614 research outputs found
Distributional Memory: A General Framework for Corpus-Based Semantics
No full textResearch into corpus-based semantics has focused on the development of ad hoc models that treat single tasks, or sets of closely related tasks, as unrelated challenges to be tackled by extracting different kinds of distributional information from the corpus. As an alternative to this “one task, one model” approach, the Distributional Memory framework extracts distributional information once and for all from the corpus, in the form of a set of weighted word-link-word tuples arranged into a third-order tensor. Different matrices are then generated from the tensor, and their rows and columns constitute natural spaces to deal with different semantic problems. In this way, the same distributional information can be shared across tasks such as modeling word similarity judgments, discovering synonyms, concept categorization, predicting selectional preferences of verbs, solving analogy problems, classifying relations between word pairs, harvesting qualia structures with patterns or example pairs, predicting the typical properties of concepts, and classifying verbs into alternation classes. Extensive empirical testing in all these domains shows that a Distributional Memory implementation performs competitively against task-specific algorithms recently reported in the literature for the same tasks, and against our implementations of several state-of-the-art methods. The Distributional Memory approach is thus shown to be tenable despite the constraints imposed by its multi-purpose nature
Segregation discovery in a social network of companies
No full textWe introduce a framework for a data-driven analysis of segregation
of minority groups in social networks, and challenge it on a complex
scenario. The framework builds on quantitative measures of segregation,
called segregation indexes, proposed in the social science literature.
The segregation discovery problem consists of searching sub-graphs and
sub-groups for which a reference segregation index is above a minimum
threshold. A search algorithm is devised that solves the segregation problem.
The framework is challenged on the analysis of segregation of social
groups in the boards of directors of the real and large network of Italian
companies connected through shared directors
Segregation discovery in a social network of companies
No full textWe introduce a framework for the data-driven analysis of social segregation of minority groups, and challenge it on a complex scenario. The framework builds on quantitative measures of segregation, called segregation indexes, proposed in the social science literature. The segregation discovery problem is introduced, which consists of searching sub-groups of population and minorities for which a segregation index is above a minimum threshold. A search algorithm is devised that solves the segregation problem by computing a multi-dimensional data cube that can be explored by the analyst. The machinery underlying the search algorithm relies on frequent itemset mining concepts and tools. The framework is challenged on a cases study in the context of company networks. We analyse segregation on the grounds of sex and age for directors in the boards of the Italian companies. The network includes 2.15M companies and 3.63M directors
Gli enti locali e la difesa del principio di sussidiarietà: quali prospettive per un accesso diretto alla Corte costituzionale?
No full textArchitecture Description Leveraging Model Driven Engineering and Semantic Wikis
No full textA previous study, run by some of the authors in collaboration with practitioners, has emphasized the need to improve architectural languages in order to (i) make them simple and intuitive enough to communicate effectively with project stakeholders, and (ii) enable formality and rigour to allow analysis and other automated tasks. Although a multitude of languages have been created by researchers and practitioners, they rarely address both of these needs. In order to reconcile these divergent needs, this paper presents an approach that (i) combines the rigorous foundations of model-driven engineering with the usability of semantic wikis, and (ii) enables continuous syncronization between them, this allows software architects to simultaneously use wiki pages for communication and models for model-based analysis and manipulation. In this paper we explain how we applied the approach to an industry-inspired case study using the Semantic Media Wiki wiki engine and a model-driven architecture description implemented within the Eclipse Modeling Framework. We also discuss how our approach can be generalized to other wiki-based and model-driven technologies. © 2014 IEEE
Concepts and properties in word spaces
No full textProperties play a central role in most theories of conceptual
knowledge. Since computational models derived from word co-occurrence statistics have been claimed to provide a natural basis for semantic representations, the question arises of whether such models are capable of producing reasonable property-based descriptions of concepts, and whether these descriptions are similar to those elicited from humans. This article presents a qualitative analysis of the properties generated by humans in two different settings, as well as those
produced, for the same concepts, by two computational models. In order to find high-level generalizations, the analysis is conducted in terms of property types, i.e., categorizing properties into classes such as functional and taxonomic properties. We discover that differences and similarities among models cut across the human/computational distinction, suggesting on the one hand caution in making broad generalizations, e.g., about “grounded” and “amodal” approaches, and, on the other, that different models might reveal different facets of meaning, and thus they should rather be integrated than seen as rival ways to get at the same information
How we BLESSed distributional semantic evaluation
No full textWe introduce BLESS, a data set specifically designed for the evaluation of distributional semantic models. BLESS contains a set of tuples instantiating different, explicitly typed semantic relations, plus a number of controlled random tuples. It is thus possible to assess the ability of a model to detect truly related word pairs, as well as to perform in-depth analyses of the types of semantic relations that a model favors. We discuss the motivations for BLESS, describe its construction and structure, and present examples of its usage in the evaluation of distributional semantic models
Wacky! Working papers on the Web as Corpus
No full textWacky!
Working Papers on the Web as Corpus
TABLE OF CONTENTS
Front Matter
(Includes author contact information)
A WaCky Introduction
Silvia Bernardini, Marco Baroni and Stefan Evert
Experience Building a Large Corpus for Chinese Lexicon Construction
Thomas Emerson and John O'Neil
Creating General-Purpose Corpora Using Automated Search Engine Queries
Serge Sharoff
Evaluation of Japanese Web-Based Reference Corpora: Effects of Seed Selection and Time Interval
Motoko Ueyama
Measuring Web Corpus Randomness: A Progress Report
Massimiliano Ciaramita and Marco Baroni
Using the Web as a Source of LSP Corpora in the Terminology Classroom
Sara Castagnoli
Specialized Corpora from the Web and Term Extraction for Simultaneous Interpreters
Claudio Fantinuoli
The Net for the Graphs: Towards Webgenre Representation for Corpus Linguistic Studies
Alexander Mehler and Rüdiger Glei
One semantic memory, many semantic tasks
No full textWe propose an approach to corpus-based semantics, inspired by cognitive science, in which different semantic tasks are tackled using the same underlying repository of distributional information, collected once and for all from the source corpus. Task-specific semantic spaces are then built on demand from the repository. A straightforward implementation of our proposal achieves state-of-the-art performance on a number of unrelated tasks
- …
