehenengo Galdera Erantzun-Sistemak 1960.hamarkadan hasi ziren hedatzen. Baina gaur egungokoak testu-dokumentuak erabiltzen dituzte ezagutzaren oinarri bezala, eta Lengoaia Naturalaren Prozesamenduaren teknika desberdinak konbinatzen dituzte.

Beraien funtzionamendua azalduko dut orain. Gaur egungo sistemak galdera-klasifikazio bat daukate, eta honek zein galdera-mota den eta beraren erantzuna determinatzen saiatzen da. Ostean, dokumentu-berreskurapen nodulu bat aplikatzen da, eta honek galderaren erantzuna edukiko duen dokumentuan bilatzaileak ezartzen ditu dokumentu eta paragrafo konkretuak aurkitzeko.

Eta azkenean, testu zati txikiak aukeratuko dituen filtro bat ezartzen da. Adibidez, galdera hau bilatu nahi badugu (Zein da Bizkaiko hiriburua?), filtroak hiriburuak eta kapitalak dituzten testuak bilatuko ditu.

 Erreferentziak:

• Búsqueda de respuestas. ( 2009, 12 ) de junio. Wikipedia, La enciclopedia libre. 2009ko ekainaren 20, 18:14an kontsultatua. Orrialdea: http://es.wikipedia.org/w/index.php?title=B%C3%BAsqueda_de_respuestas&oldid=27183159.
• Web. (2009, 8 ) de junio. Wikipedia, La enciclopedia libre. 2009ko ekainarem 20, 18:28an kontsultatua. Orrialdea: http://es.wikipedia.org/w/index.php?title=Web&oldid=27073062.

Machine Translation is a sub-field of computational linguistics. It investigates computer software used to translate texts from one language into another. It can perform in two levels. At its basic level Machine Translation, makes a simple substitution of words. It also can use corpus techniques to attempt more complex translations.

Current machine translation software often allows for customization by domain or profession (such as weather reports . This technique is very effective when using the language of formulas. It follows then that machine translation of government and legal documents more readily produces usable output than conversation or less standardized text.

The improved quality of results can be achieved by human intervention. Some systems more accurately reflected if the user identifies the words of the text as names. With these techniques, the MT is useful for working with people who translate texts.

REFERENCES

Machine translation Wikipedia, the free encyclopedia. Retrieved 17 June 2009. From http://en.wikipedia.org/wiki/Machine_translation

There are other research topics apart from Speaker Recognition and Computational Semantics. One that I think is really interesting is Machine Translation. This term has its origin in the 17th century when René Descartes (French philosopher, mathematician…) proposed a universal language. He wanted that the same ideas in different languages had the same symbol.

In these times, Machine Translation or MT is a field of computational linguistics that investigate how to translate text or speech from one natural language to another using computer software. It has to be said that the invention is extremely useful in areas where formal language is used such as legal or administrative documents. Nevertheless, when it is a colloquial or familiar text, the machine normally makes lots of mistakes because it translates the text word by word. We can see an example in the following picture.

Many computer scientists, linguists… have tried to improve this machine with more or less success. We could mention Hans Uszkoreit who I have talked about in a previous article. He worked in a machine translation project while he was staying at Austin. Moreover, there have being carried out several projects all over the world. For example, one in the National Centre for Language Technology in Ireland or the Norwegian-English Machine Translation in Norway.

References:

• Machine translation (2009, June, 12) In Wikipedia, The Free Encyclopedia. Retrieved: 17:00, June 20, 2009, from http://en.wikipedia.org/wiki/Machine_translation
• Logon Norwegian-English Machine Translation (2007, November, 30). Retrieved: 18:34, June 20, 2009, from http://www.emmtee.net/
• NCLT Research Groups (2009, April, 15) In National Centre for Language Technology. Retrieved: 9:50, June 19, 2009, from http://www.nclt.dcu.ie/

Nowadays, computer scientists are concerned about many topics. However, there are some issues which are more discussed. Computational Semantics has a great importance and there have been done lots of projects in this field. But what does Computational Semantics mean? Well, first of all, it has to be said that to understand it you have to know terms like semantics, linguistics, natural language … Wikipedia defines it like this:

“Computational Semantics is the study of how to automate the process of constructing and reasoning with meaning representations of natural language expressions. It consequently plays an important role in natural language processing and computational linguistics.”

In other words, the aim of this multidisciplinary field is to find techniques to write automatically semantic representations for expressions of human language. Indeed, we will be able to perform inference thanks to these representations.

Another important research topic is Speaker Recognition, this happens when the computer tries to recognize who is speaking. Mainly, it uses the features of speech that everybody has different like anatomy (size of the mouth, shape of the throat…) and learned behavioural patterns (speaking style, voice pitch…). It is similar to Speech Recognition. Nevertheless, it has nothing to do with that. Speech Recognition is the fact of recognizing what is being said.

Finally, I would like to say that one particularly project sticks in my mind with regard to speaker recognition. The name of the project is Secure Access Front-End and scientists are trying to improve the services access security without increasing the service complexity.

References:                                                                                                

• Computational Semantics (2009, March, 9) In Wikipedia, The Free Encyclopedia. Retrieved: 9:00, June, 19, from http://en.wikipedia.org/wiki/Computational_semantics
• Computational Semantics Patrick Blackburn, Johan Bos. In The University of Edinburgh School of Informatics. Retrieved: 10:15, June, 19, from http://www.inf.ed.ac.uk/
• Speaker Recognition (2009, June, 12) In Wikipedia, The Free Encyclopedia. Retrieved: 23:10, June, 19, from http://en.wikipedia.org/wiki/Voice_recognition
• Projects (2009, June, 9) In Language Technology World. Retrieved: 23:20, June 19, from http://www.lt-world.org/

Itzulpengintza automatikoaren helburua hizkuntza natural batean egiten diren galderei  automatikoki erantzutea da.

Horretarako datu aurre base bat erabili daiteke, edota, hizkuntza naturalen dokumentu bilketa bat, World Wide Web-en antzera. Galdetutako galderak bi motatakoak izan daitezke: bai dominio galderak edota dominio galdera irekiak. Lehenengoei dagokienez, erantzuteko errezenak bezala kontsideratuta daude, izan ere, interneten erraz bilatzen den gai baten ingurukoak dira. Bestalde, dominio galdera irekiak erantzuteko zailagoak dira erantzunak munduaren jakiturian oinarritzen direlako.

Inbertitutako diruaz gain, galderei erantzuteko erabilitako sistemak “Powerset” edo “Assimov the chatbot” oraindik ere lan gehiago egiteko dagoela adierazten dute, izan ere, galdera asko zehaztasun osoz  ezin izan direlako erantzunak izan.

Iturriak:

• Question Answering Engine (2009). In Answers.com. Kontsultatua:23:10, ekainak 12, 2009. Orrialdea: http://www.answers.com/bb/
• Búsqueda de respuestas (2009, maiatzak 10). Wikipedia, Entziklopedia askea. Kontsultatua: 23:12, ekainak 12, 2009. Orrialdea:  http://es.wikipedia.org/w/index.php?title=B%C3%BAsqueda_de_respuestas&oldid=26219643

Lehendik ere hitz egin izan dut nire artikuluetako batean itzulpen makinei buruz, baina oraingoan adibide sail bat  emango dut guztiok erabil ditzazuen.

Gaur egun sistema aunitz ditugu itzulpenak egiteko, eta guztiz zehatza izan ezean, baliagarriak diren itzulpenak lor daitezke, dokumentazio tekniko arloan behintzat. Gainera, software paketeak, zeintzuk printzipalki diseinatuta dauden itzulpenen produkzioan giza itzultzailearen laguntzeko, geroz eta harrakasta handiagoa lortzen ari dira itzulpen profesionalen erakundeen barruan.

Hona hemen adibide batzuk:

• Lucy, http://www.translendium.net:8080/home/
• Google, http://www.transledium.com
• Open Trad,http://www.opentrad.org/demo
• Reverso Traductor, http://www.reverso.net/text_translation.asp?lang=ES
• ProMT, http://elmundo.reverso.net/textonly/default.asp

Iturriak:

• Machine translation. (2009, March 26). Wikipedia, Entziklopedia askea. Kontsultatua 16:18,ekainak 9 , 2009, orrialdea http://en.wikipedia.org/w/index.php?title=Machine_translation&oldid=279707378

Hans Uszkoreit was born in Rostock (Germany) the 23th January 1950. Nowadays, he has his residence in Saarbruecken and Berlin.

He studied Linguistics and Computer Science at the Technical University of Berlin and the University of Texas at Austin. While he was studying in Austin, he also worked as a research associate in a large machine translation project at the Linguistics Research Center.

Furthermore, after he received his Ph.D. in Linguistics from the University of Texas, he worked as a computer scientist at the Artificial Intelligence Center and he was affiliated with the Center for the Study of Language and Information at Stanford University.

At present, he is teaching as a professor of Computational Linguistics at Saarland University. Moreover, he serves as a Scientific Director at the German Research Center for Artificial Intelligence (DFKI) where he heads the DFKI Language Technology Lab.

SOURCES:

• Hans Uszkoreit. (2009, June 14). In Wikipedia, The Free Encyclopedia. Retrieved 22:02, June 14, 2009, from http://en.wikipedia.org/w/index.php?title=Hans_Uszkoreit&oldid=296429295
• Hans Uszkoreit C.V. (2009). In Saarland University. Retrieved 12:14, June 13, 2009, from http://www.coli.uni-saarland.de/~hansu/bio.html

INFORMATION EXTRACTION

- Named Entity Recognition (NER)

INFORMATION RETRIEVAL

- Clustering

LANGUAGE ANALYSIS

- Parsing

LANGUAGE UNDERSTANDING

- Pragmatics

KNOWLEDGE REPRESENTATION AND DISCOVERY

- Semantic web

SPOKEN LANGUAGE INPUT

- Speech recognition

MULTIMODALITY

- Modality integration: Facial movement, Representations of Space and Time, and Speech.

MULTILINGUALITY

- Machine Translation

- Machine-Aided Human Translation

REFERENCES

-Named Entity Recognition. (2009, March 25). In Wikipedia, The Free Encyclopedia. Retrieved 11:10, March 25, 2009, from http://en.wikipedia.org/w/index.php?title=Named_entity_recognition&oldid=279521544

-Colaboradores de Wikipedia. Cluster (informática) [en línea]. Wikipedia, La enciclopedia libre, 2009 [fecha de consulta: 18 de marzo del 2009]. Disponible en <http://es.wikipedia.org/w/index.php?title=Cluster_(inform%C3%A1tica)&oldid=24900365>.

-Cluster (computing). (2009, March 20). In Wikipedia, The Free Encyclopedia. Retrieved 11:14, March 25, 2009, from http://en.wikipedia.org/w/index.php?title=Cluster_(computing)&oldid=278511256

- Parsing. (2009, March 11). In Wikipedia, The Free Encyclopedia. Retrieved 11:18, March 25, 2009, from http://en.wikipedia.org/w/index.php?title=Parsing&oldid=276620765

- Pragmatics. (2009, March 20). In Wikipedia, The Free Encyclopedia. Retrieved 11:25, March 25, 2009, from http://en.wikipedia.org/w/index.php?title=Pragmatics&oldid=278540321

- Semantic Web. (2009, March 20). In Wikipedia, The Free Encyclopedia. Retrieved 11:31, March 25, 2009, from http://en.wikipedia.org/w/index.php?title=Semantic_Web&oldid=278574575

- Speech recognition. (2009, March 19). In Wikipedia, The Free Encyclopedia. Retrieved 11:39, March 25, 2009, from http://en.wikipedia.org/w/index.php?title=Speech_recognition&oldid=278372461

- Machine translation. (2009, March 23). In Wikipedia, The Free Encyclopedia. Retrieved 11:43, March 25, 2009, from http://en.wikipedia.org/w/index.php?title=Machine_translation&oldid=295950237

- Computer-assisted translation. (2009, March 19). In Wikipedia, The Free Encyclopedia. Retrieved 11:54, March 25, 2009, from http://en.wikipedia.org/w/index.php?title=Computer-assisted_translation&oldid=294759999