|Title||:||Bridge Correlational Neural Networks|
|Speaker||:||Mitesh Khapra (IBM Research)|
|Details||:||Thu, 7 Jan, 2016 3:30 PM @ BSB 361|
|Abstract:||:||Recently there has been a lot of interest in learning common representations for multiple views of data. Typically, such common representations are learned using a parallel corpus between the two views (say, 1M images and their English captions). In this work, we address a real-world scenario where no direct parallel data is available between two views of interest (say, V1 and V2) but parallel data is available between each of these views and a pivot view (V3). We propose a model for learning a common representation for V1, V2 and V3 using only the parallel data available between V1V3 and V2V3. The proposed model is generic and even works when there are $n$ views of interest and only one pivot view which acts as a bridge between them. There are two specific downstream applications that we focus on (i) Transfer learning between languages L1,L2,...,Ln using a pivot language L and (ii) cross modal access between images and a language L1 using a pivot language L2. We evaluate our model using two datasets : (i) publicly available multilingual TED corpus and (ii) a new multilingual multimodal dataset created and released as a part of this work. On both these datasets, our model outperforms state of the art approaches.
Speaker Bio: Mitesh M Khapra is currently working as a Researcher at IBM Research India. During the past three years at IBM he has worked on several interesting problems in the areas of Statistical Machine Translation, Cross Language Learning, Multimodal Learning, Argument Mining and Deep Learning. This work has led to publications in top conferences in the areas of Computational Linguistics and Machine Learning. Prior to joining IBM, he completed his PhD and M.Tech degrees from IIT Bombay in the year 2012 and 2008 respectively. His Ph.D. thesis dealt with the important problem of reusing resources for multilingual computation.