57 Hits in 7.3 sec

Improving scalability of inductive logic programming via pruning and best-effort optimisation

Mishal Kazmi, Peter Schüller, Yücel Saygın
2017 Expert systems with applications  
With respect to processing natural language, ILP can cater for the constant change in how we use language on a daily basis.  ...  Results show that our improvements allow for learning on bigger datasets with results that are of similar quality to state-of-the-art systems on the same task.  ...  We are grateful to Carmine Dodaro for providing us with support regarding the WASP solver.  ... 
doi:10.1016/j.eswa.2017.06.013 fatcat:mi7unvggkrhezklwzf6nsnerhm

Maps of Lessons Learnt in Requirements Engineering: A Research Preview [chapter]

Ibtehal Noorwali, Nazim H. Madhavji
2013 Lecture Notes in Computer Science  
Such maps would thus be: (a) a driver for research to "light up" the darker areas of RE and (b) a guide for practice to benefit from the brighter areas.  ...  Both researchers and practitioners have emphasized the importance of learning from past experiences and its consequential impact on project time, cost, and quality.  ...  Acknowledgements First and foremost, my sincere thanks go to Professor Nazim Madhavji for his continuous guidance, supervision, and encouragement during the course of my research.  ... 
doi:10.1007/978-3-642-37422-7_9 fatcat:m67nibzpmna6rmedkg2rmy3zwu

Recognizing Textual Entailment [chapter]

Mark Sammons
2015 The Handbook of Contemporary Semantic Theory  
In section 1.4, where we discuss key research investigating different approaches to RTE, we map each line of research to our framework at a high level (for full implementation details, the reader is referred  ...  EVALITA, an Italian NLP evaluation program run by FBK-Irst of Trento, Italy, assesses NLP technologies for the Italian language on a range of problems that includes Recognizing Textual Entailment.  ... 
doi:10.1002/9781118882139.ch17 fatcat:h5hpwxywa5gc7nyenwmsq3wlay

Scientific Review Paper

Maria Eskevich, Antal van den Bosch
2017 Zenodo  
This report provides information about the work on the scientific review paper that gives a critical review of the past, present and future of the state-of-the-art of the field of text and data mining  ...  This publication aims to broaden perspective on the past, current, and future trends in TDM amongst audience, outlined via desktop research, consultation with the practitioners (Deliverables D.4.3. and  ...  , and reports on work in progress.  ... 
doi:10.5281/zenodo.1240763 fatcat:r47vdutlo5ca3lfjdig5wv4fyq

H2020 692819 Simpatico - D1.3: Data Management Plan V1

Matteo Gerosa, Serena Bressan, Marco Pistore
2017 Zenodo  
A revised deliverable is expected at the end of the project ("D1.4 – Data management plan v.2", at M36). However, the DMP will be a living do [...]  ...  SIMPATICO takes part in the Open Research Data Pilot (ORD pilot); this pilot aims to improve and maximise access to and re-use of research data generated by Horizon 2020 projects, such as the data generated  ...  and reports, providing on-line access to scientific information that is free of charge to the reader [9] .  ... 
doi:10.5281/zenodo.1040817 fatcat:2otghrrjcjajngo2j6kaad4wr4

Extracting Temporal and Causal Relations between Events [article]

Paramita Mirza
2016 arXiv   pre-print
Finally, we report our adaptation efforts of temporal information processing for languages other than English, namely Italian and Indonesian.  ...  In this thesis we present a framework for an integrated temporal and causal relation extraction system.  ...  -Charlemagne Research on temporal information processing has been gaining a lot of attention from the NLP community, but most research efforts have focused only on English.  ... 
arXiv:1604.08120v1 fatcat:fmd7z6hwyjhgphbrnc3mgpifde

The EVALITA Dependency Parsing Task: From 2007 to 2011 [chapter]

Cristina Bosco, Alessandro Mazzei
2013 Lecture Notes in Computer Science  
establish a reference forum for research on Computational Linguistics of the Italian community with contributions from a wide range of disciplines going from Computational Linguistics, Linguistics and  ...  Following the success of previous editions, we organized EVALITA 2014, the fourth evaluation campaign with the aim of continuing to provide a forum for the comparison and evaluation of research outcomes  ...  This research is part of the HDOMO 2.0 project founded by the National Research Centre on Aging (INRCA) in partnership with the Government of the Marche region under the action "Smart Home for Active and  ... 
doi:10.1007/978-3-642-35828-9_1 fatcat:p6dyjaxm4zbitfajtciwclwipu

Structured data and inference in DeepQA

A. Kalyanpur, B. K. Boguraev, S. Patwardhan, J. W. Murdock, A. Lally, C. Welty, J. M. Prager, B. Coppola, A. Fokoue-Nkoutche, L. Zhang, Y. Pan, Z. M. Qiu
2012 IBM Journal of Research and Development  
The DeepQA system does not contain a single monolithic structured data module; instead, it allows for different components to use and integrate structured and semistructured data, with varying degrees  ...  We present details of appropriate components and demonstrate their end-to-end impact on the IBM Watsoni system.  ...  He has been a Research Assistant at FBK-Irst and a Post-Doctoral Researcher at University of Trento, and he coauthored more than 15 technical papers in human language technology.  ... 
doi:10.1147/jrd.2012.2188737 fatcat:uwnsuladcvam3jxavej5baw6mq

Findings of the 2014 Workshop on Statistical Machine Translation

Ondrej Bojar, Christian Buck, Christian Federmann, Barry Haddow, Philipp Koehn, Johannes Leveling, Christof Monz, Pavel Pecina, Matt Post, Herve Saint-Amand, Radu Soricut, Lucia Specia (+1 others)
2014 Proceedings of the Ninth Workshop on Statistical Machine Translation  
We present the results of the WMT13 shared tasks, which included a translation task, a task for run-time estimation of machine translation quality, and an unofficial metrics task.  ...  We created a test set for each language pair by translating newspaper articles and provided training data.  ...  We would also like to thank our colleagues Matouš Macháček and Martin Popel for detailed discussions.  ... 
doi:10.3115/v1/w14-3302 dblp:conf/wmt/BojarBFHKLMPPSS14 fatcat:m6oq63m3zbhxhee2h7pvsqw2ce

A Multi-Lingually Applicable Journalist Toolset For The Big-Data Era

G. Kiomourtzis, G. Giannakopoulos, V. Karkaletsis, A. Kosmopoulos
2016 Zenodo  
This research was supported in part by a Discovery and Innovation Research Seed award from the Office of the Vice Provost for Research at Cornell.  ...  Acknowledgments This work was supported by REVEAL 5 project, which has received funding by the European Unions 7th Framework Program for research, technology development and demonstration under the Grant  ...  union or other union, re- search (either climate research or other), technology, and other. 10.  ... 
doi:10.5281/zenodo.1242850 fatcat:nfkqg7jhjffdvgezdjzc6xxppa

Getting Past the Language Gap: Innovations in Machine Translation [chapter]

Rodolfo Delmonte
2012 Mobile Speech and Advanced Natural Language Solutions  
One research line takes n-best translations of single systems, and produces the final output by means of either sentence-level combination, i.e. a direct selection from original outputs of single SMT systems  ...  The multi-engine approach involves the translation of a given text by two or more different MT architectures (SMT and RBMT, for example) and the integration of outputs for the selection of the 'best' output  ...  Dugast et al. (2007) report research on combining SYSTRAN with PB-SMT systems Moses and Portage.  ... 
doi:10.1007/978-1-4614-6018-3_6 fatcat:2njkc6meabhaxosl4wircumfjm

Exploring convolutional neural networks for drug–drug interaction extraction

Víctor Suárez-Paniagua, Isabel Segura-Bedmar, Paloma Martínez
2017 Database: The Journal of Biological Databases and Curation  
The current state-of-the-art for the extraction of DDIs is based on feature-engineering algorithms (such as support vector machines), which usually require considerable time and effort.  ...  The goal is to determine the best parameter of this basic CNN that should be considered for future research.  ...  Acknowledgements We are grateful to Mr Denny Britz (Google Brain), who was a valuable source of information and advice, to Dr Mar ıa Herrero-Zazo  ... 
doi:10.1093/database/bax019 pmid:28605776 pmcid:PMC5467573 fatcat:m4nkvrmbbbdilj552mxwo3thm4

Comparison of topic extraction approaches and their results

Theresa Velden, Kevin W. Boyack, Jochen Gläser, Rob Koopman, Andrea Scharnhorst, Shenghui Wang
2017 Scientometrics  
Towards a comparative approach to the identification of thematic structures in science. This is the last paper in the Synthesis section of the special issue on 'Same Data, Different Results'.  ...  We conclude with a discussion of future work needed to develop methods for comparison and validation of topic extraction results, and express our concern about the lack of access to non-proprietary benchmark  ...  lively discussions of the topic extraction exercise at the series of workshops held from 2013-2015 in Berlin and Amsterdam.  ... 
doi:10.1007/s11192-017-2306-1 fatcat:ox6ypanwbvad3fyg7pdainxule

Discourse in Statistical Machine Translation

Christian Hardmeier
2012 Discours  
We demonstrate the viability of this decoding approach for different document-level models. From a linguistic viewpoint, we focus on the problem of translating pronominal anaphora.  ...  From a technical viewpoint, the main contribution of our work is the development of a document-level decoder based on stochastic local search that translates a complete document as a single unit.  ...  After each adjustment, the learning rate is held constant for at least 6 epochs (lines 22-31).  ... 
doi:10.4000/discours.8726 fatcat:gxkpd2ubvzbjna7f7hw62oicg4

The EVALITA 2016 Event Factuality Annotation Task (FactA) [chapter]

Anne-Lyse Minard, Manuela Speranza, Tommaso Caselli
EVALITA. Evaluation of NLP and Speech Tools for Italian  
The suite has been designed so that it can integrate and reuse existing state of the art NLP components developed by researchers at FBK (HLT group) as much as possible.  ...  This module is part of TextPro pipeline, a multilingual NLP pipeline developed at FBK.  ... 
doi:10.4000/books.aaccademia.1934 fatcat:jzhf37untvcrfdhni3j5llxaca
« Previous Showing results 1 — 15 out of 57 results