<\/p>\n
<\/p>\n
<\/p>\n
<\/p>\n
<\/p>\n
Abstract.<\/strong> While NLP systems become more pervasive, their accountability gains value as a focal point of effort. Epistemological opaqueness of nonlinear learning methods, such as deep learning models, can be a major drawback for their adoptions. In this paper, we discuss the application of Layerwise Relevance Propagation over a linguistically motivated neural architecture, the Kernel-based Deep Architecture, in order to trace back connections between linguistic properties of input instances and system decisions. Such connections then guide the construction of argumentations on network\u2019s inferences, i.e., explanations based on real examples, semantically related to the input. We propose here a methodology to evaluate the transparency and coherence of analogy-based explanations modeling an audit stage for the system. Quantitative analysis on two semantic tasks, i.e., question classification and semantic role labeling, show that the explanatory capabilities (native in KDAs) are effective and they pave the way to more complex argumentation methods.<\/p>\n <\/p>\n <\/p>\n <\/p>\n <\/p>\n <\/p>\n <\/p>\n Abstract.<\/strong> Artificial Intelligence may accelerate the fourth Industrial Revolution exploiting Human Knowledge stored in Personal Data. Will the job market and your future job survive this fourth Industrial Revolution?\u00a0All of us are invited to think about it.<\/p>\n Short cv.<\/strong> Fabio Massimo Zanzotto is Associate Professor at the Department of Enterprise Engineering of the University of Rome Tor Vergata. He has been working for more than 20 years in the Artificial Intelligence (AI) field and he is author of several publications in the area of Natural Language Processing (NLP), Machine Learning applied to NLP and to Medicine. Recently, he has realized how disruptive the impact of AI research can be. Consequently, he has redesigned his research agenda to help to contribute to a fairer AI.<\/p>\n <\/p>\n <\/p>\n <\/p>\n <\/p>\n Abstract. <\/strong>Today’s Web represents a huge repository of human knowledge, not only about facts, people, places and so on (encyclopedic knowledge), but also about everyday beliefs that average human beings are expected to hold (commonsense knowledge). Automated agents such as domestic robots and virtual assistants need to be equipped with this kind of knowledge in order to be autonomous in their functions. However, the majority of the commonsense knowledge on the Web is present in the form of natural language, rather than structured formats ready to be processed by machines. Semantic Parsing and Word Sense Disambiguation are two well-studied tasks in NLP that aim at extracting the structure and lexical semantics from natural language, respectively. During my appointment at Inria Sophia Antipolis on the EU project ALOOF (Autonomous Learning of the Meaning of Objects [1]), I worked on combining the two tasks in order to “read” a large quantity of text on the Web and collect many instances of structured grounded knowledge, under the common framework of Frame Semantics. After creating a corpus and parsing it with the pipeline we developed KNEWS (Knowledge Extraction With Semantics [2]), we use clustering techniques to filter out the noise and distill the most prototypical knowledge about common concepts, particularly objects, locations and actions. The final result is a Linked Data language-neutral dataset, subset of the commonsense knowledge base DeKO (Default Knowledge about Objects [3]).<\/p>\n [1] https:\/\/project.inria.fr\/aloof\/ Short bio. <\/strong>Valerio Basile is a postdoc researcher at University of Turin. During his PhD at the University of Groningen he worked on formal representations of meaning, including the construction of the Groningen Meaning Bank, a semantically annotated corpus of English; linguistic annotation and gamification, including the development of Wordrobe, an online Game With A Purpose for semantic annotation; natural language generation, particularly starting from logical formulas as abstract meaning representations. During a two-year postdoc at Inria Sophia Antipolis, France, he worked on commonsense knowledge base building, using machine reading and frame semantics, in the context of the European e ALOOF (Autonomous Learning of the Meaning of Objects). In parallel, his research interests included multilingual semantic parsing for the ERC project MOUSSE, and sentiment analysis, with the organization of the SENTIPOLC, ABSITA and SemEval Emoji classification shared tasks.<\/p>\n <\/p>\n \u00a0<\/strong><\/p>\n \u00a0<\/strong> \u00a0<\/em><\/strong><\/p>\n \u00a0<\/em><\/strong> \u00a0<\/em><\/strong> \u00a0<\/em><\/strong> \u00a0<\/em><\/strong><\/p>\n \u00a0<\/span><\/em><\/strong> ABSTRACT<\/span><\/em><\/strong>:<\/em><\/strong><\/p>\n Le slide del seminario possono essere scaricate da TokunagaTakenobu@TorVergata<\/a>.<\/p>\n short cv<\/span><\/em><\/strong><\/p>\n <\/p>\n \u00a0<\/em><\/strong> \u00a0<\/span><\/em><\/strong> \u00a0<\/span><\/em><\/strong> ABSTRACT<\/span><\/em><\/strong>: <\/em><\/strong> \u00a0<\/em><\/strong> In 2009, the Defense Advanced Research Projects Agency (DARPA) initiated what was intended to be a 5-year project (though in the end, it lasted only 3) aimed at exploring the principles behind the design and implementation (at least in prototype form) of systems that could take more-or-less arbitrary “factually informative” English text and understand it. I had the honor and privilege of being the Principal\u00a0 Investigator of the SRI-led team, one of three large teams in the Program.\u00a0 That privilege meant I didn’t really have to do any actual work, beyond (i) being ultimately responsible for the progress of the team and for reporting said progress to DARPA\u00a0 on, tracking budgets, etc., etc. and (ii) that honor mean I was free to think large-ish thoughts about how one should conceive of the goals of such a project and how to put our team’s approach, focused on large-scale joint inference, into a wider research context.\u00a0 I promise I will not talk about (i) in this seminar; so if you’ve read and understood this abstract, you should know what I will be talking about. \u00a0 \u00a0<\/em><\/strong> Short bio<\/span><\/em><\/strong>: <\/em><\/strong>Dr. Israel recently retired from the Artificial Intelligence Center at SRI, with the title of Principal Scientist (Emeritus). \u00a0Prior to his retirement, he worked in a number of areas in AI, including Knowledge Representation and Reasoning, Theory of (Rational) Action and various parts of Natural Language Processing, including Formal Semantics and the Theory and Design of Machine Reading systems. Le diapositive della presentazione possono essere scaricate da questo link<\/a>.<\/p>\n \u00a0<\/em><\/strong><\/p>\n SPEAKER:<\/em><\/strong>\u00a0<\/em><\/strong><\/p>\n Gruppo di Ricerca in Intelligenza Artificiale Univ. Tor Vergata<\/strong><\/p>\n Abstract. <\/strong>In recent years, machine learning (ML) has been more and more used to acquire effective models to solve complex tasks in different disciplines, ranging from Machine Vision to Information Retrieval (IR) or Natural Language Processing (NLP). Within this scenario, Kernels Methods provide a powerful paradigm for the automatic induction of models by characterizing similarity functions between data examples, either represented in continuous domains or over discrete structures, such as graphs and tree collections. Kernels are appealing as their application in Web Application allows adopting a Structured Learning paradigm where ML algorithms are directly applied to complex structures representing linguistic information, without the need of complex feature engineering. In this talk the adoption of Kernel Methods within state-of-the-art ML algorithms for Statistical Language Processing will be introduced, in order to show how to directly use discrete but complex structures within learning processes. Several linguistic tasks benefiting from the application of Kernel Methods will be discussed, such as Question Answering, Sentiment Analysis or Spoken Language Understanding in the context of Human Robot Interaction. Finally, some challenges for future research, e.g. issues of Scalability of kernel-based methods when applied in \u201cBig Data\u201d scenarios will be introduced. \u00a0 Short bio: <\/strong>Danilo Croce received Ph.D. in Informatics Engineering from the University of Roma Tor Vergata since 2012. Currently, he is an Assistant Professor at the Dept. of Enterprise Engineering, he is a member of the SAG@ART group at the same university. His expertise concerns theoretical and applied Machine Learning in the areas of Natural Language Processing, Information Retrieval and Data Mining. In particular, he is interested in innovative kernels within support vector and other kernel-based machines for advanced syntactic\/semantic processing. Author of more than 50 scientific publications, received a few best paper awards in international conferences. For more information, see http:\/\/sag.art.uniroma2.it\/people\/croce\/.<\/p>\n <\/p>\n <\/p>\n \u00a0<\/em><\/strong>SPEAKER:<\/em><\/strong><\/p>\n \u00a0IBM Italia, Center for Advanced Studies<\/strong><\/p>\n \u00a0<\/em><\/strong> \u00a0<\/em><\/strong> ABSTRACT<\/span><\/em><\/strong>: <\/em><\/strong> \u00a0<\/em><\/strong> I modelli concettuali con cui rappresentiamo le conoscenze nei sistemi informativi si fondano generalmente sull’apparato della logica dei predicati, in particolare i modelli basati su frazioni computabili della logica dei predicati del primo ordine, detti ontologie (‘discorsi su ci\u00f2 che esiste’). Cos\u00ec come per la logica, la natura dei predicati e della relazione di interpretazione che li lega ai loro oggetti non viene specificamente indagata. Invece, cos\u00ec come la semiotica ha individuato gi\u00e0 nell’800 diverse tipologie di segni, si possono scorgere facilmente, nelle moderne ontologie, diversi tipi di predicati e di interpretazioni. Bench\u00e9 la differenza tra concetti lessicali del linguaggio ordinario, i concetti formalizzati nelle teorie delle scienze naturali, quelli riferiti a normative, le categorie metafisiche, ecc. sia evidente, i formalismi e le metodologie alla base delle tecnologie informatiche non supportano n\u00e9 incoraggiano un trattamento consapevole di tali specificit\u00e0, pur se rilevante per molte applicazioni. Recuperare tali differenze implica guardare ai concetti delle ontologie (informatiche) non come simboli di predicato in attesa di una qualsivoglia interpretazione, ma come oggetti semiotici facenti parte di specifici processi di comunicazione.<\/strong><\/p>\n _ _ _<\/i><\/b><\/p>\n \u00a0<\/em><\/strong><\/p>\n SPEAKER:<\/em><\/strong><\/p>\n \u00a0DIAG, Universit\u00e0 La Sapienza, Roma<\/p>\n Luigia Carlucci Aiello, professore ordinario di Intelligenza Artificiale, dal 1982 \u00e8 alla Sapienza Universit\u00e0 di Roma, Dipartimento di Ingegneria Informatica, Automatica e Gestionale Antonio Ruberti (DIAG). Presiede il CCL e coordina il Dottorato in Ingegneria Informatica; dal 2006 al 2010 \u00e8 direttore del Dipartimento di Informatica e Sistemistica, ora DIAG; dal 2010 al 2013 presiede la Facolt\u00e0 di Ingegneria dell\u2019Informazione, Informatica e Statistica. Costituisce il gruppo di ricerca in Intelligenza Artificiale del DIS-DAG, e conduce ricerche in intelligenza artificiale (rappresentazione della conoscenza e ragionamento automatico) e sue applicazioni. Pi\u00f9 recentemente si occupa di robotica cognitiva. Fondatrice, primo presidente, ora socio onorario della Associazione Italiana per l’Intelligenza Artificiale. Fellow dell’AAAI e dell’ECCAI, presidente del Board of Trustees di IJCAI. Nel 2002 riceve un dottorato honoris causa dall\u2019Universit\u00e0 di Link\u00f6ping (Svezia). Nel 2009 riceve il \u201cDonald Walker Distinguished Service Award: for her substantial contributions and extensive service to the field of Artificial Intelligence throughout her career.\u201d Nel 2014 le viene conferito analogo premio da ECCAI.<\/p>\n_ _ _<\/i><\/b><\/h2>\n
AVVISO DI SEMINARIO<\/h2>\n
Hey, Merry Men!<\/i><\/b> Robin-Hood Artificial Intelligence is Calling You!<\/b><\/h1>\n
Mercoled\u00ec 4 Settembre, ore 14:00<\/em><\/h3>\n
Aula Archimede (Macroarea di Ingegneria)<\/strong><\/h3>\n
\u00a0SPEAKER:<\/h3>\n
Fabio Massimo Zanzotto
\n<\/strong><\/h2>\n(Universit\u00e0 degli Studi di Roma “Tor Vergata”)<\/h4>\n
_ _ _<\/i><\/b><\/h2>\n
AVVISO DI SEMINARIO<\/h2>\n
Semantic Parsing and Beyond to Create a\u00a0<\/strong>Commonsense Knowledge Base<\/strong><\/h1>\n
Mercoled\u00ec 11 Aprile, ore 14:00<\/em><\/h3>\n
Aula Archimede (Macroarea di Ingegneria)<\/strong><\/h3>\n
\u00a0SPEAKER:<\/h3>\n
Valerio Basile<\/strong><\/h2>\n
(Universit\u00e0 degli Studi di Torino)<\/h4>\n
\n[2] https:\/\/github.com\/valeriobasile\/learningbyreading
\n[3] http:\/\/deko.inria.fr\/<\/p>\n<\/h2>\n
_ _ _<\/i><\/b><\/h2>\n
AVVISO DI SEMINARIO<\/strong><\/h2>\n
Annotator behaviour mining for natural language processing<\/strong><\/h1>\n
Marted\u00ec 7 marzo 2017, ore 11.30<\/em><\/strong><\/h3>\n
Aula Archimede della Macroarea di Ingegneria<\/em><\/strong><\/h3>\n
SPEAKER:<\/em><\/strong><\/h3>\n
Tokunaga Takenobu<\/strong><\/h3>\n
School of Computing, Tokyo Institute of Technology<\/h3>\n
The last two decades witnessed a great success of revived empiricism in natural language processing (NLP) research. Namely, the corpus construction and machine learning (CC-ML) approach has been the main stream of NLP research, where corpora are annotated for a specific task and then they are used as training data for machine learning (ML) techniques to build a system for the task. From a viewpoint of annotation, this approach utilises only the results of annotation, i.e. annotated corpora. In this talk we will introduce our recent attempts that aims at utilising the information obtained during the annotation process as well as the annotation results. To be more concrete, we collect data of annotator behaviour during their corpus annotation and utilise it for improving NLP systems. We starts with the overview of our project followed by two studies in which annotator’s eye tracking data is utilised for the named entity recognised task and predicate argument structure analysis.<\/h4>\n
Takenobu Tokunaga is a professor at School of Computing, Tokyo Institute of Technology. He received his Ph.D. \u00a0from Tokyo Institute of Technology in 1991. His current interests include natural language processing, in particular, building and managing language resources, applications of language technologies to intelligent information access and education, and dialogue systems.<\/h4>\n
_ _ _<\/i><\/b><\/h2>\n
AVVISO DI SEMINARIO<\/strong><\/h2>\n
\u00a0<\/strong><\/h2>\n
Machine Reading: Central\u00a0 Goal(s) and Promising (?) Approaches<\/em><\/strong><\/h1>\n
\u00a0<\/em><\/strong><\/h1>\n
Luned\u00ec 14 dicembre 2015, ore 11.00<\/em><\/strong><\/h2>\n
Aula Archimede della Macroarea di Ingegneria<\/em><\/strong><\/h4>\n
\u00a0<\/em><\/strong><\/h2>\n
SPEAKER: <\/em><\/strong><\/h4>\n
\u00a0<\/em><\/strong><\/h2>\n
David Israel<\/em><\/strong><\/h1>\n
Artificial Intelligence Center at SRI<\/h2>\n
<\/h2>\n
\u00a0 _ _ _<\/i><\/b><\/h2>\n
\u00a0\u00a0<\/em><\/strong><\/h2>\n
AVVISO DI SEMINARIO<\/strong><\/h2>\n
\u00a0<\/strong>\u00a0<\/strong><\/h2>\n
Kernel Methods for Structured Learning<\/strong><\/h1>\n
in Statistical Language Processing<\/strong><\/h1>\n
Gioved\u00ec 22 Ottobre, ore 15:00<\/em><\/h2>\n
Aula \u201cArchimede\u201d<\/strong>\u00a0<\/em><\/strong><\/h2>\n
Danilo Croce<\/strong><\/em><\/h2>\n
_ _ _<\/i><\/b><\/h2>\n
La prospettiva semiotica nella modellazione concettuale<\/em><\/strong><\/h1>\n
Gioved\u00ec 21 maggio 2015, ore 11.00<\/em><\/strong><\/h2>\n
Aula Archimede della Macroarea di Ingegneria<\/em><\/strong><\/h2>\n
\u00a0<\/em><\/strong>Guido Vetere<\/em><\/strong><\/h2>\n
Breve cv<\/span><\/strong><\/h4>\n
Guido Vetere \u00e8 dirigente di ricerca presso IBM Italia, ed associato all’Istituto di Scienze e Tecnologie della Cognizione del CNR. E\u2019 in IBM dal 1988, dove ha svolto attivit\u00e0 di ricerca e sviluppo in vari ambiti dell’Intelligenza Artificiale e coordinato la partecipazione di IBM in progetti di ricerca europei. Dal 2005 \u00e8 direttore del Centro Studi Avanzati di IBM Italia, con sedi a Roma e Trento. Nel 2012 ha ricoperto il ruolo di coordinatore internazionale dei Centri Studi IBM. E’ autore di numerose pubblicazioni nel campo delle tecnologie semantiche e della linguistica computazionale. Collabora col Sole 24 Ore (N\u00f2va) alla divulgazione di temi legati alla societ\u00e0 dell’informazione e l’intelligenza artificiale. E\u2019 Presidente dell’associazione Senso Comune (www.sensocomune.it),\u00a0 per la costruzione di una base di conoscenza aperta della lingua italiana. \u00a0Attualmente, i sui interessi si rivolgono principalmente al rapporto tra lessico e ontologia, alla rappresentazione della conoscenza e il suo accesso attraverso il linguaggio naturale.<\/strong><\/h5>\n
Mercoled\u00ec 21 gennaio 2015, ore 10.30<\/em><\/strong><\/h2>\n
Aula Convegni della Macroarea di Ingegneria<\/em><\/strong><\/h2>\n
Luigia Carlucci Aiello<\/em><\/strong><\/h2>\n
L\u2019Intelligenza Artificiale \u00e8 morta,<\/strong><\/h1>\n
anzi, \u00e8 pi\u00f9 viva che mai<\/strong><\/h1>\n