You are here

Feed aggregator

Paper accepted at FETLT 2016 - Future and Emerging Trends in Language Technologies, Machine Learning and Big Data

Title: Bootstrapping Technique + Embeddings = Emotional Corpus Annotated Automatically
Authors: Lea Canales, Carlo Strapparava, Ester Boldrini and Patricio Martinez-Barco

AMTA 2016

Marcello Federico will present "An Arabic-Hebrew parallel corpus of TED talks" by Mauro Cettolo at the AMTA Workshop on Semitic Machine Translation (SeMaT)

Marcello Federico will present "Machine Translation Adaptation from Translation Memories in ModernMT" at the AMTA Commercial Users Track

Matteo Negri will present "Instance Selection for Online Automatic Post-Editing in a multi-domain scenario" by
Rajen Chatterjee, Mihael Arcan, Matteo Negri and Marco Turchi

Language English

EMNLP 2016

Marcello Federico will present the paper:

Neural versus Phrase-Based Machine Translation Quality: a Case Study
Luisa Bentivogli, Arianna Bisazza, Mauro Cettolo and Marcello Federico

Language English

La ricerca va in città

Marcello federico gives the flash talk "Un cervello artificiale per tradurre" to high school students.

Language English

Four papers accepted at CLiC-it 2016

"LICO: A Lexicon of Italian Connectives", "Comparing State-of-the-art Dependency Parsers on the Italian Stanford Dependency Treebank", "Semantic Interpretation of Events in Live Soccer Commentaries", and "Grounding the Lexical Sets of Causative-Inchoative Verbs with Word Embedding"

Analysis and processing of temporal information in Basque and the creation of an annotated corpus

In the context of temporal processing, Begoña Altuna will describe the linguistic analysis of temporal constructions, the adaptation of a mark-up language for temporal information, the creation of an annotated corpus and the development of a tool for Basque temporal expression extraction and normalisation.

Language English

Paper accepted at CLiC-it 2016

Online Automatic Post-Editing across Domains
Rajen Chatterjee, Gebremedhen Gebremelak, Matteo Negri, Marco Turchi

Language English

Presentation at AMTA 2016 Commercial Users Track

Machine Translation Adaptation from Translation Memories in ModernMT
Marcello Federico

Language English

Paper accepted at AMTA 2016

Instance Selection for Online Automatic Post-Editing in a multi-domain scenario
Rajen Chatterjee, Mihael Arcan, Matteo Negri and Marco Turchi

Language English

Long paper accepted at IEEE International Conference on Data Science and Advanced Analytics

Title: Exploiting a Bootstrapping Approach for Annotating Emotions in Texts Automatically
Authors: Lea Canales, Carlo Strapparava, Ester Boldrini and Patricio Martinez-Barco

Short paper accepted at EMNLP 2016

Title: Learning to Identify Metaphors from a Corpus of Proverbs
Authors: Gözde Özbal, Carlo Strapparava, Serra Sinem Tekiroglu and Daniele Pighin

Long paper accepted at EMNLP 2016

Neural versus Phrase-Based Machine Translation Quality: a Case Study
Luisa Bentivogli, Arianna Bisazza, Mauro Cettolo and Marcello Federico

Language English

Paper accepted in Natural Language Engineering

A transformation-driven approach for recognizing textual entailment

Roberto Zanoli and Silvia Colombo

Paper accepted in the DATABASE journal

A knowledge-poor approach to chemical-disease relation extraction
Firoj Alam, Anna Corazza, Alberto Lavelli, and Roberto Zanoli
Database Vol. 2016, baw071 doi:10.1093/database/baw071

Release of the WAGS dataset

WAGS, the English/Italian Word Alignment Gold Standard has been released. You can download it here

Language English

Two demo papers accepted at ACL 2016

TMOP: A TOOL FOR UNSUPERVISED TRANSLATION MEMORY CLEANING
Masoud Jalili Sabet, Matteo Negri, Marco Turchi, José G. C. de Souza and Marcello Federico

TRANSCRATER: A TOOL FOR AUTOMATIC SPEECH RECOGNITION QUALITY ESTIMATION
Shahab Jalalvand, Matteo Negri, Marco Turchi, José G. C. de Souza and Falavigna Daniele

Language English

EUCLIP-Contest

On May 13, within the EUCLIP-Contest, students from two schools in Trento and Bolzan are asked to identify semantic entities in different languages, supported by Active Learning computerized systems used within the EUCLIP research activities.

Language English

Pages