Filters








337 Hits in 5.0 sec

FCC: Three Approaches for Semantic Textual Similarity

Maya Carrillo, Darnes Vilariño, David Pinto, Mireya Tovar, Saúl León, Esteban Castillo
2012 International Workshop on Semantic Evaluation  
In this paper we describe the three approaches we submitted to the Semantic Textual Similarity task of SemEval 2012.  ...  The first approach considers to calculate the semantic similarity by using the Jaccard coefficient with term expansion using synonyms.  ...  In this paper, we present three different approaches for the Textual Semantic Similarity task of Semeval 2012 (Agirre et al., 2012) .  ... 
dblp:conf/semeval/CarrilloVPTLC12 fatcat:e35jx7yjtnc3dnmtj3opfsxsbq

PolyUCOMP: Combining Semantic Vectors with Skip bigrams for Semantic Textual Similarity

Jian Xu, Qin Lu, Zhengzhong Liu
2012 International Workshop on Semantic Evaluation  
This paper presents the work of the Hong Kong Polytechnic University (PolyUCOMP) team which has participated in the Semantic Textual Similarity task of SemEval-2012.  ...  The PolyUCOMP system combines semantic vectors with skip bigrams to determine sentence similarity.  ...  The SemEval 2012 competition includes a task targeted at Semantic Textual Similarity (STS) between sentence pairs (Eneko et al., 2012) .  ... 
dblp:conf/semeval/XuLL12 fatcat:jaaizosabjh5fkgcqtgjtldtke

Look, Read and Enrich. Learning from Scientific Figures and their Captions [article]

Jose Manuel Gomez-Perez, Raul Ortega
2019 arXiv   pre-print
supervised baselines and ad-hoc approaches.  ...  We also show that transferring lexical and semantic knowledge from a knowledge graph significantly enriches the resulting features.  ...  While direct combination provides a notion of the agreement between the two branches, supervised pre-training is the most similar supervised approach to our method.  ... 
arXiv:1909.09070v1 fatcat:zhlscpvkmneylinylv7c5xjcji

Generalizing Cross-Document Event Coreference Resolution Across Multiple Corpora [article]

Michael Bugert and Nils Reimers and Iryna Gurevych
2021 arXiv   pre-print
We compare a corpus-independent, feature-based system against a recent neural system developed for ECB+.  ...  To investigate this assumption, we define a uniform evaluation setup involving three CDCR corpora: ECB+, the Gun Violence Corpus and the Football Coreference Corpus (which we reannotate on token level  ...  Special thanks are due to Jan-Christoph Klie and Nafise Sadat Moosavi for the frequent exchange of ideas.  ... 
arXiv:2011.12249v2 fatcat:6mbqk25lvbdmzhpsjmicx6274a

Generalizing Cross-Document Event Coreference Resolution Across Multiple Corpora

Michael Bugert, Nils Reimers, Iryna Gurevych
2021 Computational Linguistics  
We compare a corpus-independent, feature-based system against a recent neural system developed for ECB+.  ...  To investigate this assumption, we define a uniform evaluation setup involving three CDCR corpora: ECB+, the Gun Violence Corpus and the Football Coreference Corpus (which we reannotate on token level  ...  Acknowledgments We thank Mohsen Mesgar, Kevin Stowe, Prasetya Ajie Utama and Mingzhu Wu for their helpful comments.  ... 
doi:10.1162/coli_a_00407 fatcat:wuyugyp4kbbnlplpzmcni7rz7i

Building Multi-model Collaboration in Detecting Multimedia Semantic Concepts

Hsin-Yu Ha, Fausto Fleites, Shu-Ching Chen
2013 Proceedings of the 9th IEEE International Conference on Collaborative Computing: Networking, Applications and Worksharing  
It is further applied with the logistic regression method to refine ARC fusion method proposed in our previous work for semantic concept detection.  ...  After combining features from multiple modalities, each classification model is built on one feature cluster, which is generated from our previous work FCC-MMF.  ...  Usually, each modality is analyzed independently, so it has the flexibility to select the most suitable approach for different modalities, such as latent semantic Index (LSI) for textual modality, and  ... 
doi:10.4108/icst.collaboratecom.2013.254110 dblp:conf/colcom/HaFC13 fatcat:bddsyn2cajgk7h675s5m34hddm

Judicial diplomacy of the German Federal Constitutional Court: bilateral court meetings as a novel data source to assess transnational communication of constitutional courts

Philipp Meyer
2021 Zeitschrift für Vergleichende Politikwissenschaft  
This study presents a novel approach to assess such meetings. It analyses the German Federal Constitutional Court meeting reports between 1998–2019, using content and semantic network analysis.  ...  Bilateral court meetings are essential for judicial diplomacy, encompassing jurisprudential (e.g., discussion of case law) and aims of strategic (e.g., maximising influence).  ...  Semantic networks of meeting reports Fig. 5 illustrates the semantic network of the FCC meeting reports. Semantic networks are graphical illustrations of the proximity of word occurrences.  ... 
doi:10.1007/s12286-021-00499-0 fatcat:up6v6gyerrfv5dajzc4iz7t4uq

Using Fuzzy Logic to Leverage HTML Markup for Web Page Representation [article]

Alberto P. García-Plaza and Víctor Fresno and Raquel Martínez and Arkaitz Zubiaga
2016 arXiv   pre-print
In this paper we introduce a fuzzy term weighing approach that makes the most of the HTML structure for document clustering.  ...  Our proposed approach, called Abstract Fuzzy Combination of Criteria (AFCC), can adapt to datasets whose features are distributed differently, achieving good results compared to other similar fuzzy logic  ...  ACKNOWLEDGMENT The authors would like to thank the anonymous reviewers for their valuable comments and suggestions to improve the quality of the paper.  ... 
arXiv:1606.04429v1 fatcat:ktd6knlh55dkzafkiohblme46y

Using Fuzzy Logic to Leverage HTML Markup for Web Page Representation

Alberto P. Garcia-Plaza, Victor Fresno, Raquel Martinez Unanue, Arkaitz Zubiaga
2017 IEEE transactions on fuzzy systems  
ACKNOWLEDGMENT The authors would like to thank the anonymous reviewers for their valuable comments and suggestions to improve the quality of the paper.  ...  ., plain textual content, titles, or hyperlinks. There are mainly three different approaches. First, content based, which make use of the textual content of documents.  ...  Building on the state-of-the-art unsupervised fuzzy logic approach for HTML document representation [2] , known as Fuzzy Combinations of Criteria (FCC), we propose three alternative approaches, namely  ... 
doi:10.1109/tfuzz.2016.2586971 fatcat:lrzsskroxbew5otzvvzcacjqb4

Learning a taxonomy from a set of text documents

Mari-Sanna Paukkeri, Alberto Pérez García-Plaza, Víctor Fresno, Raquel Martínez Unanue, Timo Honkela
2012 Applied Soft Computing  
Three different feature extraction approaches with varying degree of language independence are compared in this study.  ...  The third approach is the traditional tf-idf weighting scheme with commonly used rulebased stemming. Experiments are conducted for the English, Finnish, and Spanish languages.  ...  Other similar approaches used for taxonomy learning are, e.g., [16, 17] .  ... 
doi:10.1016/j.asoc.2011.11.009 fatcat:qxond2lfpzhehm3nt7ugcsqsge

Investigating the readability of state-based formal requirements specification languages

Marc K. Zimmerman, Kristina Lundqvist, Nancy Leveson
2002 Proceedings of the 24th international conference on Software engineering - ICSE '02  
It can serve as a starting point for more thorough and carefully controlled experimentation in specification language readability.  ...  For example, when subjects are given three different specifications testing the readability of a certain feature, we wanted the types of questions asked about the three specifications to be as similar  ...  Textual notation The textual expression reads as straightforward English text.  ... 
doi:10.1145/581344.581347 fatcat:b7gngxw33zhb3pipeah777d6bu

Investigating the readability of state-based formal requirements specification languages

Marc K. Zimmerman, Kristina Lundqvist, Nancy Leveson
2002 Proceedings of the 24th international conference on Software engineering - ICSE '02  
It can serve as a starting point for more thorough and carefully controlled experimentation in specification language readability.  ...  For example, when subjects are given three different specifications testing the readability of a certain feature, we wanted the types of questions asked about the three specifications to be as similar  ...  Textual notation The textual expression reads as straightforward English text.  ... 
doi:10.1145/581339.581347 dblp:conf/icse/ZimmermanLL02 fatcat:qpm5q3hxgnhk5eazehnbeaq6rq

Zoonymic Peculiarity in Feature Cartoons for Children

Анастасія Кузьменко
2019 Психолінгвістика  
be analyzed, such as induction and deduction, analysis and synthesis, abstraction and concretization; longitudinal, processing and interpretation methods; psycholinguistic analysis; method of context-semantic  ...  Materials for the research are gathered from Paramount Pictures production, Dream Works animation, Universal Studio, Walt Disney production and the selection is the English feature cartoons for children  ...  The lingvopsychological approach to this problematic study has led to selection of methods such as longitudinal (for monitoring the components of speech activity in the FCC), processing and interpretation  ... 
doi:10.31470/2309-1797-2019-26-2-190-207 fatcat:fjvjqhdvsrdkvdmrzg4vty2tlu

ROSF: Leveraging Information Retrieval and Supervised Learning for Recommending Code Snippets

He Jiang, Liming Nie, Zeyi Sun, Zhilei Ren, Weiqiang Kong, Tao Zhang, Xiapu Luo
2016 IEEE Transactions on Services Computing  
For providing high-quality code examples, previous studies present several methods to recommend code snippets mainly based on information retrieval.  ...  In our method, we recommend Top-Kcode snippets for a givenfree-form query based on two stages, i.e., coarse-grained searching and fine-grained re-ranking.  ...  Intuitively, the terms are textual, visible, while the topics are semantic, latent. They can complement each other to achieve better performance for text matching tasks [24] .  ... 
doi:10.1109/tsc.2016.2592909 fatcat:mlbzhm54v5gdtenfubr6jegsya

Generating and Measuring Similar Sentences using Long Short-Term Memory and Generative Adversarial Networks

Zhiyao Liang, Shiru Zhang
2021 IEEE Access  
ACKNOWLEDGMENT The authors would like to thank the anonymous reviewers for their valuable remarks and comments.  ...  We address the similarity between two sentences regarding their semantics through the machine-learning approach using neural networks.  ...  Currently, the website of nlprogress.com mentions MT-DNN as the second-best solution for the task of textual similarity, while the best is XLNet.  ... 
doi:10.1109/access.2021.3103669 fatcat:gfgi4gmr3nevppuvana2tuupb4
« Previous Showing results 1 — 15 out of 337 results