Suchergebnisse

[EN] Template extraction is the process of isolating the template of a given webpage. It is widely used in several disciplines, including webpages development, content extraction, block detection, and webpages indexing. One of the main goals of template extraction is identifying a set of webpages with the same template without having to load and analyze too many webpages prior to identifying the template. This work introduces a new technique to automatically discover a reduced set of webpages in a website that implement the template. This set is computed with an hyperlink analysis that computes a very small set with a high level of confidence. ; This work has been partially supported by the Spanish Ministerio de Econom´ıa y Competitividad (Secretar´ıa de Estado de Investigacion, Desarrollo e Innovaci ´ on) ´ under grant TIN2013-44742-C4-1-R and by the Generalitat Valenciana under grant PROMETEO/2011/052. David Insa was partially supported by the Spanish Ministerio de Eduacion under FPU grant AP2010-4415. Salvador Tamarit was partially supported by research project POLCA, Programming Large Scale Heterogeneous Infrastructures (610686), funded by the European Union, STREP FP7. ; Alarte, J.; Insa Cabrera, D.; Silva Galiana, JF.; Tamarit Muñoz, S. (2014). Automatic detection of webpages that share the same web template. Electronic Proceedings in Theoretical Computer Science. 163:2-15. https://doi.org/10.4204/EPTCS.163.2 ; S ; 2 ; 15 ; 163

[EN] Simultaneous machine translation has recently gained traction thanks to significant quality improvements and the advent of streaming applications. Simultaneous translation systems need to find a trade-off between translation quality and response time, and with this purpose multiple latency measures have been proposed. However, latency evaluations for simultaneous translation are estimated at the sentence level, not taking into account the sequential nature of a streaming scenario. Indeed, these sentence-level latency measures are not well suited for continuous stream translation, resulting in figures that are not coherent with the simultaneous translation policy of the system being assessed. This work proposes a stream-level adaptation of the current latency measures based on a re-segmentation approach applied to the output translation, that is successfully evaluated on streaming conditions for a reference IWSLT task. ; The research leading to these results has received funding from the European Union's Horizon 2020 research and innovation program under grant agreement no. 761758 (X5Gon) and 952215 (TAILOR) and Erasmus+ Education program under grant agreement no. 20-226-093604-SCH; the Government of Spain's research project Multisub, ref. RTI2018-094879-B-I00 (MCIU/AEI/FEDER,EU) and FPU scholarships FPU18/04135; and the Generalitat Valenciana's research project Classroom Activity Recognition, ref. PROMETEO/2019/111. ; Iranzo-Sánchez, J.; Civera Saiz, J.; Juan, A. (2021). Stream-level Latency Evaluation for Simultaneous Machine Translation. The Association for Computational Linguistics. 664-670. http://hdl.handle.net/10251/182203 ; S ; 664 ; 670

[EN] The widespread use of experimental benchmarks in AI research has created competition and collaboration dynamics that are still poorly understood. Here we provide an innovative methodology to explore these dynamics and analyse the way different entrants in these challenges, from academia to tech giants, behave and react depending on their own or others' achievements. We perform an analysis of 25 popular benchmarks in AI from Papers With Code, with around 2,000 result entries overall, connected with their underlying research papers. We identify links between researchers and institutions (that is, communities) beyond the standard co-authorship relations, and we explore a series of hypotheses about their behaviour as well as some aggregated results in terms of activity, performance jumps and efficiency. We characterize the dynamics of research communities at different levels of abstraction, including organization, affiliation, trajectories, results and activity. We find that hybrid, multi-institution and persevering communities are more likely to improve state-of-the-art performance, which becomes a watershed for many community members. Although the results cannot be extrapolated beyond our selection of popular machine learning benchmarks, the methodology can be extended to other areas of artificial intelligence or robotics, and combined with bibliometric studies. ; F.M.-P. acknowledges funding from the AI-Watch project by DG CONNECT and DG JRC of the European Commission. J.H.-O. and S.O.h. were funded by the Future of Life Institute, FLI, under grant RFP2-152. J.H.-O. was supported by the EU (FEDER) and Spanish MINECO under RTI2018-094403-B-C32, Generalitat Valenciana under PROMETEO/2019/098 and European Union's Horizon 2020 grant no. 952215 (TAILOR). ; Martínez-Plumed, F.; Barredo, P.; Ó Héigeartaigh, S.; Hernández-Orallo, J. (2021). Research community dynamics behind popular AI benchmarks. Nature Machine Intelligence. 3(7):581-589. https://doi.org/10.1038/s42256-021-00339-6 ; S ; 581 ; 589 ; 3 ; 7

This work has been developed with the financial support of the European Union's Horizon 2020 research and innovation programme under grant agreement No. 824231 ; Gil Pascual, M.; Pastor-Ricós, F.; Torres Bosch, MV.; Vos, TE. (2020). DECODER - DEveloper COmpanion for Documented and annotatEd code Reference. Springer. 643-644. http://hdl.handle.net/10251/178910 ; S ; 643 ; 644

[EN] This paper describes the participation of the MLLP research group of the Universitat Politècnica de València in the WMT 2019 Similar Language Translation Shared Task. We have submitted systems for the Portuguese ↔ Spanish language pair, in both directions. We have submitted systems based on the Transformer architecture as well as an in development novel architecture which we have called 2D alternating RNN. We have carried out domain adaptation through fine-tuning. ; The research leading to these results has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement no. 761758 (X5gon); the Government of Spain's research project Multisub, ref. RTI2018-094879-B-I00 (MCIU/AEI/FEDER, EU) and the Generalitat Valenciana's predoctoral research scholarship ACIF/2017/055. ; Baquero-Arnal, P.; Iranzo-Sánchez, J.; Civera Saiz, J.; Juan, A. (2019). The MLLP-UPV Spanish-Portuguese and Portuguese-Spanish Machine Translation Systems for WMT19 Similar Language Translation Task. The Association for Computational Linguistics. 179-184. http://hdl.handle.net/10251/180621 ; S ; 179 ; 184

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-642-54624-2_12 ; Trace inspection is concerned with techniques that allow the trace content to be searched for specific components. This paper presents a rich and highly dynamic, parameterized technique for the trace inspection of Rewriting Logic theories that allows the non-deterministic execution of a given unconditional rewrite theory to be followed up in different ways. Using this technique, an analyst can browse, slice, filter, or search the traces as they come to life during the program execution. Starting from a selected state in the computation tree, the navigation of the trace is driven by a user-defined, inspection criterion that specifies the required exploration mode. By selecting different inspection criteria, one can automatically derive a family of practical algorithms such as program steppers and more sophisticated dynamic trace slicers that facilitate the dynamic detection of control and data dependencies across the computation tree. Our methodology, which is implemented in the Anima graphical tool, allows users to capture the impact of a given criterion thereby facilitating the detection of improper program behaviors. ; This work has been partially supported by the EU (FEDER), the Spanish MEC project ref. TIN2010-21062-C02-02, the Spanish MICINN complementary action ref. TIN2009-07495-E, and by Generalitat Valenciana ref. PROMETEO2011/052. This work was carried out during the tenure of D. Ballis' ERCIM "Alain Bensoussan "Postdoctoral Fellowship. The research leading to these results has received funding from the European Union Seventh Framework Programme (FP7/2007-2013) under grant agreement n. 246016. F. Frechina was supported by FPU-ME grant AP2010-5681. ; Alpuente Frasnedo, M.; Ballis, D.; Frechina, F.; Sapiña Sanchis, J. (2014). Inspecting rewriting logic computations (in a parametric and stepwise way). En Specification, algebra, and software: essays dedicated to Kokichi Futatsugi. Springer Verlag (Germany). ...

[EN] Privacy has been a concern for humans long before the explosive growth of the Internet. The advances in information technologies have further increased these concerns. This is because the increasing power and sophistication of computer applications offers both tremendous opportunities for individuals, but also significant threats to personal privacy. Autonomous agents and multi-agent systems are examples of the level of sophistication of computer applications. Autonomous agents usually encapsulate personal information describing their principals, and therefore they play a crucial role in preserving privacy. Moreover, autonomous agents themselves can be used to increase the privacy of computer applications by taking advantage of the intrinsic features they provide, such as artificial intelligence, pro-activeness, autonomy, and the like. This article introduces the problem of preserving privacy in computer applications and its relation to autonomous agents and multi-agent systems. It also surveys privacy-related studies in the field of multi-agent systems and identifies open challenges to be addressed by future research. ; This work has been partially supported by CONSOLIDER-INGENIO 2010 under grant CSD2007-00022, and project TIN2011-27652-C03-00 of the Spanish Government. ; Such Aparicio, JM.; Espinosa Minguet, AR.; García-Fornes, A. (2014). A survey of privacy in multi-agent systems. The Knowledge Engineering Review. 29(3):314-344. doi:10.1017/S0269888913000180 ; S ; 314 ; 344 ; 29 ; 3

In this paper, we present the systems that the Natural Language Engineering and Pattern Recognition group (ELiRF) has submitted to the MediaEval 2013 Spoken Web Search task. All of them are based on a Subsequence Dynamic Time Warping algorithm and are zero-resources systems. ; Work funded by the Spanish Government and the E.U. under contract TIN2011-28169-C05 and FPU Grant AP2010- 4193. ; Gómez Adrian, JA.; Hurtado Oliver, LF.; Calvo Lance, M.; Sanchís Arnal, E. (2013). ELIRF at MEDIAEVAL 2013: Spoken Web Search Task. CEUR Workshop Proceedings. 1042:59-60. http://hdl.handle.net/10251/38157 ; S ; 59 ; 60 ; 1042

This paper describes the Natural Language Engineering and Pattern Recognition group (ELiRF) approaches and results towards the Similar Segments of Social Speech Task of Me- diaEval 2013. The task involves finding segments similar to a query segment in a multimedia collection of informal, un- structured dialogs among members of a small community. Our approach has two phases. In a first phase a preprocess of the sentences is performed based on the morphology and semantics of the words. In a second phase, a searching pro- cess based on different distance measures is carried out. This has been done taking the correctly transcribed sentences and the output of an Automatic Speech Recognizer. ; Work funded by the Spanish Government and the E.U. under the contracts TIN2011-28169-C05 and TIN2012-38603- C02, and FPU Grant AP2010-4193 ; García Granada, F.; Sanchís Arnal, E.; Calvo Lance, M.; Pla Santamaría, F.; Hurtado Oliver, LF. (2013). ELIRF at MEDIAEVAL 2013: Similar Segments of Social Speech Task. CEUR Workshop Proceedings. 1043:135-136. http://hdl.handle.net/10251/38151 ; S ; 135 ; 136 ; 1043

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-642-40087-2_6 ; The development of models for automatic detection of text re-use and plagiarism across languages has received increasing attention in recent years. However, the lack of an evaluation framework composed of annotated datasets has caused these efforts to be isolated. In this paper we present the CL!TR 2011 corpus, the first manually created corpus for the analysis of cross-language text re-use between English and Hindi. The corpus was used during the Cross-Language !ndian Text Re-Use Detection Competition. Here we overview the approaches applied the contestants and evaluate their quality when detecting a re-used text together with its source. ; This research work is partially funded by the WIQ-EI (IRSES grant n. 269180)and ACCURAT (grant n. 248347) projects, and the Seventh Framework Programme (FP7/2007-2013) under grant agreement n. 246016 from the European Union. The first author was partially funded by the CONACyT-Mexico 192021 grant and currently works under the ERCIM "Alain Bensoussan" Fellowship Programme. The research of the second author is in the framework of the VLC/Campus Microcluster on Multimodal Interaction in Intelligent Systems and partially funded by the MICINN research project TEXT-ENTERPRISE 2.0 TIN2009-13391-C04-03 (plan I+D+i). The research from AU-KBC Centre is supported by the Cross Lingual Information Access (CLIA) Phase II Project. ; Barrón Cedeño, LA.; Rosso ., P.; Sobha, LD.; Clough ., P.; Stevenson ., M. (2013). PAN@FIRE: Overview of the cross-language !ndian Text re-use detection competition. En Multilingual Information Access in South Asian Languages. Springer Verlag (Germany). 7536:59-70. https://doi.org/10.1007/978-3-642-40087-2_6 ; S ; 59 ; 70 ; 7536 ; Addanki, K., Wu, D.: An Evaluation of MT Alignment Baseline Approaches upon Cross-Lingual Plagiarism Detection. In: FIRE [12] ; Aggarwal, N., Asooja, K., Buitelaar, P.: Cross Lingual Text Reuse Detection Using Machine Translation & ...

"The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-642-21257-4_85 ; To date, automatic handwriting text recognition systems are far from being perfect and heavy human intervention is often required to check and correct the results of such systems. As an alternative, an interactive framework that integrates the human knowledge into the transcription process has been presented in previous works. In this work, multimodal interaction at character-level is studied. Until now, multimodal interaction had been studied only at whole-word level. However, character-level pen-stroke interactions may lead to more ergonomic and friendly interfaces. Empirical tests show that this approach can save significant amounts of user effort with respect to both fully manual transcription and non-interactive post-editing correction. ; Work supported by the Spanish Government (MICINN and "Plan E") under the MITTRAL (TIN2009-14633-C03-01) research project and under the research programme Consolider Ingenio 2010: MIPRCV (CSD2007-00018), and by the Generalitat Valenciana under grant Prometeo/2009/014. ; Martín-Albo Simón, D.; Romero Gómez, V.; Toselli ., AH.; Vidal, E. (2011). Character-level interaction in multimodal computer-assisted transcription of text images. En Pattern Recognition and Image Analysis. Springer Verlag (Germany). 684-691. https://doi.org/10.1007/978-3-642-21257-4 ; S ; 684 ; 691

According to Torres Hostench et al. (2016), the use of machine translation (MT) in Catalan and Spanish translation companies is low. Based on these results, the Tradumàtica research group, through the ProjecTA and ProjecTA-U projects, set to bring MT and translators closer with a two-fold strategy. On the one hand, by developing MTradumàtica, a free Moses-based web platform with graphical user interface (GUI) for statistical machine translation (SMT) trainers. On the other hand, by including MT-related contents in translators' training. This paper will describe the latest developments in MTradumàtica. ; Funded by the Ministerio de Economía y Competitividad of the Spanish government (Ref: FFI2013-46041-R and FFI2016-78612-R). www.projecta.tradumatica.net.

[EN] The paper is concerned with the consensus problem in a multi-agent system such that each agent has boundary constraints. Classical Olfati-Saber's consensus algorithm converges to the same value of the consensus variable, and all the agents reach the same value. These algorithms find an equality solution. However, what happens when this equality solution is out of the range of some of the agents? In this case, this solution is not adequate for the proposed problem. In this paper, we propose a new kind of algorithms called supportive consensus where some agents of the network can compensate for the lack of capacity of other agents to reach the average value, and so obtain an acceptable solution for the proposed problem. Supportive consensus finds an equity solution. In the rest of the paper, we define the supportive consensus, analyze and demonstrate the network's capacity to compensate out of boundaries agents, propose different supportive consensus algorithms, and finally, provide some simulations to show the performance of the proposed algorithms. ; The author(s) received specific funding for this work from the Valencian Research Institute for Artificial Intelligence (VRAIN) where the authors are currently working. This work is partially supported by the Spanish Government project RTI2018-095390-B-C31, GVA-CEICE project PROMETEO/2018/002, and TAILOR, a project funded by EU Horizon 2020 research and innovation programme under GA No 952215. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. ; Palomares Chust, A.; Rebollo Pedruelo, M.; Carrascosa Casamayor, C. (2020). Supportive consensus. PLoS ONE. 15(12):1-30. https://doi.org/10.1371/journal.pone.0243215 ; S ; 1 ; 30 ; 15 ; 12 ; Olfati-Saber, R., Fax, J. A., & Murray, R. M. (2007). Consensus and Cooperation in Networked Multi-Agent Systems. Proceedings of the IEEE, 95(1), 215-233. doi:10.1109/jproc.2006.887293 ; Pérez, I. J., Cabrerizo, F. J., Alonso, S., Dong, Y. C., Chiclana, ...

The overall machine translation quality available for professional translators working with the Spanish–Basque pair is rather poor, which is a deterrent for its adoption. This work investigates the plausibility of building a comprehensive recommendation system to speed up decision time between post-editing or translation from scratch using the very limited training data available. First, we build a set of regression models that predict the post-editing effort in terms of overall quality, time and edits. Secondly, we build classification models that recommend the most efficient editing approach using post-editing effort features on top of linguistic features. Results show high correlations between the predictions of the regression models and the expected HTER, time and edit number values. Similarly, the results for the classifiers show that they are able to predict with high accuracy whether it is more efficient to translate or to post-edit a new segment. ; The research leading to this work was partially funded by the TIN2015-70214-P project (MINECO-FEDER) and the KK-2017/00094 project (Basque Government).

While systems using the Neural Network-based Machine Translation (NMT) paradigm achieve the highest scores on recent shared tasks, phrase-based (PBMT) systems, rule-based (RBMT) systems and other systems may get better results for individual examples. Therefore, combined systems should achieve the best results for MT, particularly if the system combination method can take advantage of the strengths of each paradigm. In this paper, we describe a system that predicts whether a NMT, PBMT or RBMT will get the best Spanish translation result for a particular English sentence in DGT-TM 20161. Then we use fuzzy-match repair (FMR) as a mechanism to show that the combined system outperforms individual systems in a black-box machine translation setting. ; John E. Ortega is supported by the Universitat d'Alacant and the Spanish government through the EFFORTUNE (TIN2015-69632-R) project. Kyunghyun Cho was partly supported by Samsung Advanced Institute of Technology (Next Generation Deep Learning: from pattern recognition to AI) and Samsung Electronics (Improving Deep Learning using Latent Structure).