Pierpaolo Basile

UNIBA: JIGSAW algorithm for Word Sense Disambiguation

Word Sense Disambiguation (WSD) is traditionally considered an AI-hard problem. A breakthrough in this field would have a significant impact on many relevant web-based applications, such as information retrieval and information extraction. This paper describes JIGSAW, a knowledge-based WSD system that attemps to disambiguate all words in a text by exploiting WordNet senses. The main assumption is that a specific strategy for each Part-Of-Speech (POS) is better than a single strategy. We evaluated the accuracy of JIGSAW on SemEval-2007 task 1 competition. This task is an application-driven one, where the application is a fixed cross-lingual information retrieval system. Participants disambiguate text by assigning WordNet synsets, then the system has to do the expansion to other languages, index the expanded documents and run the retrieval for all the languages in batch. The retrieval results are taken as a measure for the effectiveness of the disambiguation.

Semantics-aware Graph-based Recommender Systems Exploiting Linked Open Data

The ever increasing interest in semantic technologies and the availability of several open knowledge sources have fueled recent progress in the field of recommender systems. In this paper we feed recommender systems with features coming from the Linked Open Data (LOD) cloud - a huge amount of machine-readable knowledge encoded as RDF statements - with the aim of improving recommender systems effectiveness. In order to exploit the natural graph-based structure of RDF data, we study the impact of the knowledge coming from the LOD cloud on the overall performance of a graph-based recommendation algorithm. In more detail, we investigate whether the integration of LOD-based features improves the effectiveness of the algorithm and to what extent the choice of different feature selection techniques influences its performance in terms of accuracy and diversity. The experimental evaluation on two state of the art datasets shows a clear correlation between the feature selection technique and the ability of the algorithm to maximize a specific evaluation metric. Moreover, the graph-based algorithm leveraging LOD-based features is able to overcome several state of the art baselines, such as collaborative filtering and matrix factorization, thus confirming the effectiveness of the proposed approach.

Concept-based item representations for a cross-lingual content-based recommendation process

The growth of the Web is the most influential factor that contributes to the increasing importance of text retrieval and filtering systems. On one hand, the Web is becoming more and more multilingual, and on the other hand users themselves are becoming increasingly polyglot. In this context, platforms for intelligent information access as search engines or recommender systems need to evolve to deal with this increasing amount of multilingual information. This paper proposes a content-based recommender system able to generate cross-lingual recommendations. The idea is to exploit user preferences learned in a given language, to suggest item in another language. The main intuition behind the work is that, differently from keywords which are inherently language dependent, concepts are stable across different languages, allowing to deal with multilingual and cross-lingual scenarios. We propose four knowledge-based strategies to build concept-based representation of items, by relying on the knowledge contained in two knowledge sources, i.e. Wikipedia and BabelNet. We learn user profiles by leveraging the different concept-based representations, in order to define a cross-lingual recommendation process. The empirical evaluation carried out on two state of the art datasets, DBbook and Movielens, shows that concept-based approaches are suitable to provide cross-lingual recommendations, even though there is not a clear advantage of using one of the different proposed representations. However, it emerges that most of the times the approaches based on BabelNet outperform those based on Wikipedia, which clearly shows the advantage of using a native multilingual knowledge source.

Introducing linked open data in graph-based recommender systems

We investigate the impact of the integration of the knowledge coming from the LOD cloud in a graph-based recommendation framework.We propose a methodology to automatically feed a graph-based recommendation algorithm with features coming from the LOD cloud.We give guidelines to drive the choice of the feature selection technique, according to the needs of a specic recommendation scenario (i.e., maximize accuracy, maximize diversity).We validate our methodology by evaluating its effectiveness with respect to several state-of-the-art datasets. Thanks to the recent spread of the Linked Open Data (LOD) initiative, a huge amount of machine-readable knowledge encoded as RDF statements is today available in the so-called LOD cloud. Accordingly, a big effort is now spent to investigate to what extent such information can be exploited to develop new knowledge-based services or to improve the effectiveness of knowledge-intensive platforms as Recommender Systems (RS).To this end, in this article we study the impact of the exogenous knowledge coming from the LOD cloud on the overall performance of a graph-based recommendation framework. Specifically, we propose a methodology to automatically feed a graph-based RS with features gathered from the LOD cloud and we analyze the impact of several widespread feature selection techniques in such recommendation settings.The experimental evaluation, performed on three state-of-the-art datasets, provided several outcomes: first, information extracted from the LOD cloud can significantly improve the performance of a graph-based RS. Next, experiments showed a clear correlation between the choice of the feature selection technique and the ability of the algorithm to maximize specific evaluation metrics, as accuracy or diversity of the recommendations. Moreover, our graph-based algorithm fed with LOD-based features was able to overcome several baselines, as collaborative filtering and matrix factorization.

UNIBA: Sentiment Analysis of English Tweets Combining Micro-blogging, Lexicon and Semantic Features

This paper describes the UNIBA team participation in the Sentiment Analysis in Twitter task (Task 10) at SemEval-2015. We propose a supervised approach relying on keyword, lexicon and micro-blogging features as well as representation of tweets in a word space.

Content-Based Recommender Systems + DBpedia Knowledge = Semantics-Aware Recommender Systems

This paper provides an overview of the work done in the ESWC Linked Open Data-enabled Recommender Systems challenge, in which we proposed an ensemble of algorithms based on popularity, Vector Space Model, Random Forests, Logistic Regression, and PageRank, running on a diverse set of semantic features. We ranked 1st in the top-N recommendation task, and 3rd in the tasks of rating prediction and diversity.

An Artificial Player for a Language Game

A knowledge infusion process gives a system the linguistic and cultural knowledge-normally the prerogative of human beings-required to play a complex language game.

Boosting a Semantic Search Engine by Named Entities

Traditional Information Retrieval (IR) systems are based on bag-of-words representation. This approach retrieves relevant documents by lexical matching between query and document terms. Due to synonymy and polysemy, lexical methods produce imprecise or incomplete results. In this paper we present SENSE (SEmantic N-levels Search Engine), an IR system that tries to overcome the limitations of the ranked keyword approach, by introducing semantic levels which integrate (and not simply replace) the lexical level represented by keywords. Semantic levels provide information about word meanings, as described in a reference dictionary, and named entities. This paper focuses on the named entity level. Our aim is to prove that named entities are useful to improve retrieval performance. We exploit a model able to capture entity relationships, although they are not explicit in documents text. Experiments on CLEF dataset prove the effectiveness of our hypothesis.

Super-Sense Tagging Using Support Vector Machines and Distributional Features

This paper describes our participation in the EVALITA 2011 Super-Sense Tagging (SST) task. SST is the task of annotating each word in a text with a super-sense that defines a general concept such as animal, person or food. Due to the smaller set of concepts involved the task is simpler than Word Sense Disambiguation one which identifies a specific meaning for each word. In this task, we exploit a supervised learning method based on Support Vector Machines. However, supervised approaches are subject to the data-sparseness problem. This side effect is more evident when lexical features are involved, because test data can contain words with low frequency (or absent) in training data. To overcome the sparseness problem, in our supervised strategy, we incorporate information coming from a distributional space of words built on a large corpus, Wikipedia. The results obtained in the task show the effectiveness of our approach.

MARS: a MultilAnguage Recommender System

The exponential growth of the Web is the most influential factor that contributes to the increasing importance of cross-lingual text retrieval and filtering systems. Indeed, relevant information exists in different languages, thus users need to find documents in languages different from the one the query is formulated in. In this context, an emerging requirement is to sift through the increasing flood of multilingual text: this poses a renewed challenge for designing effective multilingual Information Filtering systems. In this paper, we propose a language-independent content-based recommender system, called MARS (MultilAnguage Recommender System), that builds cross-language user profiles, by shifting the traditional text representation based on keywords, to a more complex language-independent representation based on word meanings. As a consequence, the recommender system is able to suggest items represented in a language different from the one used in the content-based user profile. Experiments conducted in a movie recommendation scenario show the effectiveness of the approach.