Massimiliano Ciaramita

Google Research


Massimiliano Ciaramita is a research scientist at Google Zurich. Previously he has worked as a researcher at Yahoo! Research and the Italian National Research Council. He did his undergraduate studies at the University of Rome "La Sapienza" and obtained ScM and PhD degrees from Brown University. His main research interests involve language understanding and its applications to search technologies.
He has worked on a wide range of topics in natural language processing and information retrieval, including disambiguation, acquisition, information extraction, syntactic and semantic parsing, query analysis, computational advertising and question answering.
He co-teaches (with Enrique Alfonseca) "Introduction to Natural Language Processing" at ETH Zurich.

Invited talk: Distributed Wikipedia LDA

When someone mentions Mercury, are they talking about the planet, the god, the car, the element, Freddie, or one of some 89 other possibilities? This problem is called disambiguation, and while it’s necessary for communication, and humans are amazingly good at it, computers need help. Automatic disambiguation is a long standing problem and is the focus of much recent work in natural language processing, web search and data mining. The surge in interest is due primarily to the availability of large scale knowledge bases such as Wikipedia and Freebase which offer enough coverage and structured information to support algorithmic solutions and web-scale applications. In this talk I will present recent work on the disambiguation problem based on a novel distributed inference and representation framework that builds on Wikipedia, Latent Dirichlet Allocation and pipelines of MapReduce.

Rada Mihalcea

Associate Professor of Computer Science
Dept. of Computer Science and Engineering
University of North Texas


Rada Mihalcea is an Associate Professor in the Department of Computer Science and Engineering at the University of North Texas. Her research interests are in computational linguistics, with a focus on lexical semantics, graph-based algorithms for natural language processing, and multilingual natural language processing. She serves or has served on the editorial boards of the Journals of Computational Linguistics, Language Resources and Evaluations, Natural Language Engineering, Research in Language in Computation, IEEE Transations on Affective Computing, and Transactions of the Association for Computational Linguistics. She was a program co-chair for the Conference of the Association for Computational Linguistics (2011), and the Conference on Empirical Methods in Natural Language Processing (2009). She is the recipient of a National Science Foundation CAREER award (2008) and a Presidential Early Career Award for Scientists and Engineers (2009).

Invited talk: Multimodal Sentiment Analysis

During real-life interactions, people are naturally gesturing and modulating their voice to emphasize specific points or to express their emotions. With the recent growth of social websites such as YouTube, Facebook, and Amazon, video reviews are emerging as a new source of multimodal and natural opinions that has been left almost untapped by automatic opinion analysis techniques. One crucial challenge for the coming decade is to be able to harvest relevant information from this constant flow of multimodal data. In this talk, I will introduce the task of multimodal sentiment analysis, and present a method that integrates linguistic, audio, and visual features for the purpose of identifying sentiment in online videos. I will first describe a novel dataset consisting of videos collected from the social media website YouTube and annotated for sentiment polarity at both video and utterance level. I will then show, through comparative experiments, that the joint use of visual, audio, and textual features greatly improves over the use of only one modality at a time. Finally, by running evaluations on datasets in English and Spanish, I will show that the method is portable and works equally well when applied to different languages.

Hans Uszkoreit

Saarbrücken and Berlin, Germany
Professor at Saarland University
Scientific Director at the German Research Center for Artificial Intelligence (DFKI)


Hans Uszkoreit is Professor of Computational Linguistics and–by cooptation–of Computer Science at Saarland University. At the same time he serves as Scientific Director at the German Research Center for Artificial Intelligence (DFKI) where he heads the DFKI Language Technology Lab. He has more than 30 years of experience in language technology which are documented in more than 180 international publications. Uszkoreit is Coordinator of the European Network of Excellence META-NET with 60 research centers in 34 countries and he leads several national and international research projects. His current research interests are information extraction, atomatic translation and other advanced applications of language and knowledge technologies as well as computer models of human language understanding and production.

Invited talk: Big Data and Text Analytics

Text analytics is faced with rapidly increasing volumes of language data. In our talk we will show that big language data are not only a challenge for language technology but also an opportunity for obtaining application-specific language models that can cope with the long tail of linguistic creativity. Such models range from statistical models to large rule systems. Using examples from relation/event extraction we will illustrate the exploitation of large-scale learning data for the acquisition of application specific syntactic and semantic knowledge and discuss the achieved improvements of recall and precision.


Karte Nuance lingenio DFKI MultilingualWeb DIPF EML Linguistik - Portal für Sprachwissenschaft
A A A | Drucken Print | Impressum Impressum | Sitemap Sitemap | Kontakt Contact
zum Seitenanfangzum Seitenanfang