1 code implementation • WS 2018 • Pranava Swaroop Madhyastha, Josiah Wang, Lucia Specia
We hypothesize that end-to-end neural image captioning systems work seemingly well because they exploit and learn {`}distributional similarity{'} in a multimodal feature space, by mapping a test image to similar training images in this space and generating a caption from the same space.
no code implementations • WS 2018 • Chiraag Lala, Pranava Swaroop Madhyastha, Carolina Scarton, Lucia Specia
For task 1b, we explore three approaches: (i) re-ranking based on cross-lingual word sense disambiguation (as for task 1), (ii) re-ranking based on consensus of NMT n-best lists from German-Czech, French-Czech and English-Czech systems, and (iii) data augmentation by generating English source data through machine translation from French to English and from German to English followed by hypothesis selection using a multimodal-reranker.
no code implementations • WS 2017 • Pranava Swaroop Madhyastha, Xavier Carreras, Ariadna Quattoni
We present a low-rank multi-linear model for the task of solving prepositional phrase attachment ambiguity (PP task).
no code implementations • WS 2017 • Pranava Swaroop Madhyastha, Cristina Espa{\~n}a-Bonet
We propose a simple log-bilinear softmax-based model to deal with vocabulary expansion in machine translation.
no code implementations • 5 Aug 2016 • Pranava Swaroop Madhyastha, Cristina España-Bonet
Out-of-vocabulary words account for a large proportion of errors in machine translation systems, especially when the system is used on a different domain than the one where it was trained.
no code implementations • WS 2016 • Pranava Swaroop Madhyastha, Mohit Bansal, Kevin Gimpel, Karen Livescu
We consider the supervised training setting in which we learn task-specific word embeddings.
no code implementations • NAACL 2016 • Ariadna Quattoni, Arnau Ramisa, Pranava Swaroop Madhyastha, Edgar Simo-Serra, Francesc Moreno-Noguer
We address the task of annotating images with semantic tuples.
no code implementations • 22 Dec 2014 • Pranava Swaroop Madhyastha, Xavier Carreras, Ariadna Quattoni
We investigate the problem of inducing word embeddings that are tailored for a particular bilexical relation.