Alessandro Maisto

Multimodal Deception Detection: A t-pattern Approach

This work proposes a new approach to deception detection, based on finding significant differences between liars and truth tellers through the analysis of their behavior, verbal and non-verbal. This is based on the combination of two factors: multimodal data collection, and t-pattern analysis. Multimodal approach has been acknowledged in literature about deception detection and on several studies concerning the understanding of any communicative phenomenon. We believe a methodology such as T-pattern analysis could be able to get the best advantages from an approach that combines data coming from multiple signaling systems. In fact, T-pattern analysis is a recent methodology for the analysis of behavior that unveil the complex structure at the basis of the organization of human behavior. For this work, we conducted an experimental study and analyzed data related to a single subject. Results showed how T-pattern analysis allowed to find differences between truth telling and lying. This work aims at making progress in the state of knowledge about deception detection, with the final goal to propose a useful tool for the improvement of public security and well-being.

Tuning SyntaxNet for POS Tagging Italian Sentences

Part-of-speech (POS) tagging is a Natural Language Processing (NLP) technique extremely relevant in Question Answering systems and becomes more complex when these systems operate on spoken language. For the use case of Italian spoken language, here considered, enclitic forms are very difficult to be tagged, since they consist of one or more pronouns appended as suffixes to verbs. This work describes a case study aiming at investigating how to refine SyntaxNet, the NLP framework released by Google, to efficiently tag enclitic forms in Italian. In particular, first, a forward selection of different features is presented, aimed to assess their influence on POS tagging performance of SyntaxNet in Italian. Second, further features are added, as suggested by morphological rules characterizing Italian enclitics, in order to improve POS tagging performance. Finally, a qualitative and quantitative evaluation with respect to sentences coming from real spoken dialogs is performed, showing very promising results.

Morpheme-Based Recognition and Translation of Medical Terms

In this paper we use Nooj to solve a recognition and translation task on medical terms with a morphosemantic approach. The Medical domain is characterized by a huge number of different terms that appear in corpora with very low frequencies. For this reason, machine learning or statistical approaches do not achieve good results on this domain. In our work we apply a morpho-semantic approach that take advantage from a number of Italian and English word-formation strategies for the automatic analysis of Italian words and for the generation of Italian/English bilingual lexicons in the medical sub-code. Using Nooj we built a series of Italian and bilingual dictionaries of morphemes, a set of morphological grammars that specify how morphemes combine with each other, a syntactic grammar for the recognition of compound terms and a Finite State Transducer (FST) for the translation of medical terms based on morphemes. This approach produces as output: a categorized Italian electronic dictionary of medical simple words, provided with labels specifying the meaning of each term; a Thesaurus of simples and compounds medical terms, organized in 22 medical subcategories; A an Italian/English translation of medical terms.

A Method for Topic Detection in Great Volumes of Data

Topics extraction has become increasingly important due to its effectiveness in many tasks, including information filtering, information retrieval and organization of document collections in digital libraries. The Topic Detection consists to find the most significant topics within a document corpus. In this paper we explore the adoption of a methodology of feature reduction to underline the most significant topics within a document corpus. We used an approach based on a clustering algorithm (X-means) over the \(tf-idf\) matrix calculated starting from the corpus, by which we describe the frequency of terms, represented by the columns, that occur in the documents, represented by the rows. To extract the topics, we build n binary problems, where n is the numbers of clusters produced by an unsupervised clustering approach and we operate a supervised feature selection over them, considering the top features as the topic descriptors. We will show the results obtained on two different corpora. Both collections are expressed in Italian: the first collection consists of documents of the University of Naples Federico II, the second one consists in a collection of medical records.

Automatic Population of Italian Medical Thesauri: A Morphosemantic Approach

In the age of Semantic Web, one of the most valuable challenges is the one connected with the information extraction from raw data. Information must be managed with sophisticated linguistic and computational architectures, which are able to approach the semantic dimension of words and sentences. In this paper we propose a morphosemantic method for the automatic creation and population of medical lexical resources. Our approach is grounded on a list of neoclassical formative elements pertaining to the medical domain an on a large sized corpus of medical diagnoses. The outcomes of this work are automatically built electronic dictionaries and thesauri and an annotated corpus for the NLP in the medical domain.

Morphosemantic strategies for the automatic enrichment of Italian lexical databases in the medical domain

Because of the importance of the information conveyed by the clinical documents and owing to the large quantity of raw texts produced in the healthcare system, it became a determinant challenge, in the NLP research field, to arrange the extraction and the management of meaningful data, starting from real text occurrences. In this paper we approach a corpus of 5000 medical diagnoses with sophisticated linguistic and computational devices, which are able to access the semantic dimension of words and sentences contained in it. Our morphosemantic method is grounded on a list of neoclassical formative elements pertaining to the medical domain which has been used for the automatic creation and population of medical lexical resources. The outcomes of this work are automatically built electronic dictionaries and thesauri and an annotated corpus for the NLP in the medical domain.

NooJ Morphological Grammars for Stenotype Writing

Stenotyping is a writing method system used to transcribe spoken texts, rapidly and in real time, using a mechanical or digital device equipped with a special keyboard. This device is called a stenotype, stenotype machine, shorthand machine or steno writer, and it is a specialized chorded keyboard or typewriter allowing to performing beats of one or more keys simultaneously. Stenotyping requires the application of specific coded writing systems intended to limit and accelerate the number of beats. Whereas high-speed beats often generate a high amount of typos, the creation of a stenotype writing method based on a non-casual combination of morphemes would rely on a defined list of elements to be combined (i.e., the morphemes of a language) together with a production syntax (that is, the morphological rules of a language). Therefore, in this paper, we will show how to use NooJ linguistic resources and morphological grammars to build and implement a system for real-time typos automatic correction during stenotype writing.

Morphological Analysis and Generation of Monolingual and Bilingual Medical Lexicons

To efficiently extract and manage extremely large quantities of meaningful data in a delicate sector like healthcare requires sophisticated linguistic strategies and computational solutions. In the research described here we approach the semantic dimension of the formative elements of medical words in monolingual and bilingual environments. The purpose is to automatically build Italian–English medical lexical resources by grounding their analysis and generation on the manipulation of their consituent morphemes. This approach has a significant impact on the automatic analysis of neologisms, typical for the medical domain. We created two electronic dictionaries of morphemes and a morphological finite state transducer, which, together, find all possible combinations of prefixes, confixes, and suffixes, and are able to annotate and translate the terms contained in a medical corpus, according to the meaning of the morphemes that compose these words. In order to enable the machine to “understand” also medical multiword expressions, we designed a syntactic grammar net that includes several paths based on different combinations of nouns, adjectives, and prepositions.

New wine in old wineskins: a morphology-based approach to translate medical terminology

English. In this work we introduce the first steps toward the development of a machine translation system for medical terminology. We explore the possibility of basing a machine translation task in the medical domain on morphology. Starting from neoclassical formative elements, or confixes, we started building MedIta, a cross-language ontology of medical morphemes, aiming to offer a standardized medical consistent resource that includes distributional and semantic information of medical morphemes. Using this information, we have built an ontology-driven Italian-English machine translation prototype, based on a set of Finite State Transducers, and we have carried out an experiment on Orphanet medical corpus to evaluate the feasibility of this approach. Italiano. In questo lavoro si introduce lo sviluppo di un sistema per la traduzione automatica della terminologia medica. Si propone un approcio morfologico, che utilizza gli elementi formativi neoclassici, i confissi. Si introduce MedIta, un’ontologia multilingua di morfemi del dominio medico, che mira ad offrire una risorsa validata secondo gli standard medici e che contiene informazioni semantiche e statistiche. La fattibilit della risorsa viene valutata tramite un prototipo di sistema di traduzione italiano-inglese basato su Trasduttori a Stati Finiti.L’applicazione viene poi testata su un campione estratto dal corpus medico Orphanet.

Feature-Based Customer Review Summarization

To systematically monitor the online customer satisfaction means to deal with a large amount of non-structured data and with many Natural Language Processing challenges. The purpose of the present research is to automatically identify the benefits and the drawbacks expressed by internet users in Italian customer reviews in free text format. The work is grounded on Italian lexical and grammatical resources that, together, are able to investigate the semantic relation between the product features and the opinions expressed on them. On the base of these resources we built DOXA, a linguistic-based application that gives a feedback of statistics about the positive or negative nature of the opinions and about the semantic categories of the features.