2023 02.22
03/03【AI x Future AI趨勢論壇】AI如何協助人類克服舌尖現象問題
我們很榮幸邀請到了法國國家科學研究中心榮譽主任— Michael Zock 於 3/3(五)前來成大演講!
【主講人】Michael Zock
【講題】Finding the needle in a haystack, or how to help authors to overcome the Tip-Of-the-Tongue-Problem?
【時間】3/3 星期五 10:30-12:00
【演講報名連結】請於 3 月 1 日(含)前於此連結報名

One of the most vexing problems in speaking or writing is failing to access a particular word even though it is clearly stored in the user's brain. This kind of search failure known as dysnomia or Tip of the Tongue-problem (TOT),1 occurs not only in language, but also in other activities of everyday life. It is basically a search- and index-problem which we are reminded of when we look for something that exists in real world or in our mind (keys, glasses, people's names), but which we are unable to locate, access or retrieve in time.
Word finding problems are generally dealt with via a lexicon. Our concern here is language production, a task still too much neglected in lexicographical work. When speaking or writing, authors typically start from meanings (set of concepts). This is the normal route and it works in most cases, yet sometimes it does not, in which case we may resort to alternative strategies: we start from a word in a foreign language (translation), we perform topic-based search (thesaurus), or we rely on associations, i.e. lexical (synonyms, antonyms, ...) or conceptual relations. These latter two strategies are illustrated via lexical graphs — (for example, WordNet, JeuxDeMots, BabelNet, etc.) — which are very precious resources. Yet, given their size and complexity (multidimensional space) they also pose certain problems. Hence, in order to be truly useful for authors (allowing them to stay on top of the data, i.e. words), care must be taken to minimize noise (drowning the user with irrelevant data) and to set sign-posts, i.e. lables or orientational clues, as otherwise the user does not know which direction to go: every node (word) having a great number of outgoing links and nodes (associated terms). These just mentioned problems arise whenever a word is connected to a large number of words (or associated terms), which is usually the case, and whenever the target word is not an immediate neighbor of the query- or source-word (a quite frequent case). I will sketch a framework allowing to integrate and situate all this work. In particular, I will try to answer the question whether the mental lexicon can be used as a blueprint for the dictionaries of tomorrow.

Michael Zock is emeritus research director at the CNRS and Honorary Professor of the Research Institute of Information and Language Processing (university of Wolverhampton, UK). Starting his research career in the eighties at LIMSI, an A.I. lab close to Paris, he joined 2006 the NLP group of LIF (now LIS-lab) at the university of Aix-Marseille. He has published extensively in the area of computational linguistics or cognitive science (more than 250 international publications in books, magazines or conferences), and he has edited several books and special issues on Natural Language Generation, lexical resources, electronic dictionaries and Computer Assisted Language Learning. The focus of his recent research has been on outline planning (reveal automatically possible links between ideas to help authors to produce coherent discourse), lexical access (help authors to find an elusive word by taking into account certain features of the mental lexicon), and the acquisition of basic speaking skills: help students to become quickly fluent in a foreign language by learning the basic vocabulary and syntactic structures (learn words in context).
He served as evaluator for various national and international organisations like the National Science Foundation (NSF, Washington), the East-Asian (Japan, China)- and the european community (INCOCOPERNICUS, SNF, Switzerland, ANR, France). Being evaluator or PC member of the major conferences of computational linguistics he has reviewed more than 400 papers, book chapters or project proposals. He has been invited as a keynote speaker, or as lecturer to give tutorials at international conferences in psychology, computational linguistics (COLING, LREC, NLPRS, RANLP, ESSLLI) and artificial intelligence (AI & Education, IJCAI, 2018). He has been actively involved in COLING as author (1986, 1988, 1992, 1996, 2002, 2004, 2006, 2008, 2010, 2012), lecturer (tutorial on ‘language generation’, Tokyo, 1994), panelist (1994, 2010), organizer (panel:1996; workshops: 2004, 2008, 2010, 2012, 2014, 2016, 2020), and program committee member (1994, Kyoto).