You are here
Our students Josè Camargo de Souza, Nick Ruiz and Amin Farajian participated to the Google NLP PhD Summit 2015, held at Google Zurich on 23 - 26 September 2015.Language English
The HLT-MT unit will be present at the Researcher's Night event. The general theme of our boot will machine translation, with a particular focus and the "word alignment technology" used to train statistical machine translation systems. The even will be attended by Luisa, Matteo and Marcello.Language English
Marcello Federico attended the Facebook Faculty Summit that was held in London on 22 Sept 2015. About 100 people were invited to the meeting, including FB people from USA and Europe and externals from Europe. The meeting was organised in four separate tracks: machine learning, security, programming languages, and systems. The purpose of the meeting was to update participants about FB's research agenda and activities and to foster collaborations with the invited researchers. MF gave a short presentation about the ideas developed in MateCat and the MMT project.Language English
I'm glad to announce that Nick Ruiz was awarded the Best Student Paper Award at the INTERSPEECH Conference in Dresden (Germany) for the joint FBK-Microsoft research paper:
"Adapting Machine Translation Models toward Misrecognized Speech with Text-to-Speech Pronunciation Rules and Acoustic Confusability"
by Nicholas Ruiz, Qin Gao, William Lewis, Marcello Federico.
INTERSPEECH is among the world largest conferences on Speech and Language Technology (746 papers presented this year).Language English
Thanks to Ondrej for sending us this nice picture, taken on 27 August 2015!Language English
Student Ngoc Phuoc An Vo has been selected for the Google NLP PhD Summit 2015, which will be held at Google Zurich on 23 - 26 Setember 2015.
- Slogans are not forever: Adapting Linguistic Expressions to the News
- Looking at Mondrian's Victory Boogie-Woogie: What do I feel?
In this talk I will present a cloud platform for automatic speech recognition, CloudASR, built on top of Kaldi speech recognition toolkit. The platform supports both batch and online speech recognition mode and it has an annotation interface for transcription of the submitted recordings. The key features of the platform are scalability, customizability and easy deployment. Benchmarks of the platform show that the platform achieves comparable performance with Google Speech API in terms of latency and it can achieve better accuracy on limited domains.Language English
The "TAL e Beni Culturali" workshop promotes synergies between humanities and technologies in Natural Language ProcessingLanguage Undefined
We are glad to acknowledge a financial gift from eBay Inc. to Marcello Federico in order to support research activities by the PhD students working in the HLT-MT research unit.Language English
List of the short papers accepted at ACL 2015Language English
Four oral presentations (three task organization and one system description) three system description posters by HLT-NLP researchers
Serra Sinem Tekiroğlu, Gözde Özbal and Carlo Strapparava. Exploring Sensorial Features for Metaphor Identification
Marco Guerini, Gözde Özbal and Carlo Strapparava. Echoes of Persuasion: The Effect of Euphony in Persuasive Communication
The First Worskop on Computing News Storylines (CNewS 2015) aims at bringing together researchers and scientists working on narrative extraction and representation from news within Computational Linguistics and Artificial Intelligence.Language English
Title: Multitask Learning for Adaptive Quality Estimation of Automatically Transcribed Utterances
Authors: José G. C. de Souza, Hamed Zamani, Matteo Negri, Marco Turchi, Falavigna DanieleLanguage English
List of the papers accepted at ACL 2015Language English