Event Information

Last updated 103 days ago by George Giannakopoulos (Admin)

Categories: events

Invited Talk

Enrique Alfonseca is a Staff Research Scientist at Google Research Europe, where
he manages a team working on language understanding. Over the past ten years, he 
has worked at Google in ads quality, search quality and natural language processing,
with a current focus on conversational search.
Abstract: In this talk, I will discuss some of the challenges that conversational search 
faces in providing information to users. Some of them stem from the fact that many
questions are answered with snippets from the web, which may not be the most
appropriate to be inserted inside conversations. Secondly, I will describe in more 
detail the sentence compression and summarization approaches that are running 
in production in Google Home for improving the user experience around question
Accepted papers and Proposed Schedule
April 3rd, 2017
09:30 - 11:00    Opening and Invited talk
09:30 - 09:45    MultiLing 2017 Welcome
George Giannakopoulos
09:45 - 11:00    Invited talk: Sentence Compression for Conversational Search
Enrique Alfonseca, Google
11:00 - 11:30    Coffee break
11:30 - 13:00    MultiLing Tasks and Systems I
Chair: John Conroy, IDA
Co-Chair: Elena Lloret, Univ. of Alicante
11:30 - 11:50    MultiLing 2017 Overview
George Giannakopoulos1, John Conroy2, Jeff Kubina3, Peter A. Rankel4, Elena Lloret5, Josef Steinberger6, Marina Litvak7, Benoit Favre8
1NCSR Demokritos & SciFY NPC, 2IDA Center for Computing Sciences, 3U.S. Department of Defense, 4University of Maryland, 5University of Alicante, 6University of West Bohemia, 7Shamoon College of Engineering, 8Aix-Marseille University LIF/CNRS
11:50 - 12:10    Decoupling Encoder and Decoder Networks for Abstractive Document Summarization
Ying Xu1, Jey Han Lau2, Timothy Baldwin3, Trevor Cohn4
1Monash University, IBM Research, 2IBM Research, 3The University of Melbourne, 4University of Melbourne
12:10 - 12:30    Centroid-based Text Summarization through Compositionality of Word Embeddings
Gaetano Rossiello1, Pierpaolo Basile2, Giovanni Semeraro1
1University of Bari "Aldo Moro", 2Department of Computer Science, University of Bari Aldo Moro
12:30 - 12:50    Query-based summarization using MDL principle
Marina Litvak and Natalia Vanetik
Shamoon College of Engineering
14:30 - 16:00    MultiLing Tasks and Systems II
Chair: Marina Litvak, Shamoon College of Engineering
Co-Chair: Josef Steinberger, Univ. of West Bohemia
14:30 - 14:50    Multilingual Single Document Summarization Overview
John Conroy
14:50 - 15:10    Word Embedding and Topic Modeling Enhanced Multiple Features for Content Linking and Argument / Sentiment Labeling in Online Forums
Lei Li, Liyuan Mao, Moye Chen
Beijing University of Posts and Telecommunications
15:10 - 15:30    Ultra-Concise Multi-genre Summarisation of Web2.0: towards Intelligent Content Generation
Elena Lloret1, Ester Boldrini2, Patricio Martinez-Barco3, Manuel Palomar1
1University of Alicante, 2University of Alicante, GPLSI Research Group, 3Universidad de Alicante
15:30 - 15:50    Machine Learning Approach to Evaluate MultiLingual Summaries
Samira Ellouze1, Maher Jaoua2, Lamia Hadrich Belguith2
1ANLP Group, MIRACL Laboratory, University of Sfax, Tunisia, 2ANLP Group, MIRACL Laboratory, University of Sfax
16:00 - 16:30    Coffee break and poster setup
16:30 - 18:00    Poster session and Closing
16:30 - 17:30    Poster session
17:30 - 18:00    Closing remarks and planning