Translating from Multiple Modalities to Text and Back
Professor Mirella Lapata leads this year’s Karen Spärck Jones lecture.
This lecture is sponsored by IBM.
SPEAKERS
Introductory speaker - Dr Petrena Prince, Global University Programs Europe Leader, IBM
Headline Speaker - Professor Mirella Lapata, University of Edinburgh
Vote of Thanks - Professor Carron Shankland, Computing Science and Mathematics, University of Stirling
------------------------------------------------------------------------------------
AGENDA
17:30-18:00 - Registration with tea/coffee
18:00 - Lecture commences
19:30 - End of lecture
19:30-20:30 - Networking and refreshments
20:30 - Close
------------------------------------------------------------------------------------
SYNOPSIS
Recent years have witnessed the development of a wide range of computational tools that process and generate natural language text. Many of these have become familiar to mainstream computer users in the from of web search, question answering, sentiment analysis, and notably machine translation. The accessibility of the web could be further enhanced with applications that not only translate between different languages (e.g., from English to French) but also within the same language, between different modalities, or different data formats. The web is rife with non-linguistic data (e.g., video, images, source code) that cannot be indexed or searched since most retrieval tools operate over textual data.
In this talk I will argue that in order to render electronic data more accessible to individuals and computers alike, new types of translation models need to be developed. I will focus on three examples, text simplification, source code generation, and movie summarization. I will illustrate how recent advances in deep learning can be extended in order to induce general representations for different modalities and learn how to translate between these and natural language.
------------------------------------------------------------------------------------
SPEAKER BIOGRAPHY
Headline Speaker: Professor Mirella Lapata
Mirella Lapata is professor of natural language processing in the School of Informatics at the University of Edinburgh. Her research focuses on getting computers to understand, reason with, and generate natural language. She is the first recipient (2009) of the BCS and Information Retrieval Specialist Group (BCS/IRSG) Karen Spärck Jones award and a Fellow of the Royal Society of Edinburgh. She has also received best paper awards in leading NLP conferences and has served on the editorial boards of the Journal of Artificial Intelligence Research, the Transactions of the ACL, and Computational Linguistics. She was president of SIGDAT (the group that organizes EMNLP) in 2018.
About the organiser:
The BCS Academy of Computing organises this event; find out more about the group at: https://www.bcs.org/more/bcs-academy-of-computing/
Things to note:
- This event may be recorded.
- The lecture will take place in the Clore Lecture Theatre, 180 Queens Gate, Department of Computing, South Kensington Campus, Imperial College London, SW7 2AZ. This is situated on the 2nd floor of the Huxley Building (this is on the ground floor as you come in through the Queens Gate entrance) The drinks reception will be held in Huxley 341/342.
