Papers and publications

Read, Spot and Translate
Lucia Specia, Josiah Wang, Sun Jae Lee, Alissa Ostapenko and Pranava Madhyastha.
In Machine Translation (Springer) 2020. (forthcoming)

Grounded Sequence to Sequence Transduction
Lucia Specia, Loïc Barrault, Ozan Caglayan, Amanda Duarte, Desmond Elliott, Spandana Gella, Nils Holzenberger, Chiraag Lala, Sun Jae Lee, Jindřich Libovický, Pranava Madhyastha, Florian Metze, Karl Mulligan, Alissa Ostapenko, Shruti Palaskar, Ramon Sanabria, Josiah Wang, and Raman Arora.
In IEEE Journal of Selected Topics in Signal Processing 2020.

Deciding When, How and for Whom to Simplify
Carolina Scarton, Pranava Madhyastha and Lucia Specia.
In proceedings of ECAI 2020.

On Model Stability as a Function of Random Seed
Pranava Madhyastha and Rishabh Jain.
In proceedings of CoNLL 2019.

Deep copycat Networks for Text-to-Text Generation
Julia Ive, Pranava Madhyastha and Lucia Specia.
In proceedings of EMNLP 2019.

VIFIDEL: Evaluating the Visual Fidelity of Image Descriptions
Pranava Madhyastha, Josiah Wang and Lucia Specia.
In proceedings of ACL 2019.

Distilling translations with visual awareness
Julia Ive, Pranava Madhyastha and Lucia Specia.
In proceeding of ACL 2019.

Probing the need for visual context in multimodal machine translation
Ozan Çağlayan, Pranava Madhyastha, Lucia Specia, and Loïc Barrault.
In Proceedings of NAACL 2019. (Best Paper Award)

Learning from multiview correlations in open-domain videos
Nils Holzenberger, Shruti Palaskar, Pranava Madhyastha, Florian Metze and Raman Arora.
In proceedings of ICASSP 2019.

Imperial College London Submission to VATEX Video Captioning Task
Ozan Caglayan, Zixiu Wu, Pranava Madhyastha, Josiah Wang and Lucia Specia.
In proceedings of the workshop on closing the loop between vision & language 2019.

WMDO: Fluency-based Word Mover’s Distance for Machine Translation Evaluation
Julian Chow, Lucia Specia and Pranava Madhyastha.
In proceedings of WMT 2019.

Model Explanations under Calibration
Rishabh Jain and Pranava Madhyastha.
In proceedings of EARS 2019.

Grounded Word Sense Translation
Chiraag Lala, Pranava Madhyastha and Lucia Specia.
In proceedings of SiVL 2019.

Using Language to Evaluate Image Enhancement Tasks
Leonardo Galteri, Pranava Madhyastha, Marco Bertini, Lucia Specia and Alberto del Bimbo.
In proceedings of workshop on language and vision 2019.

End-to-End Image Captioning Exploits Multimodal Distributional Similarity
Pranava Madhyastha, Josiah Wang and Lucia Specia. In proceedings of BMVC 2018.

The Role of Image Representations in Vision to Language Tasks
Pranava Madhyastha, Josiah Wang and Lucia Specia. In JNLE 2018.

Defoiling foiled image captions
Pranava Madhyastha, Josiah Wang and Lucia Specia. In proceedings of NAACL 2018.

Object counts! bringing explicit detections back into image captioning
Josiah Wang, Pranava Madhyastha and Lucia Specia.
In proceedings of NAACL 2018.

Predicting Language Recovery after Stroke with Convolutional Networks on Stitched MRI
Yusuf Roohani, Noor Sajid, Pranava Madhyastha, Cathy Price and Thomas Hope.
In proceedings of ML4H 2018.

Estimating Visual Fidelity in Image Captions
Pranava Madhyastha, Josiah Wang, and Lucia Specia.
In proceedings of SiVL 2018.

End-to-end Image Captioning Exploits Distributional Similarity in Multimodal Space
Pranava Madhyastha, Josiah Wang, and Lucia Specia.
In proceedings of BlacboxNLP 2018.

Sheffield’s submissions for wmt18 multimodal translation tasks
Chiraag Lala, Pranava Madhyastha, Carolina Scarton, and Lucia Specia.
In proceedings of WMT 2018.

Prepositional Phrase Attachment over Word Embedding Products
Pranava Madhyastha, Xavier Carreras, Ariadna Quattoni.
In proceedings of IWPT 2017.

Semi-supervised adaptation of RNNLMs by fine-tuning with domain-specific auxiliary features
Salil Deena, Raymond Ng, Pranava Madhyastha, Lucia Specia and Thomas Hain.
In proceedings of INTERSPEECH 2017.

Exploring hypotheses spaces in neural machine translation
Frédéric Blain, Lucia Specia, Pranava Madhyastha.
In proceedings of AAMT 2017.

Unraveling the Contribution of Image Captioning and Neural Machine Translation for Multimodal Machine Translation
Chiraag Lala, Pranava Madhyastha, Josiah Wang and Lucia Specia.
In proceedings of PBML 2017.

Exploring the use of Acoustic Embeddings in Neural Machine Translation
Salil Deena, Raymond Ng, Pranava Madhyashtha, Lucia Specia, and Thomas Hain.
In proceedings of ASRU 2017.

Sheffield multimt: Using object posterior predictions for multimodal machine translation
Pranava Madhyastha, Josiah Wang and Lucia Specia.
In proceedings of WMT 2017.

Learning bilingual projections of embeddings for vocabulary expansion in machine translation
Pranava Madhyastha and Cristina España-Bonet.
In proceedings of RepL4NLP 2017.

Structured Prediction with Output Embeddings for Semantic Image Annotation
Ariadna Quattoni, Arnau Ramisa, Pranava Madhyastha, Edgar Simo-Serra, Francesc Moreno-Noguer.
In proceedings of NAACL 2016.

Mapping unseen words to task-trained embedding spaces
Pranava Madhyastha, Mohit Bansal, Kevin Gimpel and Karen Livescu.
In proceedings of RepL4NLP 2016. (Best Paper Award)

Semantic tuples for evaluation of image sentence generation
Lily Ellebracht, Arnau Ramisa, Pranava Madhyastha, Cordero Rama, Jose Alejandro, Francesc Moreno-Noguer, and Ariadna Quattoni.
In proceedings of workshop on vision and language 2016.

Tailoring word embeddings for bilexical predictions: An experimental comparison
Pranava Madhyastha, Xavier Carreras, and Ariadna Quattoni.
In ICLR (workshop track) 2015.

Learning task-specific bilexical embeddings
Pranava Madhyastha, Xavier Carreras, and Ariadna Quattoni.
In proceedings of COLING 2014.

Building the Uppsala Hindi Corpus
Anju Saxena, Pranava Madhyasta and Joakim Nivre. In proceedings of SLTC 2008.