169,916 research outputs found
Rappresentare l'extraterritoriale: la contro-geografia visuale di Ursula Biemann
No full textIn questo capitolo si presenta l’analisi di un video-saggio il quale affronta il conflitto israelo-palestinese da una prospettiva particolare, e cioè provando a raccontare lo spazio extraterritoriale dei campi profughi palestinesi. Per quanto, dunque, X-Mission di Ursula Biemann, artista, curatrice e anche critica svizzera, non sia un esempio direttamente ascrivibile al genere del documentario, in ogni caso dialoga con le questioni poste dalla rappresentazione visiva della memoria, dei suoi spazi e delle sue immagini. I lavori di Biemann da sempre, infatti, interrogano direttamente i modi di documentazione del reale e il ruolo dell’artista come testimone, qui alle prese con un oggetto, il campo, ma anche la figura del profugo, che viene ricomposto attraverso ulteriori testimonianze di “esperti”: avvocati, architetti, giornalisti, antropologi. X-Mission non si propone di ricostruire una memoria, né Biemann intende assegnare ai palestinesi il ruolo esplicito di vittime, ma le strategie di mantenimento e di costruzione di una identità che si basa sull’extraterritoralità propria dei campi profughi, sono in ogni caso segnate dal trauma che si può subire nell’essere esservi confinati, e spesso si affidano alla memoria mitica e mitizzata di una condizione perduta
Semiautomatic Extension of CoreNet (Korean WordNet) using a Bootstrapping Mechanism on Corpus-based Co-occurrences
No full textA framework for enriching lexical semantic resources with distributional semantics
No full textWe present an approach to combining distributional semantic representations induced from text corpora with manually constructed lexical semantic networks. While both kinds of semantic resources are available with high lexical coverage, our aligned resource combines the domain specificity and availability of contextual information from distributional models with the conciseness and high quality of manually crafted lexical networks. We start with a distributional representation of induced senses of vocabulary terms, which are accompanied with rich context information given by related lexical items. We then automatically disambiguate such representations to obtain a full-fledged proto-conceptualization, i.e. a typed graph of induced word senses. In a final step, this proto-conceptualization is aligned to a lexical ontology, resulting in a hybrid aligned resource. Moreover, unmapped induced senses are associated with a semantic type in order to connect them to the core resource. Manual evaluations against ground-truth judgments for different stages of our method as well as an extrinsic evaluation on a knowledge-based Word Sense Disambiguation benchmark all indicate the high quality of the new hybrid resource. Additionally, we show the benefits of enriching top-down lexical knowledge resources with bottom-up distributional information from text for addressing high-end knowledge acquisition tasks such as cleaning hypernym graphs and learning taxonomies from scratch
Learning Concept Hierarchies from Text with a Guided Agglomerative Clustering Algorithm
No full textCimiano P, Staab S. Learning Concept Hierarchies from Text with a Guided Agglomerative Clustering Algorithm. In: Biemann C, Paas G, eds. Proceedings of the ICML 2005 Workshop on Learning and Extending Lexical Ontologies with Machine Learning Methods. Bonn; 2005
Enriching frame representations with distributionally induced senses
No full textWe introduce a new lexical resource that enriches the Framester knowledge graph, which links Framnet, WordNet, VerbNet and other resources, with semantic features from text corpora. These features are extracted from distributionally induced sense inventories and subsequently linked to the manually-constructed frame representations to boost the performance of frame disambiguation in context. Since Framester is a frame-based knowledge graph, which enables full-fledged OWL querying and reasoning, our resource paves the way for the development of novel, deeper semantic-aware applications that could benefit from the combination of knowledge from text and complex symbolic representations of events and participants. Together with the resource we also provide the software we developed for the evaluation in the task of Word Frame Disambiguation (WFD)
The contrastmedium algorithm: Taxonomy induction from noisy knowledge graphswith just a few links
No full textIn this paper, we present ContrastMedium, an algorithm that transforms noisy semantic networks into full-fledged, clean taxonomies. ContrastMedium is able to identify the embedded taxonomy structure from a noisy knowledge graph without explicit human supervision such as, for instance, a set of manually selected input root and leaf concepts. This is achieved by leveraging structural information from a companion reference taxonomy, to which the input knowledge graph is linked (either automatically or manually). When used in conjunction with methods for hypernym acquisition and knowledge base linking, our methodology provides a complete solution for end-to-end taxonomy induction. We conduct experiments using automatically acquired knowledge graphs, as well as a SemEval benchmark, and show that our method is able to achieve high performance on the task of taxonomy induction
Linked disambiguated distributional semantic networks
No full textWe present a new hybrid lexical knowledge base that combines the contextual information of distributional models with the conciseness and precision of manually constructed lexical networks. The computation of our count-based distributional model includes the induction of word senses for single-word and multi-word terms, the disambiguation of word similarity lists, taxonomic relations extracted by patterns and context clues for disambiguation in context. In contrast to dense vector representations, our resource is human readable and interpretable, and thus can be easily embedded within the Semantic Web ecosystem
SemEval-2013 Task 5: Evaluating Phrasal Semantics
No full textThis paper describes the SemEval-2013 Task
5: “Evaluating Phrasal Semantics”. Its first
subtask is about computing the semantic similarity
of words and compositional phrases of
minimal length. The second one addresses
deciding the compositionality of phrases in a
given context. The paper discusses the importance
and background of these subtasks and
their structure. In succession, it introduces the
systems that participated and discusses evaluation
results
Lemonade: A Web Assistant for Creating and Debugging Ontology Lexica
No full textRico M, Unger C. Lemonade: A Web Assistant for Creating and Debugging Ontology Lexica. In: Biemann C, Handschuh S, Freitas A, Meziane F, Metais E, eds. Natural Language Processing and Information Systems. 20th International Conference, NLDB 2015, Proceedings. Lecture Notes in Computer Science. Vol 9103. Cham: Springer International Publishing; 2015: 448-452
- …
