• Publications
  • Influence
Automatic induction of FrameNet lexical units
TLDR
This paper investigates the applicability of distributional and WordNet-based models on the task of lexical unit induction, i.e. the expansion of FrameNet with new lexical units, and shows good level of accuracy and coverage, especially when combined.
Combining Word Sense and Usage for Modeling Frame Semantics
TLDR
A large scale evaluation over the English FrameNet is reported, and results on extending FrameNet to the Italian language are reported, as the basis of the development of a full FrameNet for Italian.
Cross-Language Frame Semantics Transfer in Bilingual Corpora
TLDR
A robust method based on a statistical machine translation step augmented with simple rule-based post-processing is presented that alleviates problems related to preprocessing errors and the complex optimization required by syntax-dependent models of the cross-lingual mapping.
Learning Selectional Preferences for Entailment or Paraphrasing Rules
TLDR
A robust method for automatic learning of inference rules is presented, which relies on a geometrical model of similarity, based on a form of latent semantic analysis applied to the source text collection, that implies also selectional preference for the individual rule arguments.
Robust and Efficient Page Rank for Word Sense Disambiguation
TLDR
An adaptation of the PageRank algorithm recently proposed for Word Sense Disambiguation is presented that preserves the reachable accuracy while significantly reducing the requested processing time.
Enabling Advanced Business Intelligence in Divino
TLDR
The resulting platform embodies an innovative portal technology where Social Web functionalities, User Profiling and Aspect-based Opinion Mining are integrated through Liferay, a well known Enterprise Portal Technology.
EvalIta 2011: The Frame Labeling over Italian Texts Task
TLDR
The Frame Labeling over Italian texts (FLaIT) task held within the EvalIta 2011 challenge is here described and proposed systems are based on a variety of learning techniques and achieve very good results, over 80% of accuracy, in most subtasks.
Extensive Evaluation of a FrameNet-WordNet mapping resource
TLDR
This work gives an extensive evaluation of the model proposed in (De Cao et al., 2008) using gold standard proposed in other works, and gives an empirical comparison between other available resources.
Data-Driven Dialogue for Interactive Question Answering
TLDR
The resulting architecture is called REQUIRE, and represents a flexible and adaptive platform for domain specific dialogue that characterizes as a domain-driven dialogue system, whose aim is to support the specific tasks evoked by interactive question answering scenarios.
...
1
2
3
...