Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 14
Encontrada(s) 1 página(s)

Repositorio Digital de la UPF
Publication Contribución de congreso (ConferenceOutput)

Unsupervised keyword extraction using the GoW model and centrality scores

  • Batziou, Elissavet
  • Gialampoukidis, Ilias
  • Vrochidis, Stefanos
  • Kompatsiaris, Ioannis
Comunicació presentada a: The 4th International Conference, INSCI 2017, celebrat a Thessaloniki, Grècia, del 22 al 24 de novembre de 2017., Nowadays, a large amount of text documents are produced on a daily basis, so we need e cient and e ective access to their con- tent. News articles, blogs and technical reports are often lengthy, so the reader needs a quick overview of the underlying content. To that end we present graph-based models for keyword extraction, in order to compare the Bag of Words model with the Graph of Words model in the key- word extraction problem. We compare their performance in two publicly available datasets using the evaluation measures Precision@10, mean Av- erage Precision and Jaccard coe cient. The methods we have selected for comparison are grouped into two main categories. On the one hand, centrality measures on the formulated Graph-of-Words (GoW) are able to rank all words in a document from the most central to the less central, according to their score in the GoW representation. On the other hand, community detection algorithms on the GoW provide the largest commu- nity that contains the key nodes (words) in the GoW. We selected these methods as the most prominent methods to identify central nodes in a GoW model. We conclude that term-frequency scores (BoW model) are useful only in the case of less structured text, while in more structured text documents, the order of words plays a key role and graph-based models are superior to the term-frequency scores per document., This work was supported by the projects H2020-645012 (KRISTINA) and H2020-700024 (TENSOR), funded by the European Commission.
Repositorio Digital de la UPF
Publication Artículo científico (JournalArticle)

How well do hate speech, toxicity, abusive and offensive language classification models generalize across datasets?

  • Fortuna, Paula
  • Soler Company, Juan
  • Wanner, Leo
A considerable body of research deals with the automatic identification of hate speech and related phenomena. However, cross-dataset model generalization remains a challenge. In this context, we address two still open central questions: (i) to what extent does the generalization depend on the model and the composition and annotation of the training data in terms of different categories?, and (ii) do specific features of the datasets or models influence the generalization potential? To answer (i), we experiment with BERT, ALBERT, fastText, and SVM models trained on nine common public English datasets, whose class (or category) labels are standardized (and thus made comparable), in intra- and cross-dataset setups. The experiments show that indeed the generalization varies from model to model and that some of the categories (e.g., ‘toxic’, ‘abusive’, or ‘offensive’) serve better as cross-dataset training categories than others (e.g., ‘hate speech’). To answer (ii), we use a Random Forest model for assessing the relevance of different model and dataset features during the prediction of the performance of 450 BERT, 450 ALBERT, 450 fastText, and 348 SVM binary abusive language classifiers (1698 in total). We find that in order to generalize well, a model already needs to perform well in an intra-dataset scenario. Furthermore, we find that some other parameters are equally decisive for the success of the generalization, including, e.g., the training and target categories and the percentage of the out-of-domain vocabulary., The first author is supported by the research grant SFRH/BD/143623/2019, provided by the Portuguese national funding agency for science, research and technology, Fundação para a Ciência e a Tecnologia (FCT), within the scope of Operational Program Human Capital (POCH), supported by the European Social Fund and by national funds from MCTES. The work of the second and third authors has been supported by the European Commission in the context of the H2020 Research Program under the contract numbers 700024 and 786731.
Repositorio Digital de la UPF
Publication Contribución de congreso (ConferenceOutput)

VERGE in VBS 2017

  • Moumtzidou, Anastasia
  • Mironidis, Theodoros
  • Markatopoulou, Fotini
  • Andreadis, Stelios
  • Gialampoukidis, Ilias
  • Galanopoulos, Damianos
  • Ioannidou, Anastasia
  • Vrochidis, Stefanos
  • Mezaris, Vasileios
  • Kompatsiaris, Ioannis
  • Patras, Ioannis
Comunicació presentada a Video Browser Showdown (VBS'17), a 23rd International Conference on MultiMedia Modeling (MMM'17), celebrat el 4 de gener de 2017 a Reykjavik, Islàndia., This paper presents VERGE interactive video retrieval engine, which is capable of browsing and searching into video content. The system integrates several content-based analysis and retrieval modules including concept detec-tion, clustering, visual similarity search, object-based search, query analysis and multimodal and temporal fusion., This work was supported by the EU’s Horizon 2020 research and innovation programme under grant agreements H2020-687786 InVID, H2020-693092 MOVING, H2020-645012 KRISTINA and H2020-700024 TENSOR.
Repositorio Digital de la UPF
Publication Contribución de congreso (ConferenceOutput)

FORGe at SemEval-2017 Task 9: deep sentence generation based on a sequence of graph transducers

  • Mille, Simon
  • Carlini, Roberto
  • Burga Díaz, Alicia
  • Wanner, Leo
Comunicació presentada a: The 11th International Workshop on Semantic Evaluations (SemEval-2017), celebrada del 3 al 4 d'agost de 2017 a Vancouver, Canadà., We present the contribution of Universitat Pompeu Fabra’s NLP group to the Sem-Eval Task 9.2 (AMR-to-English Generation). The proposed generation pipeline comprises: (i) a series of rule-based graphtransducers for the syntacticization of the input graphs and the resolution of morphological agreements, and (ii) an off-theshelf statistical linearization component., The work described in this paper has been partially funded by the European Commission under the contract numbers FP7-ICT-610411, H2020- 645012-RIA, H2020-700024-RIA, and H2020-DRS-01-2015.
Repositorio Digital de la UPF
Publication Contribución de congreso (ConferenceOutput)

Revising the METU-Sabancı Turkish treebank: an exercise in surface-syntactic annotation of agglutinative languages

  • Burga Díaz, Alicia
  • Öktem, Alp
  • Wanner, Leo
Comunicació presentada a: the Fourth International Conference on Dependency Linguistics (Depling 2017), celebrada a Pisa, Itàlia, del 18 al 20 de setembre 2017., In this paper, we present a revision of the training set of the METU-Sabancı Turkish syntactic dependency treebank composed of 4997 sentences in accordance with the principles of the Meaning-Text Theory (MTT). MTT reflects the multilayered nature of language by a linguistic model in which each linguistic phenomenon is treated at its corresponding level(s). Our analysis of the METU-Sabancı syntactic relation tagset reveals that it encodes deepmorphological and surface-syntactic phenomena, which should be separated according to the MTT model. We propose an alternative surface-syntactic relation annotation schema and show that this schema also allows for a sound projection of the obtained surface annotation onto a deepsyntactic annotation, as needed for the implementation of down-stream language understanding applications., The presented work has been funded by the European Commission as part of the H2020 Programme, under the contract numbers 645012–RIA and 700024-RIA.
Repositorio Digital de la UPF
Publication Contribución de congreso (ConferenceOutput)

A Demo of FORGe: the Pompeu Fabra open rule-based generator

  • Mille, Simon
  • Wanner, Leo
Comunicació presentada a: The 10th International Natural Language Generation conference, celebrat del 3 al 4 de setembre de 2017 a Santiago de Compostela, This demo paper presents the multilingual deep sentence generator developed by the TALN group at Universitat Pompeu Fabra, implemented as a series of rule-based graphtransducers., The work described in this paper has been partially funded by the European Commission under the contract numbers FP7-ICT-610411, H2020-645012-RIA, H2020-700024-RIA, and H2020-700475-RIA.
Repositorio Digital de la UPF
Publication Contribución de congreso (ConferenceOutput)

Targets and aspects in social media hate speech

  • Shvets, Alexander
  • Fortuna, Paula
  • Wanner, Leo
Comunicació presentada a The 5th Workshop on Online Abuse and Harms (WOAH 2021), celebrat el 6 d'agost de 2021 de manera virtual., Mainstream research on hate speech focused so far predominantly on the task of classifying mainly social media posts with respect to predefined typologies of rather coarse-grained hate speech categories. This may be sufficient if the goal is to detect and delete abusive language posts. However, removal is not always possible due to the legislation of a country. Also, there is evidence that hate speech cannot be successfully combated by merely removing hate speech posts; they should be countered by education and counter-narratives. For this purpose, we need to identify (i) who is the target in a given hate speech post, and (ii) what aspects (or characteristics) of the target are attributed to the target in the post. As the first approximation, we propose to adapt a generic state-of-the-art concept extraction model to the hate speech domain. The outcome of the experiments is promising and can serve as inspiration for further work on the task., Paula Fortuna is supported by the research grant SFRH/BD/143623/2019, provided by the Portuguese national funding agency for science, research and technology, Fundação para a Ciência e a Tecnologia (FCT), within the scope of the Operational Program Human Capital (POCH), supported by the European Social Fund and by national funds from MCTES. The work of Alexander Shvets, Juan Soler-Company, and Leo Wanner has been supported by the European Commission in the context of the H2020 Research Program under the contract numbers 700024, 786731, and 825079.
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Unsupervised keyword extraction using the GoW model and centrality scores

  • Batziou, Elissavet
  • Gialampoukidis, Ilias
  • Vrochidis, Stefanos
  • Kompatsiaris, Ioannis
Comunicació presentada a: The 4th International Conference, INSCI 2017, celebrat a Thessaloniki, Grècia, del 22 al 24 de novembre de 2017., Nowadays, a large amount of text documents are produced on a daily basis, so we need e cient and e ective access to their con- tent. News articles, blogs and technical reports are often lengthy, so the reader needs a quick overview of the underlying content. To that end we present graph-based models for keyword extraction, in order to compare the Bag of Words model with the Graph of Words model in the key- word extraction problem. We compare their performance in two publicly available datasets using the evaluation measures Precision@10, mean Av- erage Precision and Jaccard coe cient. The methods we have selected for comparison are grouped into two main categories. On the one hand, centrality measures on the formulated Graph-of-Words (GoW) are able to rank all words in a document from the most central to the less central, according to their score in the GoW representation. On the other hand, community detection algorithms on the GoW provide the largest commu- nity that contains the key nodes (words) in the GoW. We selected these methods as the most prominent methods to identify central nodes in a GoW model. We conclude that term-frequency scores (BoW model) are useful only in the case of less structured text, while in more structured text documents, the order of words plays a key role and graph-based models are superior to the term-frequency scores per document., This work was supported by the projects H2020-645012 (KRISTINA) and H2020-700024 (TENSOR), funded by the European Commission.
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Targets and aspects in social media hate speech

  • Shvets, Alexander
  • Fortuna, Paula
  • Wanner, Leo
Comunicació presentada a The 5th Workshop on Online Abuse and Harms (WOAH 2021), celebrat el 6 d'agost de 2021 de manera virtual., Mainstream research on hate speech focused so far predominantly on the task of classifying mainly social media posts with respect to predefined typologies of rather coarse-grained hate speech categories. This may be sufficient if the goal is to detect and delete abusive language posts. However, removal is not always possible due to the legislation of a country. Also, there is evidence that hate speech cannot be successfully combated by merely removing hate speech posts; they should be countered by education and counter-narratives. For this purpose, we need to identify (i) who is the target in a given hate speech post, and (ii) what aspects (or characteristics) of the target are attributed to the target in the post. As the first approximation, we propose to adapt a generic state-of-the-art concept extraction model to the hate speech domain. The outcome of the experiments is promising and can serve as inspiration for further work on the task., Paula Fortuna is supported by the research grant SFRH/BD/143623/2019, provided by the Portuguese national funding agency for science, research and technology, Fundação para a Ciência e a Tecnologia (FCT), within the scope of the Operational Program Human Capital (POCH), supported by the European Social Fund and by national funds from MCTES. The work of Alexander Shvets, Juan Soler-Company, and Leo Wanner has been supported by the European Commission in the context of the H2020 Research Program under the contract numbers 700024, 786731, and 825079.
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

How well do hate speech, toxicity, abusive and offensive language classification models generalize across datasets?

  • Fortuna, Paula
  • Soler Company, Juan
  • Wanner, Leo
A considerable body of research deals with the automatic identification of hate speech and related phenomena. However, cross-dataset model generalization remains a challenge. In this context, we address two still open central questions: (i) to what extent does the generalization depend on the model and the composition and annotation of the training data in terms of different categories?, and (ii) do specific features of the datasets or models influence the generalization potential? To answer (i), we experiment with BERT, ALBERT, fastText, and SVM models trained on nine common public English datasets, whose class (or category) labels are standardized (and thus made comparable), in intra- and cross-dataset setups. The experiments show that indeed the generalization varies from model to model and that some of the categories (e.g., ‘toxic’, ‘abusive’, or ‘offensive’) serve better as cross-dataset training categories than others (e.g., ‘hate speech’). To answer (ii), we use a Random Forest model for assessing the relevance of different model and dataset features during the prediction of the performance of 450 BERT, 450 ALBERT, 450 fastText, and 348 SVM binary abusive language classifiers (1698 in total). We find that in order to generalize well, a model already needs to perform well in an intra-dataset scenario. Furthermore, we find that some other parameters are equally decisive for the success of the generalization, including, e.g., the training and target categories and the percentage of the out-of-domain vocabulary., The first author is supported by the research grant SFRH/BD/143623/2019, provided by the Portuguese national funding agency for science, research and technology, Fundação para a Ciência e a Tecnologia (FCT), within the scope of Operational Program Human Capital (POCH), supported by the European Social Fund and by national funds from MCTES. The work of the second and third authors has been supported by the European Commission in the context of the H2020 Research Program under the contract numbers 700024 and 786731.
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

VERGE in VBS 2017

  • Moumtzidou, Anastasia
  • Mironidis, Theodoros
  • Markatopoulou, Fotini
  • Andreadis, Stelios
  • Gialampoukidis, Ilias
  • Galanopoulos, Damianos
  • Ioannidou, Anastasia
  • Vrochidis, Stefanos
  • Mezaris, Vasileios
  • Kompatsiaris, Ioannis
  • Patras, Ioannis
Comunicació presentada a Video Browser Showdown (VBS'17), a 23rd International Conference on MultiMedia Modeling (MMM'17), celebrat el 4 de gener de 2017 a Reykjavik, Islàndia., This paper presents VERGE interactive video retrieval engine, which is capable of browsing and searching into video content. The system integrates several content-based analysis and retrieval modules including concept detec-tion, clustering, visual similarity search, object-based search, query analysis and multimodal and temporal fusion., This work was supported by the EU’s Horizon 2020 research and innovation programme under grant agreements H2020-687786 InVID, H2020-693092 MOVING, H2020-645012 KRISTINA and H2020-700024 TENSOR.
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Revising the METU-Sabancı Turkish treebank: an exercise in surface-syntactic annotation of agglutinative languages

  • Burga Díaz, Alicia
  • Öktem, Alp
  • Wanner, Leo
Comunicació presentada a: the Fourth International Conference on Dependency Linguistics (Depling 2017), celebrada a Pisa, Itàlia, del 18 al 20 de setembre 2017., In this paper, we present a revision of the training set of the METU-Sabancı Turkish syntactic dependency treebank composed of 4997 sentences in accordance with the principles of the Meaning-Text Theory (MTT). MTT reflects the multilayered nature of language by a linguistic model in which each linguistic phenomenon is treated at its corresponding level(s). Our analysis of the METU-Sabancı syntactic relation tagset reveals that it encodes deepmorphological and surface-syntactic phenomena, which should be separated according to the MTT model. We propose an alternative surface-syntactic relation annotation schema and show that this schema also allows for a sound projection of the obtained surface annotation onto a deepsyntactic annotation, as needed for the implementation of down-stream language understanding applications., The presented work has been funded by the European Commission as part of the H2020 Programme, under the contract numbers 645012–RIA and 700024-RIA.
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

A Demo of FORGe: the Pompeu Fabra open rule-based generator

  • Mille, Simon
  • Wanner, Leo
Comunicació presentada a: The 10th International Natural Language Generation conference, celebrat del 3 al 4 de setembre de 2017 a Santiago de Compostela, This demo paper presents the multilingual deep sentence generator developed by the TALN group at Universitat Pompeu Fabra, implemented as a series of rule-based graphtransducers., The work described in this paper has been partially funded by the European Commission under the contract numbers FP7-ICT-610411, H2020-645012-RIA, H2020-700024-RIA, and H2020-700475-RIA.
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

FORGe at SemEval-2017 Task 9: deep sentence generation based on a sequence of graph transducers

  • Mille, Simon
  • Carlini, Roberto
  • Burga Díaz, Alicia
  • Wanner, Leo
Comunicació presentada a: The 11th International Workshop on Semantic Evaluations (SemEval-2017), celebrada del 3 al 4 d'agost de 2017 a Vancouver, Canadà., We present the contribution of Universitat Pompeu Fabra’s NLP group to the Sem-Eval Task 9.2 (AMR-to-English Generation). The proposed generation pipeline comprises: (i) a series of rule-based graphtransducers for the syntacticization of the input graphs and the resolution of morphological agreements, and (ii) an off-theshelf statistical linearization component., The work described in this paper has been partially funded by the European Commission under the contract numbers FP7-ICT-610411, H2020- 645012-RIA, H2020-700024-RIA, and H2020-DRS-01-2015.