Francesco Ronzano

Modelling Sarcasm in Twitter, a Novel Approach

Automatic detection of figurative language is a challenging task in computational linguistics. Recognising both literal and figurative meaning is not trivial for a machine and in some cases it is hard even for humans. For this reason novel and accurate systems able to recognise figurative languages are necessary. We present in this paper a novel computational model capable to detect sarcasm in the social network Twitter (a popular microblogging service which allows users to post short messages). Our model is easy to implement and, unlike previous systems, it does not include patterns of words as features. Our seven sets of lexical features aim to detect sarcasm by its inner structure (for example unexpectedness, intensity of the terms or imbalance between registers), abstracting from the use of specific terms.

How Cosmopolitan Are Emojis?: Exploring Emojis Usage and Meaning over Different Languages with Distributional Semantics

Choosing the right emoji to visually complement or condense the meaning of a message has become part of our daily life. Emojis are pictures, which are naturally combined with plain text, thus creating a new form of language. These pictures are the same independently of where we live, but they can be interpreted and used in different ways. In this paper we compare the meaning and the usage of emojis across different languages. Our results suggest that the overall semantics of the subset of the emojis we studied is preserved across all the languages we analysed. However, some emojis are interpreted in a different way from language to language, and this could be related to socio-geographical differences.

Dr. Inventor Framework: Extracting Structured Information from Scientific Publications

Even if research communities and publishing houses are putting increasing efforts in delivering scientific articles as structured texts, nowadays a considerable part of on-line scientific literature is still available in layout-oriented data formats, like PDF, lacking any explicit structural or semantic information. As a consequence the bootstrap of textual analysis of scientific papers is often a time-consuming activity. We present the first version of the Dr. Inventor Framework, a publicly available collection of scientific text mining components useful to prevent or at least mitigate this problem. Thanks to the integration and the customization of several text mining tools and on-line services, the Dr. Inventor Framework is able to analyze scientific publications both in plain text and PDF format, making explicit and easily accessible core aspects of their structure and semantics. The facilities implemented by the Framework include the extraction of structured textual contents, the discursive characterization of sentences, the identifications of the structural elements of both papers header and bibliographic entries and the generation of graph based representations of text excerpts. The Framework is distributed as a Java library. We describe in detail the scientific mining facilities included in the Framework and present two use cases where the Framework is respectively exploited to boost scientific creativity and to generate RDF graphs from scientific publications.

On the Discoursive Structure of Computer Graphics Research Papers

Understanding the structure of scientific discourse is of paramount importance for the development of appropriate Natural Language Processing tools able to extract and summarize information from research articles. In this paper we present an annotated corpus of scientific discourse in the domain of Computer Graphics. We describe the way we built our corpus by designing an annotation schema and relying on three annotators for manually classifying all sentences into the defined categories. Our corpus constitutes a semantically rich resource for scientific text mining. In this respect, we also present the results of our initial experiments of automatic classification of sentences into the 5 main categories in our corpus.

Knowledge extraction and modeling from scientific publications

During the last decade the amount of scientific articles available online has substantially grown in parallel with the adoption of the Open Access publishing model. Nowadays researchers, as well as any other interested actor, are often overwhelmed by the enormous and continuously growing amount of publications to consider in order to perform any complete and careful assessment of scientific literature. As a consequence, new methodologies and automated tools to ease the extraction, semantic representation and browsing of information from papers are necessary. We propose a platform to automatically extract, enrich and characterize several structural and semantic aspects of scientific publications, representing them as RDF datasets. We analyze papers by relying on the scientific Text Mining Framework developed in the context of the European Project Dr. Inventor. We evaluate how the Framework supports two core scientific text analysis tasks: rhetorical sentence classification and extractive text summarization. To ease the exploration of the distinct facets of scientific knowledge extracted by our platform, we present a set of tailored Web visualizations. We provide on-line access to both the RDF datasets and the Web visualizations generated by mining the papers of the 2015 ACL-IJCNLP Conference.

Semantify CEUR-WS Proceedings: Towards the Automatic Generation of Highly Descriptive Scholarly Publishing Linked Datasets

Rich and fine-grained semantic information describing varied aspects of scientific productions is essential to support their diffusion as well as to properly assess the quality of their output. To foster this trend, in the context of the ESWC2014 Semantic Publishing Challenge, we present a system that automatically generates rich RDF datasets from CEUR-WS workshop proceedings. Proceedings are analyzed through a sequence of processing phases. SVM classifiers complemented by heuristics are used to annotate missing CEUR-WS markups. Annotations are then linked to external datasets like DBpedia and Bibsonomy. Finally, the data is modeled and published as an RDF graph. Our system is provided as an on-line Web service to support on-the-fly RDF generation. In this paper we describe the system and present its evaluation following the procedure set by the organizers of the challenge.

On the Automated Generation of Scholarly Publishing Linked Datasets: The Case of CEUR-WS Proceedings

The availability of highly-informative semantic descriptions of scholarly publishing contents enables an easier sharing and reuse of research findings as well as a better assessment of the quality of scientific productions. In the context of the ESWC2015 Semantic Publishing Challenge, we present a system that automatically generates rich RDF datasets from CEUR-WS workshop proceedings and exposes them as Linked Data. Web pages of proceedings and textual contents of papers are analyzed through proper text processing pipelines. Semantic annotations are added by a set of SVM classifiers and refined by heuristics, gazetteers and rule-based grammars. Web services are exploited to link annotations to external datasets like DBpedia, CrossRef, FundRef and Bibsonomy. Finally, the data is modelled and published as an RDF graph.

An Empirical Assessment of Citation Information in Scientific Summarization

Considering the recent substantial growth of the publication rate of scientific results, nowadays the availability of effective and automated techniques to summarize scientific articles is of utmost importance. In this paper we investigate if and how we can exploit the citations of an article in order to better identify its relevant excerpts. By relying on the BioSumm2014 dataset, we evaluate the variation in performance of extractive summarization approaches when we consider the citations to extend or select the contents of an article to summarize. We compute the maximum ROUGE-2 scores that can be obtained when we summarize a paper by considering its contents together with its citations. We show that the inclusion of citation-related information brings to the generation of better summaries.

UPF-taln: SemEval 2015 Tasks 10 and 11. Sentiment Analysis of Literal and Figurative Language in Twitter

In this paper, we describe the approach used by the UPF-taln team for tasks 10 and 11 of SemEval 2015 that respectively focused on “Sentiment Analysis in Twitter” and “Sentiment Analysis of Figurative Language in Twitter”. Our approach achieved satisfactory results in the figurative language analysis task, obtaining the second best result. In task 10, our approach obtained acceptable performances. We experimented with both wordbased features and domain-independent intrinsic word features. We exploited two machine learning methods: the supervised algorithm Support Vector Machines for task 10, and Random-Sub-Space with M5P as base algorithm for task 11.

Hypernym Extraction: Combining Machine-Learning and Dependency Grammar

Hypernym extraction is a crucial task for semantically motivated NLP tasks such as taxonomy and ontology learning, textual entailment or paraphrase identification. In this paper, we describe an approach to hypernym extraction from textual definitions, where machine-learning and post-classification refinement rules are combined. Our best-performing configuration shows competitive results compared to state-of-the-art systems in a well-known benchmarking dataset. The quality of our features is measured by combining them in different feature sets and by ranking them by their Information Gain score. Our experiments confirm that both syntactic and definitional information play a crucial role in the hypernym extraction task.