• Publications
  • Influence
CATENA: CAusal and TEmporal relation extraction from NAtural language texts
We present CATENA, a sieve-based system to perform temporal and causal relation extraction and classification from English texts, exploiting the interaction between the temporal and the causal model.Expand
Shallow Discourse Parsing with Conditional Random Fields
This paper takes a data driven approach to identify arguments of explicit discourse connectives and designs the argument segmentation task as a cascade of decisions based on conditional random fields (CRFs). Expand
Annotating Causality in the TempEval-3 Corpus
This work presents some annotation guidelines to capture causality between event pairs, partly inspired by TimeML, and implements a rule-based algorithm to automatically identify explicit causal relations in the TempEval-3 corpus. Expand
Annotation of Discourse Relations for Conversational Spoken Dialogs
A comparison between the sense and connective frequency in a representative subset of the LUNA corpus and in the PDTB confirmed the differences between the two corpora and corroborates the choice to introduce dialog-specific adaptations. Expand
ERNESTA: A Sentence Simplification Tool for Children's Stories in Italian
We present ERNESTA (Enhanced Readability through a Novel Event-based Simplification Tool), the first sentence simplification system for Italian, specifically developed to improve the comprehension ofExpand
KX: A Flexible System for Keyphrase eXtraction
KX, a system for key-phrase extraction developed at FBK-IRST, which exploits basic linguistic annotation combined with simple statistical measures to select a list of weighted keywords from a document, achieves satisfactory results both in finding reader-assigned keywords and in the combined keywords subtask. Expand
Enhancing statistical machine translation with bilingual terminology in a CAT environment
This paper develops a framework that, taking as input a small amount of parallel in-domain data, gathers domain-specific bilingual terms and injects them in an SMT system to enhance the translation productivity. Expand
Corpus-based terminological evaluation of ontologies
A novel system for corpus-based terminological evaluation of ontologies, showing that the proposed ontology metrics allow for assessing the terminological coverage of an ontology with respect to a given domain, and that the framework can be effectively applied to many evaluation-related scenarios. Expand
Towards sentiment analysis for historical texts
The integration of sentiment analysis in ALCIDE, an online platform for historical content analysis, is presented, which is able to analyse the sentiment in historical texts and to discover the opinion about a topic and its change over time. Expand
Neural Text Simplification in Low-Resource Conditions Using Weak Supervision
This paper exploits large amounts of heterogeneous data to automatically select simple sentences, which are then used to create synthetic simplification pairs, and evaluates other solutions, such as oversampling and the use of external word embeddings to be fed to the neural simplification system. Expand