DKPro (Darmstadt Knowledge Processing) 2015


Darmstadt Knowledge Processing Software Repository

Resources:

  • code.google.com/p/csniper .. is a search-based annotation tool to help distributed annotation teams finding infrequent linguistic phenomena in large corpora.
  • code.google.com/p/dkpro-core-asl .. provides a set of ready to use software components for natural language processing, based on the Apache UIMA framework.
  • code.google.com/p/dkpro-lab .. is a lightweight framework for parameter sweeping experiments. It allows you to set up experiments consisting of multiple interdependent tasks in a declarative manner with minimal overhead.
  • code.google.com/p/dkpro-lsr .. (Lexical Semantic Resources) is a unified API for several lexical-semantic resources.
  • code.google.com/p/dkpro-similarity-asl .. is an open source software package for developing text similarity algorithms.
  • code.google.com/p/dkpro-spelling-asl .. includes components for real-word spelling error correction and experimental frameworks for mining such errors from the Wikipedia revision history as well as for the “Helping Our Own” shared tasks 2011 and 2012.
  • code.google.com/p/dkpro-statistics .. is a collection of open-licensed statistical tools, currently including correlation and inter-rater agreement methods.
  • code.google.com/p/dkpro-tc .. (Text Classification) is a UIMA-based text classification framework built on top of DKPro Core, DKPro Lab and the Weka Machine Learning Toolkit. It is intended to alleviate supervised machine learning experiments with any kind of textual data.
  • code.google.com/p/dkpro-wsd .. is a modular, extensible Java framework for word sense disambiguation.
  • code.google.com/p/jowkl .. (Java OmegaWiki Library) is an open-source, Java-based application programming interface that allows to access all information contained in OmegaWiki, such as glosses, usage examples, translations and much more.
  • code.google.com/p/jwktl .. (Java Wiktionary Library) is a free, Java-based application programming interface that allows to access the information contained in Wiktionary.
  • code.google.com/p/jwpl .. (Java Wikipedia Library) is a free, Java-based application programming interface that allows to access all information contained in Wikipedia.
  • code.google.com/p/uby .. is a free, Java-based application programming interface that allows to access all information contained in UBY, a large-scale lexical-semantic resource for NLP based on ISO LMF.
  • code.google.com/p/webanno .. is a general purpose web-based annotation tool for a wide range of linguistic annotations.

Wikipedia:

See also:

OpenCalais 2013


Existing Resources for Debating Technologies C Stab, I Habernal – ukp.tu-darmstadt.de … Overview of existing resources (not exhaustive) ? Annotation Tools ? DKPro-argumentation Page 3. 3 … Dr. Iryna Gurevych | Christian Stab & Ivan Habernal | DKPro-argumentation Unified type system for modeling argumentation ? Based on UIMA ? Easy to expand … Related articles

A preliminary evaluation of the impact of syntactic structure in semantic textual similarity and semantic relatedness tasks NPA Vo, O Popescu – NAACL-HLT 2015 Student Research Workshop ( …, 2015 – aclweb.org … Besides the weak baseline, we use DKPro Simi- larity (Bär et al., 2012) as a strong baseline which is an open source software and intended to use as a baseline-system in the share task STS at* SEM 2013. … google. com/p/dkpro-similarity- asl/wiki/SemEval2013 14http://wordnet. … Cited by 1 Related articles All 8 versions

VectorSLU: A continuous word vector approach to answer selection in community question answering systems Y Belinkov, M Mohtarami, S Cyphers… – SemEval-2015, 2015 – anthology.aclweb.org … Our system analyzes questions and answers with a DkPro (Eckart de Castilho and Gurevych, 2014) uimaFIT (Ogren and Bethard, 2009) pipeline. The DkPro OpenNLP (Apache Software Foundation, 2014) segmenter and chunker … Cited by 12 Related articles All 13 versions

Social Media Mining with Natural Language Processing M Abdul-Mageed, M Dickinson – 2015 – scholarworks.iu.edu … i.com/lingpipe/ ? OpenNLP: http://opennlp.apache.org/index.html ? Natural Language Toolkit (NLTK): http://www.nltk.org/ ? Illinois tools: http://cogcomp.cs.illinois.edu/page/software ? DKPro: https://www.ukp.tu-darmstadt.de/research/ current-projects/dkpro/ ? Also includes …

Voltron: A hybrid system for answer validation based on lexical and distance features I Zamanov, N Hateva, M Kraeva, I Yovcheva… – SemEval- …, 2015 – anthology.aclweb.org … and answer. Distance metrics are based on word2vec (Mikolov et al., 2013a) and DKPro Similarity (Bär, et al.),(de Castilho, 2014). 2 … cosine similarity. We use DKPro’s implementation of cosine similarity to achieve this (Bär, et al.). The … Cited by 3 Related articles All 10 versions

Semantic Relatedness and Textual Entailment via Corpus Patterns NPA Vo, F Meylan, O Popescu – pdfs.semanticscholar.org … Finally, we selected 15 features from this system and combined with 18 features extracted by the DKPRO system (Bär et al., 2013), which made a total of 33 features to feed into WEKA machine learning toolkit (Hall et al., 2009) to build a regression model (see Figure 3). The … Related articles All 2 versions

Learning to rank aggregated answers for crossword puzzles M Nicosia, G Barlacchi, A Moschitti – European Conference on Information …, 2015 – Springer … Kernel similarities. These are computed using (i) string kernels applied to clues, and tree kernels applied to structural representations DKPro Similarity (DKP). … References 1. Bär, D., Zesch, T., Gurevych, I.: Dkpro similarity: An open source framework for text simi- larity. … Cited by 2 Related articles All 6 versions

Coping with Uncertainty in Schema Matching: Bayesian Networks and Agent-Based Modeling Approach H Assoudi, H Lounis – International Conference on E-Technologies, 2015 – Springer … To the best of our knowledge, only a few generalized similarity frameworks exist: • DKPro Similarity[30] uses implementations of these existing libraries. … In DKPro Similarity, some string-based measures are based on im- plementations from this library. … Related articles All 4 versions

On the role of discourse markers for discriminating claims and premises in argumentative discourse J Eckle-Kohler, R Kluge, I Gurevych – … of the 2015 Conference on Empirical …, 2015 – Citeseer … We trained three Machine Learning algorithms (Naive Bayes (NB), Random Forests (RF) and Support Vector Machine (SVM)) on the three datasets annotated by the annotators A1, A2 and A3, using 10-fold cross-validation and the DKPro TC framework (Daxenberger et al … Cited by 8 Related articles All 11 versions

CoMiC: Exploring Text Segmentation and Similarity in the English Entrance Exams Task R Ziai, B Rudzewitz – CLEF 2015 Working Notes, 2015 – ceur-ws.org … The whole architecture of our system was realized using the UIMA framework [8], with DKPro Core [3] for the pre-processing components and DKPro Similarity [2] for the similarity metrics. … Table 2. NLP components used in our system via DKPro Core … Cited by 2 Related articles All 2 versions

Task-Independent Features for Automated Essay Grading T Zesch, M Wojatzki, D Scholten-Akoun – Silver Sponsor, 2015 – aclweb.org … 3.3 Essay Grading System In order to ensure a fair comparison, we re- implemented a state-of-the-art essay grading system based on DKPro TC (Daxenberger et al., 2014) 3 which ensures easy reproducibility and replicability. … Cited by 2 Related articles All 9 versions

How Automatic Coding of Short Text Responses Is Able to Enhance Assessment F Zehuer, C Saelzer, F Goldhammer – Annual Conference of the …, 2015 – researchgate.net Page 1. How Automatic Coding of Short Text Responses Is Able to Enhance Assessment AERA, Chicago, IL – April 17, 2015 Zehner, F.?‡, Sälzer, C.?‡ & Goldhammer, F. ‡ (in press). Automatic Coding of Short Text Responses via Clustering in Educational Assessment. … Cited by 1 Related articles

Counting What Counts: Decompounding for Keyphrase Extraction N Erbs, PB Santos, T Zesch, I Gurevych – ACL-IJCNLP 2015, 2015 – aclweb.org … 3.2 Experimental Setup For preprocessing, we rely on components from the DKPro Core framework (Eckart de Castilho and Gurevych, 2014) and on DKPro Lab (de Castilho and Gurevych, 2011) for building ex- perimental pipelines. … Cited by 1 Related articles All 8 versions

Noise or additional information? Leveraging crowdsource annotation item agreement for natural language tasks. EK Jamison, I Gurevych – anthology.aclweb.org … All systems except Affect Recognition were constructed using DKPro Text Classification (Daxenberger et al., 2014), and used Weka’s SMO (Platt, 1999) or SMOreg (Shevade et al., 2000) im- plementations with default parameters, with 10- fold (or 5-fold, for computationally … Cited by 1 Related articles All 8 versions

In defense of word embedding for generic text representation G Lev, B Klein, L Wolf – … Conference on Applications of Natural Language …, 2015 – Springer … The experimental setup used in the STS task [1] was followed, and for technical reasons (availability of DKPro scores) we employ 3 out of the 5 datasets presented: msr-par, msr-vid, and smt-eur. … When combined with the DKPro similarities, state-of-the-art results are obtained. … Cited by 2 Related articles All 6 versions

Short answer grading: When sorting helps and when it doesn’t U Pado, C Kiefer – Proceedings of the 4th workshop on NLP for Computer …, 2015 – ep.liu.se … Table 1 shows the processing steps for an example question. The analysis system uses the DKPro Core (de Castilho and Gurevych, 2014) and DKPro Similarity (Bär, Zesch and Gurevych (2013)) libraries. … 2013. DKPro Similarity: An open source framework for text similarity. … Cited by 2 Related articles All 12 versions

RExtractor: a Robust Information Extractor V Kr?z, B Hladká – Proceedings of NAACL-HLT, 2015 – anthology.aclweb.org … 2 The extraction systems known from literature were evaluated against gold standard data, eg DKPro Keyphrases (Erbs et al., 2014), Relation- Factory (Roth et al., 2014), KELVIN (McNamee et al., 2013), Propminer (Akbik et al., 2013), OL- LIE (Mausam et al., 2012). … Related articles All 8 versions

Hits at tac kbp 2015: Entity discovery and linking, and event nugget detection B Heinzerling, A Judea, M Strube – Proc. Text Analysis Conference ( …, 2015 – nist.gov … HITS’ EDL system is implemented as a UIMA pipeline (Ferrucci and Lally, 2004), using the Stan- ford CoreNLP (Manning et al., 2014) UIMA compo- nents provided by DKPro (Gurevych et al., 2007) for text segmentation, POS tagging, and named entity … Cited by 2

Reducing annotation efforts in supervised short answer scoring T Zesch, M Heilman, A Cahill – Proceedings of the Tenth Workshop on …, 2015 – aclweb.org … 3.2 Scoring System In order to allow for a fair comparison of all ap- proaches, we implement a basic short answer scor- ing system using the DKPro TC (Daxenberger et al., 1In all our experiments, we excluded item# 13 as it has mul- tiple correct answers and is thus an anomaly … Cited by 5 Related articles All 10 versions

The eras and trends of automatic short answer grading S Burrows, I Gurevych, B Stein – International Journal of Artificial …, 2015 – Springer … Bär, D., Zesch, T., Gurevych, I. (2013). DKPro similarity: an open source framework for text similarity. In H. Schuetze, P. Fung, M. Poesio (Eds.), Proceedings of the 51st annual meeting of the association for computational linguistics. System demonstrations (pp. 121–126). … Cited by 25 Related articles All 5 versions

YodaQA: a modular question answering system pipeline P Baudiš – POSTER 2015-19th International Student Conference …, 2015 – ailao.eu … NLP analysis backends are freely interchangeable thanks to the DKPro UIMA interface [8]. For semantic analysis, we also rely heavily on the WordNet lexicon [19]. For a practical illustration of the pipeline processing two particular example questions, please follow Fig. 4 and 5. … Cited by 10 Related articles All 5 versions

Personality profiling of fictional characters using sense-level links between lexical resources L Flekova, I Gurevych – Proceedings of Empirical Methods in Natural …, 2015 – aclweb.org … 4.1 Extraction and assignment of speech We process the book text using freely available components of the DKPro framework (Gurevych et al., 2007). … The classification is performed through the DKPro TC Framework (Daxenberger et al., 2014). … Cited by 4 Related articles All 10 versions

A Network Based Approach for the Visualization and Analysis of Collaboratively Edited Texts T Hecking, HU Hoppe – Proceedings of the Visual …, 2015 – pdfs.semanticscholar.org … language processing components. In this work the DKPro toolkit [7] was used. It is … a tutor. 7. REFERENCES [1] Bär, D., Zesch, T. and Gurevych, I. DKPro Similarity: An Open Source Framework for Text Similarity. In Proceedings of … Cited by 2 Related articles All 2 versions

Where to Begin? Using Network Analytics for the Recommendation of Scientific Papers L Steinert, IA Chounta, HU Hoppe – CYTED-RITOS International Workshop …, 2015 – Springer … text. In this work the implementation provided by DKPro Keyphrases 3 is used. … The similarity is then the percentage of the first text that is covered by tiles. The implementation used was provided by the DKPro Similarity 4 library. In … Cited by 1 Related articles

Distributional Neural Networks for Automatic Resolution of Crossword Puzzles A Severyn, M Nicosia, G Barlacchi… – Volume 2: Short … – anthology.aclweb.org … We compute the following similarity features between clues:(i) tree kernel similarity applied to intra-pairs, ie, between the query and the retrieved clues;(ii) DKPro Simi- larity, which defines features used in the context of the Semantic Textual Similarity (STS) chal- lenge (Bär et al … Cited by 2 Related articles All 14 versions

Inferring and evaluating semantic classes of verbs signaling modality J Eckle-Kohler – arXiv preprint arXiv:1509.03488, 2015 – arxiv.org … We repeated the same analysis for the English version of the classification, using the Reuters- 21578 corpus.10 In order to count the occur- rences of verb lemmas, we used readers and pre- processing components from the DKPro Core col- lection.11 Our verb counting pipeline … Related articles All 3 versions

Modeling of the question answering task in the YodaQA system P Baudiš, J Šedivý – International Conference of the Cross-Language …, 2015 – Springer … YodaQA represents each artifact as a separate UIMA CAS, allow- ing easy parallelization and straightforward leverage of pre-existing NLP UIMA components (via the DKPro interface); as a corollary, we compartmentalize dif- ferent tasks to interchangeable UIMA annotators. … Cited by 4 Related articles All 5 versions

Automatic disambiguation of English puns T Miller, I Gurevych – Proceedings of the 53rd Annual Meeting …, 2015 – anthology.aclweb.org … 3.2 Analysis Our judges agreed on which word was the pun in 1634 out of 1652 cases, a raw agreement of 98.91%. For the agreed cases, we used DKPro Agreement (Meyer et al., 2014) to compute Krip- pendorff’s ? (Krippendorff, 1980) for the sense annotations. … Cited by 2 Related articles All 8 versions

Generic Text Representation for Vision and NLP based on Neural Word Embedding G Lev – 2015 – cs.tau.ac.il Page 1. Generic Text Representation for Vision and NLP based on Neural Word Embedding A thesis submitted in partial fulfilment of the requirements for the degree of Master of Science in the school of computer science, Tel-Aviv university by Guy Lev … Related articles

Candidate Evaluation Strategies for Improved Difficulty Prediction of Language Tests L Beinborn, T Zesch, I Gurevych – Proceedings of the Tenth …, 2015 – anthology.aclweb.org … We also adapt the pipelines to include proper German and French pre-processing using DkPro (de Castilho and Gurevych, 2014) and adapt the candidate calculation to the different test types. In order to assure comparability … Cited by 2 Related articles All 11 versions

SACRY: Syntax-based automatic crossword puzzle resolution system G Barlacchi, M Nicosia, A Moschitti – ACL-IJCNLP 2015, 2015 – anthology.aclweb.org … Kernel similarities, ie, string kernels and tree kernels applied to structural representations. DKPro Similarity (DKP), which defines features used in the Semantic Textual Similarity (STS) challenge. … 2013. Dkpro similarity: An open source framework for text similarity. … Cited by 1 Related articles All 11 versions

Verbs Taking Clausal and Non-Finite Arguments as Signals of Modality-Revisiting the Issue of Meaning Grounded in Syntax J Eckle-Kohler – arXiv preprint arXiv:1509.03488, 2015 – arxiv.org … We used the DKPro TC framework (Daxen- berger et al., 2014) for classification and applied POS tagging and lemmatization as preprocessing. 19Reuters-21578, Distribution 1.0, see http:// kdd.ics.uci.edu/databases/reuters21578/ reuters21578.html. …

Tharawat: A Vision for a Comprehensive Resource for Arabic Computational Processing M Diab – International Conference on Intelligent Text Processing …, 2015 – Springer … In our effort to link Tharawat entries to English lexical resources, via the automatic augmentation process we will also run some of the best word sense disambiguation, such as DKpro,6 and semantic role labeling systems on the English side of the par- allel/comparable corpora … Related articles

Multi-level alignments as an extensible representation basis for textual entailment algorithms TG Noh, S Padó, V Shwartz, I Dagan… – … Semantics (* SEM 2015 …, 2015 – aclweb.org … The platform uses UIMA CAS (Fer- rucci and Lally, 2004) as the data container, adopts the DKPro type system (de Castilho and Gurevych, 2014), and defines annotation types which can be extended in a controlled manner. … Cited by 3 Related articles All 9 versions

Schema Matching as complex adaptive system H Assoudi, H Lounis – 2015 10th International Conference on …, 2015 – ieeexplore.ieee.org … Fig. 10 SMAS Prototype Simulation Visualisation The SMAS simulation model was implemented in Java using the open source ABMS framework Repast Simphony (2.1) [22], [23], the open source framework for Text Similarity DKPro Similarity (2.1.0) [24], the open source R … Related articles

Russian Lexicographic Landscape: a Tale of 12 Dictionaries Y Kiselev, A Krizhanovsky, P Braslavski, I Menshikov… – 2015 – elar.urfu.ru … In our study we used DKPro Similarity implementation of Monge-Elkan method [2]. Dictionaries contain a large number of 2–3 word definitions, which can skew similarity measurements, since such definitions are rather “standard” and occur in many dictionaries. … Cited by 3 Related articles

Keyword Extraction for Webpage Clusters V Salin, M Slastihina, I Ermilov, R Speck, S Auer… – svn.aksw.org … DKPro [6] is a collection of software components for keyword extraction based on UIMA [8]. It selects, filters, ranks and evaluates keywords employing state-of-the-art approaches. … Dkpro keyphrases: Flexible and reusable keyphrase extraction experiments. … Related articles

Taxonomy Transfer: Adapting a Knowledge Representing Resource to new Domains and Tasks L Kassner, C Kiefer – European Conference on Knowledge …, 2015 – search.proquest.com … An overview of the use case is depicted in Figure 2. We use a simple regular expression based tokenizer of our own design and the TextCat language detector (Cavnar et al. 1994) from the DKPro toolkit (TU Darmstadt 2011). … TUDarmstadt, 2011. DKPro Toolkit. … Cited by 1 Related articles All 2 versions

Design and realization of a modular architecture for textual entailment S Padó, TG Noh, A Stern, R Wang… – Natural Language …, 2015 – Cambridge Univ Press … Fortunately, there are existing CAS type systems for the NLP domain. We adopted the DKPro type system (Gurevych et al. … Section 2.2). Second, we needed to extend the DKPro type system with the types necessary to define textual entailment-specific annotation. … Cited by 14 Related articles All 8 versions

Denoising bodies to titles: Retrieving similar questions with recurrent convolutional models T Lei, H Joshi, R Barzilay, T Jaakkola… – arXiv preprint arXiv: …, 2015 – arxiv.org … SVM, we trained a re-ranker using SVM-Light (Joachims, 2002) with a linear kernel incor- porating various similarity measures from the DKPro similarity package (Bär et al., 2013). This model has been shown to provide the state of the art in sentence similarity challenges. … Cited by 2 Related articles All 3 versions

Composing Measures for Computing Text Similarity D Bär, T Zesch, I Gurevych – 2015 – tuprints.ulb.tu-darmstadt.de … reuse. As a basis for future work, we introduce DKPro Similarity, an open source software package which streamlines the development of text similarity measures and complete experimental setups. Page 3. 1 Introduction Within … Related articles All 4 versions

Feature-Based Visual Exploration of Text Classification F Stoffel, L Flekova, D Oelke, I Gurevych, DA Keim – bib.dbvis.de … filter. Feature extraction is done by the UIMA-based [4] open source DKPro framework [7]. The feature set is based on successful applications from the literature. … Zesch. Darmstadt Knowledge Processing Repository Based on UIMA. … Cited by 1 Related articles All 2 versions

Global thread-level inference for comment classification in community question answering S Joty, A Barrón-Cedeno… – Proceedings of the …, 2015 – anthology.aclweb.org … Classifier Our most important features measure the similar- ity between the question (q) and the comment (c). We compare lemmata and POS [1-4]-grams using Jaccard (1901), containment (Lyon et al., 2001), and cosine, as well as using some similarities from DKPro (Bär et al … Cited by 11 Related articles All 13 versions

A Vector Space Approach for Aspect-Based Sentiment Analysis A Alghunaim – 2015 – groups.csail.mit.edu … we start by processing the user generated content (eg restaurant reviews) using the Unstructured Information Management Architecture (UIMA) framework and dkpro- … Figure 3.1: Illustration of development framework using UIMA and dkpro-tc. … Cited by 3 Related articles All 12 versions

JoBimText Tutorial 2015 E Ruppert – 2015 – maggie.lt.informatik.tu-darmstadt.de Page 1. 1/47 … Related articles

JoBimText Tutorial Mannheim E Ruppert – 2015 – maggie.lt.informatik.tu-darmstadt.de Page 1. 1/50 … Related articles

An Open-source Framework for Multi-level Semantic Similarity Measurement MT Pilehvar, R Navigli – Proceedings of NAACL-HLT, 2015 – pdfs.semanticscholar.org … Daniel Bär, Torsten Zesch, and Iryna Gurevych. 2013. DKPro Similarity: An open source framework for text similarity. In Proceedings of ACL: System Demonstra- tions, pages 121–126, Sofia, Bulgaria. Or Biran, Samuel Brody, and Noémie Elhadad. 2011. … Cited by 1 Related articles All 12 versions

More Features Are Not Always Better: Evaluating Generalizing Models in Incident Type Classification of Tweets A Schulz, BI Marketing, DBF AG, C Guckelsberger… – aclweb.org … or replaced. Finally, we applied lemmatization to normalize all tokens. All preprocessing steps were performed by DKPro TC (de Castilho and Gurevych, 2014), a popular framework for text classification. After prepro- cessing … Related articles All 10 versions

Effectiveness of Domain Adaptation Approaches for Social Media PoS Tagging T Horsmann, T Zesch – CLiC it, 2015 – iris.unito.it … 2014. DKPro TC: A java-based framework for supervised learning experiments on textual data. In Proceedings of 52nd Annual Meeting of the Association for Computa- tional Linguistics: System Demonstrations, pages 61–66, Baltimore, Maryland. Jacob Eisenstein. 2013. … Cited by 1 Related articles All 4 versions

Metaphor mining in historical german novels: An unsupervised learning approach S Pernes – Big Data (Big Data), 2015 IEEE International …, 2015 – ieeexplore.ieee.org … 1http://www.germanistik.uni-wuerzburg.de/lehrstuehle/computerphilologie/ forschung/projekte/ digibib 2https://github.com/DARIAH-DE/DARIAH-DKPro-Wrapper 2015 IEEE International Conference on Big Data (Big Data) 978-1-4799-9926-2/15/$31.00 ©2015 IEEE 1650 Page 2. … Related articles All 3 versions

Structural representations for learning relations between pairs of texts S Filice, G Da San Martino, A Moschitti – … of the 53rd Annual Meeting of …, 2015 – aclweb.org … We also used similarity features from the DKPro of the UKP Lab (Bär et al., 2012), tested in the Semantic Textual Similarity (STS) task: – Longest common substring measure and Longest common subsequence measure, which determine the length of the longest substring … Cited by 8 Related articles All 10 versions

Reserating the awesometastic: An automatic extension of the WordNet taxonomy for novel terms D Jurgens, MT Pilehvar – … of the 2015 conference of the North …, 2015 – anthology.aclweb.org … Daniel Bär, Torsten Zesch, and Iryna Gurevych. 2013. DKPro Similarity: An open source framework for text similarity. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (ACL), pages 121–126, Sofia, Bulgaria. … Cited by 6 Related articles All 11 versions

Discourse-sensitive Automatic Identification of Generic Expressions A Friedrich, M Pinkal – … of the 53rd Annual Meeting of the …, 2015 – anthology.aclweb.org … 1999). Our system is based on dkpro (de Castilho and Gurevych, 2014). We extract the features listed in Table 1 based on the POS tags and syntactic dependencies assigned by the Stan- ford parser (Klein and Manning, 2002). … Cited by 5 Related articles All 7 versions

Context-specific Consistencies in Information Extraction P Klügl – opus.uni-wuerzburg.de Page 1. P eter Klügl Context-specific Consistencies in Information Extraction Peter Klügl Rule-based and Probabilistic Approaches C ontext-specific C on sistencies in Inform ation Extraction Page 2. Peter Klügl Context-specific Consistencies in Information Extraction Page … Related articles All 4 versions

[BOOK] Context-specific Consistencies in Information Extraction: Rule-based and Probabilistic Approaches P Klügl – 2015 – books.google.com Page 1. Peter Klüg Context-specific Consistencies in Information Extraction Rule-based and Probabilistic Approaches [5] S. Anzaroot and A. McCallum. New Dataset for Fine-Grained Citation xtraction. In ICML Workshop on Peer Reviewing and Publishing Models (PEER), 2013. … Related articles All 5 versions

Combining Topic Models for Corpus Exploration: Applying LDA for Complex Corpus Research Tasks in a Digital Humanities Project C Schnober, I Gurevych – Proceedings of the 2015 Workshop on Topic …, 2015 – dl.acm.org … We incorporated the pre-processing steps and the model estimation into a UIMA pipeline [6] using uimaFIT [15] and analysis engines from the DKPro reposi- tory [5]. The topic mixture of a document is inferred using Gibbs sampling as described in [8]. Because the inference … Cited by 1 Related articles

Semeval-2015 task 3: Answer selection in community question answering PNLMWM AlessandroMoschitti, J Glass, B Randeree – SemEval-2015, 2015 – aclweb.org … When building their systems, participants used a number of tools and resources for preprocessing, feature extraction, and machine learning, includ- ing Deeplearning4J, DKPro, GATE, GloVe, Google translate, HeidelTime, LibLinear, LibSVM, MADA, Mallet, Meteor, Networkx … Cited by 3 Related articles All 14 versions

NASARI: a novel approach to a semantically-aware representation of items J Camacho-Collados, MT Pilehvar… – Proceedings of …, 2015 – wwwusers.di.uniroma1.it Page 1. Human Language Technologies: The 2015 Annual Conference of the North American Chapter of the ACL, pages 567–577, Denver, Colorado, May 31 – June 5, 2015. cO2015 Association for Computational Linguistics … Cited by 19 Related articles All 11 versions

Assessing the impact of syntactic and semantic structures for answer passages reranking K Tymoshenko, A Moschitti – Proceedings of the 24th ACM International …, 2015 – dl.acm.org Page 1. Assessing the Impact of Syntactic and Semantic Structures for Answer Passages Reranking Kateryna Tymoshenko University of Trento Povo (Trento), Italy k.tymoshenko@gmail.com Alessandro Moschitti ? Qatar Computing … Cited by 16 Related articles All 5 versions

Approaches to Automatic Text Structuring N Erbs – 2015 – tuprints.ulb.tu-darmstadt.de Page 1. Approaches to Automatic Text Structuring Vom Fachbereich Informatik der Technischen Universität Darmstadt genehmigte Dissertation zur Erlangung des akademischen Grades Dr.-Ing vorgelegt von M.Sc. Nicolai Erbs geboren in Scherzingen (Schweiz) … Related articles

Exploiting Debate Portals for Semi-Supervised Argumentation Mining in User-Generated Web Discourse I Habernal, I Gurevych – Proceedings of the 2015 Conference on Empirical …, 2015 – Citeseer Page 1. Exploiting Debate Portals for Semi-Supervised Argumentation Mining in User-Generated Web Discourse Ivan Habernal† and Iryna Gurevych†‡ †Ubiquitous Knowledge Processing Lab (UKP-TUDA) Department of Computer … Cited by 13 Related articles All 10 versions

The Impact of Sentiment-driven Feedback on Knowledge Reuse in Online Communities M Grigore, C Rosenkranz, J Sutanto – AIS Transactions on Human- …, 2015 – aisel.aisnet.org Page 1. T ransactions on HC I uman — omputer nteraction Original Empirical Research Volume 7 Issue 4 pp. 212 – 232 December 2016 The Impact of Sentiment-driven Feedback on Knowledge Reuse in Online Communities … Related articles

Mining the Biomedical Literature C Mihaila, R Batista-Navarro, N Alnazzawi… – Healthcare Data …, 2015 – books.google.com Page 280. Chapter 8 Mining the Biomedical Literature Claudiu Mihaila National Centre for Text Mining University of Manchester Manchester, UK claudiu. mihaila@ manchester. ac. uk Riza Batista-Navarro National Centre for … Cited by 1 Related articles

Discourse Segmentation of German Texts U Sidarenka, A Peldszus, M Stede – Document-level school lesson quality …, 2015 – jlcl.org Page 76. Uladzimir Sidarenka, Andreas Peldszus, Manfred Stede Discourse Segmentation of German Texts This paper addresses the problem of segmenting German texts into minimal discourse units, as they are needed, for example, in RST-based discourse parsing. … Cited by 1 Related articles All 2 versions

Core techniques of ontology-based question answering systems: a survey D Diefenbacha, K Singha, P Mareta – Semantic Web Journal – wtlab.um.ac.ir Page 1. Undefined 0 (0) 1 1 IOS Press Core Techniques of Ontology-Based Question Answering Systems: a Survey Dennis Diefenbacha, Kamal Singha and Pierre Mareta a Université de Lyon, CNRS UMR 5516 Laboratoire … Related articles