Menü Überspringen
Contact
Deutsch
English
Not track
Data Protection
Search
Log in
DIPF News
Research
Infrastructures
Institute
Zurück
Contact
Deutsch
English
Not track
Data Protection
Search
Home
>
Research
>
Publications
>
Publications Data Base
Search results in the DIPF database of publications
Your query:
(Schlagwörter: "Automatisierung")
Advanced Search
Search term
Only Open Access
Search
Unselect matches
Select all matches
Export
54
items matching your search terms.
Show all details
Medical concept embeddings via labeled background corpora
Mencía, Eneldo Loza; De Melo, Gerard; Nam, Jinseok
Book Chapter
| Aus: European Language Resources Association (Hrsg.): Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC 2016) | Portoroz: European Language Resources Association | 2016
37067 Endnote
Author(s):
Mencía, Eneldo Loza; De Melo, Gerard; Nam, Jinseok
Title:
Medical concept embeddings via labeled background corpora
In:
European Language Resources Association (Hrsg.): Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC 2016), Portoroz: European Language Resources Association, 2016 , S. 3629-3636
URL:
http://www.lrec-conf.org/proceedings/lrec2016/pdf/1190_Paper.pdf
Publication Type:
4. Beiträge in Sammelwerken; Tagungsband/Konferenzbeitrag/Proceedings
Language:
Englisch
Keywords:
Algorithmus; Automatisierung; Computerlinguistik; Medizin; Semantik; Sprache; Textanalyse
Abstract:
In recent years, we have seen an increasing amount of interest in low-dimensional vector representations of words. Among other things, these facilitate computing word similarity and relatedness scores. The most well-known example of algorithms to produce representations of this sort are the word2vec approaches. In this paper, we investigate a new model to induce such vector spaces for medical concepts, based on a joint objective that exploits not only word co-occurrences but also manually labeled documents, as available from sources such as PubMed. Our extensive experimental analysis shows that our embeddings lead to significantly higher correlations with human similarity and relatedness assessments than previous work. Due to the simplicity and versatility of vector representations, these findings suggest that our resource can easily be used as a drop-in replacement to improve any systems relying on medical concept similarity measures. (DIPF/Orig.)
DIPF-Departments:
Informationszentrum Bildung
Enriching wikidata with frame semantics
Mousselly-Sergieh, Hatem; Gurevych, Iryna
Book Chapter
| Aus: Association for Computational Linguistics (Hrsg.): Proceedings of the 5th workshop on automated knowledge base construction (AKBC) 2016 held in conjunction with NAACL 2016 | Stroudsburg; PA: Association for Computational Linguistics | 2016
36979 Endnote
Author(s):
Mousselly-Sergieh, Hatem; Gurevych, Iryna
Title:
Enriching wikidata with frame semantics
In:
Association for Computational Linguistics (Hrsg.): Proceedings of the 5th workshop on automated knowledge base construction (AKBC) 2016 held in conjunction with NAACL 2016, Stroudsburg; PA: Association for Computational Linguistics, 2016 , S. 29-34
URL:
https://www.ukp.tu-darmstadt.de/fileadmin/user_upload/Group_UKP/publikationen/2016/2016_NAACL_AKBC_HMS.pdf
Publication Type:
4. Beiträge in Sammelwerken; Tagungsband/Konferenzbeitrag/Proceedings
Language:
Englisch
Keywords:
Automatisierung; Computerlinguistik; Lexikon; Mehrsprachigkeit; Online; Semantik
Abstract (english):
Wikidata is a large-scale, multilingual and freely available knowledge base. It contains more than 14 million facts, however, it is still missing linguistic information. In this paper, we aim to bridge this gap by aligning Wikidata with FrameNet lexicon. We propose an approach based on word embedding to identify a mapping between Wikidata relations, called properties, and FrameNet frames and to annotate the arguments of each relation with the semantic roles of the matching frames. Early empirical results show the advantage of our approach compared to other baseline methods. (DIPF/Orig.)
DIPF-Departments:
Informationszentrum Bildung
Domain-specific corpus expansion with focused webcrawling
Remus, Steffen; Biemann, Chris
Book Chapter
| Aus: European Language Resources Association (Hrsg.): Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC 2016) | Portoroz: European Language Resources Association | 2016
37066 Endnote
Author(s):
Remus, Steffen; Biemann, Chris
Title:
Domain-specific corpus expansion with focused webcrawling
In:
European Language Resources Association (Hrsg.): Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC 2016), Portoroz: European Language Resources Association, 2016 , S. 3607-3611
URL:
http://www.lrec-conf.org/proceedings/lrec2016/pdf/316_Paper.pdf
Publication Type:
4. Beiträge in Sammelwerken; Tagungsband/Konferenzbeitrag/Proceedings
Language:
Englisch
Keywords:
Algorithmus; Automatisierung; Bildung; Computerlinguistik; Data Mining; Hypertext; Modell; Sprache; Text; Textanalyse
Abstract:
This work presents a straightforward method for extending or creating in-domain web corpora by focused webcrawling. The focused webcrawler uses statistical N-gram language models to estimate the relatedness of documents and weblinks and needs as input only N-grams or plain texts of a predefined domain and seed URLs as starting points. Two experiments demonstrate that our focused crawler is able to stay focused in domain and language. The first experiment shows that the crawler stays in a focused domain, the second experiment demonstrates that language models trained on focused crawls obtain better perplexity scores on in-domain corpora. We distribute the focused crawler as open source software. (DIPF/Orig.)
DIPF-Departments:
Informationszentrum Bildung
Crowdsourcing a large dataset of domain-specific context-sensitive semantic verb relations
Sukhareva, Maria; Eckle-Kohler, Judith; Habernal, Ivan; Gurevych, Iryna
Book Chapter
| Aus: European Language Resources Association (Hrsg.): Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC 2016) | Portoroz: European Language Resources Association | 2016
36972 Endnote
Author(s):
Sukhareva, Maria; Eckle-Kohler, Judith; Habernal, Ivan; Gurevych, Iryna
Title:
Crowdsourcing a large dataset of domain-specific context-sensitive semantic verb relations
In:
European Language Resources Association (Hrsg.): Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC 2016), Portoroz: European Language Resources Association, 2016 , S. 2131-2137
URL:
https://www.ukp.tu-darmstadt.de/fileadmin/user_upload/Group_UKP/publikationen/2016/lrec2016_sukhareva.pdf
Publication Type:
4. Beiträge in Sammelwerken; Tagungsband/Konferenzbeitrag/Proceedings
Language:
Englisch
Keywords:
Automatisierung; Computerlinguistik; Data Mining; Klassifikation; Semantik; Textanalyse
Abstract (english):
We present a new large dataset of 12403 context-sensitive verb relations manually annotated via crowdsourcing. These relations capture fine-grained semantic information between verb-centric propositions, such as temporal or entailment relations. We propose a novel semantic verb relation scheme and design a multi-step annotation approach for scaling-up the annotations using crowdsourcing. We employ several quality measures and report on agreement scores. The resulting dataset is available under a permissive CreativeCommons license. It represents a valuable resource for various applications, such as automatic information consolidation or automatic summarization. (DIPF/Orig.)
DIPF-Departments:
Informationszentrum Bildung
The eras and trends of automatic short answer grading
Burrows, Steven; Gurevych, Iryna; Stein, Benno
Journal Article
| In: International Journal of Artificial Intelligence in Education | 2015
34978 Endnote
Author(s):
Burrows, Steven; Gurevych, Iryna; Stein, Benno
Title:
The eras and trends of automatic short answer grading
In:
International Journal of Artificial Intelligence in Education, 25 (2015) 1, S. 60-117
DOI:
10.1007/s40593-014-0026-8
URL:
http://link.springer.com/article/10.1007/s40593-014-0026-8
Publication Type:
3a. Beiträge in begutachteten Zeitschriften; Aufsatz (keine besondere Kategorie)
Language:
Englisch
Keywords:
Automatisierung; Computerlinguistik; Computerunterstütztes Verfahren; Frage; Leistungsbeurteilung; Methode; Notengebung; Technologiebasiertes Testen; Testaufgabe
Abstract:
Automatic short answer grading (ASAG) is the task of assessing short natural language responses to objective questions using computational methods. The active research in this field has increased enormously of late with over 80 papers fitting a definition of ASAG. However, the past efforts have generally been ad-hoc and non-comparable until recently, hence the need for a unified view of the whole field. The goal of this paper is to address this aim with a comprehensive review of ASAG research and systems according to history and components. Our historical analysis identifies 35 ASAG systems within 5 temporal themes that mark advancement in methodology or evaluation. In contrast, our component analysis reviews 6 common dimensions from preprocessing to effectiveness. A key conclusion is that an era of evaluation is the newest trend in ASAG research, which is paving the way for the consolidation of the field. (DIPF/Orig.)
DIPF-Departments:
Informationszentrum Bildung
Analyzing domain suitability of a sentiment lexicon by identifying distributionally bipolar words
Flekova, Lucie; Ruppert, Eugen; Preotiuc-Pietro, Daniel
Book Chapter
| Aus: Association for Computational Linguistics (Hrsg.): 6th workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis (WASSA 2015): Workshop proceedings, 17 September 2015, Lisboa, Portugal | Red Hook; NY: Association for Computational Linguistics | 2015
37028 Endnote
Author(s):
Flekova, Lucie; Ruppert, Eugen; Preotiuc-Pietro, Daniel
Title:
Analyzing domain suitability of a sentiment lexicon by identifying distributionally bipolar words
In:
Association for Computational Linguistics (Hrsg.): 6th workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis (WASSA 2015): Workshop proceedings, 17 September 2015, Lisboa, Portugal, Red Hook; NY: Association for Computational Linguistics, 2015 , S. 77-84
URL:
http://www.emnlp2015.org/proceedings/WASSA/WASSA-2015.pdf#page=89
Publication Type:
4. Beiträge in Sammelwerken; Tagungsband/Konferenzbeitrag/Proceedings
Language:
Englisch
Keywords:
Automatisierung; Computerlinguistik; Emotion; Kommunikation; Lexikographie; Lexikon; Online; Qualität; Soziale Software; Textanalyse; Thesaurus
Abstract:
Contemporary sentiment analysis approaches rely on lexicon based methods. This is mainly due to their simplicity, although the best empirical results can be achieved by more complex techniques. We introduce a method to assess suitability of generic sentiment lexicons for a given domain, namely to identify frequent bigrams where a polar word switches polarity. Our bigrams are scored using Lexicographers Mutual Information and leveraging large automatically obtained corpora. Our score matches human perception of polarity and demonstrates improvements in classification results using our enhanced context-aware method. Our method enhances the assessment of lexicon based sentiment detection and can be further userd to quantify ambiguous words. (DIPF/Orig.)
Linking the thoughts. Analysis of argumentation structures in scientific publications
Kirschner, Christian; Eckle-Kohler, Judith; Gurevych, Iryna
Book Chapter
| Aus: Association for Computational Linguistics (Hrsg.): Proceedings of the 2nd Workshop on Argumentation Mining held in conjunction with the 2015 Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT 2015) | Denver; CO: Association for Computational Linguistics | 2015
35503 Endnote
Author(s):
Kirschner, Christian; Eckle-Kohler, Judith; Gurevych, Iryna
Title:
Linking the thoughts. Analysis of argumentation structures in scientific publications
In:
Association for Computational Linguistics (Hrsg.): Proceedings of the 2nd Workshop on Argumentation Mining held in conjunction with the 2015 Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT 2015), Denver; CO: Association for Computational Linguistics, 2015 , S. 1-11
URL:
https://aclweb.org/anthology/W/W15/W15-05.pdf
Publication Type:
4. Beiträge in Sammelwerken; Tagungsband/Konferenzbeitrag/Proceedings
Language:
Englisch
Keywords:
Argumentation; Automatisierung; Bildungsforschung; Computerlinguistik; Data Mining; Klassifikation; Textanalyse; Veröffentlichung
Abstract:
This paper presents the results of an annotation study focused on the fine-grained analysis of argumentation structures in scientific publications. Our new annotation scheme specifies four types of binary argumentative relations between sentences, resulting in the representation of arguments as small graph structures. We developed an annotation tool that supports the annotation of such graphs and carried out an annotation study with four annotators on 24 scientific articles from the domain of educational research. For calculating the inter-annotator agreement, we adapted existing measures and developed a novel graph based agreement measure which reflects the semantic similarity of different annotation graphs. (DIPF/Orig.)
DIPF-Departments:
Informationszentrum Bildung
Die Automatisierung prozeduralen Wissens. Eine Analyse basierend auf Prozessdaten
Stelter, Annette; Goldhammer, Frank; Naumann, Johannes; Rölke, Heiko
Book Chapter
| Aus: Stiller, Jurik; Laschke, Christin (Hrsg.): Berlin-Brandenburger Beiträge zur Bildungsforschung 2015: Herausforderungen, Befunde und Perspektiven interdisziplinärer Bildungsforschung | Frankfurt am Main: Lang | 2015
35596 Endnote
Author(s):
Stelter, Annette; Goldhammer, Frank; Naumann, Johannes; Rölke, Heiko
Title:
Die Automatisierung prozeduralen Wissens. Eine Analyse basierend auf Prozessdaten
In:
Stiller, Jurik; Laschke, Christin (Hrsg.): Berlin-Brandenburger Beiträge zur Bildungsforschung 2015: Herausforderungen, Befunde und Perspektiven interdisziplinärer Bildungsforschung, Frankfurt am Main: Lang, 2015 , S. 111-132
URL:
http://www.peterlang.com/index.cfm?event=cmp.ccc.seitenstruktur.detailseiten&seitentyp=produkt&pk=83370&concordeid=265709
Publication Type:
4. Beiträge in Sammelwerken; Tagungsband/Konferenzbeitrag/Proceedings
Language:
Deutsch
Keywords:
Antwort; Aufgabe; Automatisierung; Datenanalyse; Kognitive Kompetenz; Kompetenzerwerb; Leistung; PIAAC <Programme for the International Assessment of Adult Competencies>; Regressionsanalyse; Technologiebasiertes Testen; Teilnehmer; Test; Testdurchführung; Wissen; Zeit
Abstract:
Prozessbezogene Verhaltensdaten aus computerbasierten Large Scale Assessments bieten neue Möglichkeiten zur Beschreibung des Bearbeitungsprozesses von Testteilnehmern. Dazu gehört auch die Anwendung von prozeduralem Wissen bei der Aufgabenbearbeitung. Prozedurales Wissen ist Wissen darüber, wie Tätigkeiten ausgeführt werden. Dabei nimmt mit zunehmender Expertise der Automatisierungsgrad prozeduralen Wissens zu, was anspruchsvollere kognitive Leistungen ermöglicht. Testteilnehmer brauchen zum Lösen komplexer Probleme unter anderem prozedurales Wissen und werden sich dabei im Grad der Automatisierung dieses Wissens unterscheiden. In dieser Studie wird ein Indikator für Automatisierung anhand aggregierter Testteilnehmerinteraktionen aus Protokolldaten extrahiert. Hierfür werden Daten aus dem computerbasierten Teil des 'Programme for the International Assessment of Adult Competencies' (PIAAC) genutzt. Basierend auf theoretischen Annahmen zum Kompetenzerwerb werden basale Teilaufgaben identifiziert, für die der individuelle Grad an Automatisierungen durch zeitbasierte Indikatoren erfasst wird. Anschließend werden logistische Regressionen berechnet, um die Beziehung dieser Indikatoren zur Wahrscheinlichkeit, mit der eine Aufgabe gelöst wird, zu ermitteln. Die Ergebnisse zeigen erwartungsgemäß einen negativen Zusammenhang zwischen der Lösungswahrscheinlichkeit einer Problemlöseaufgabe und der Geschwindigkeit bei der Bearbeitung basaler Teilaufgaben.
Abstract (english):
In educational research there are new ways of answering research questions through the use of behavioral process data. Behavioral process data gives detailed insight into the problem solving behavior of each test taker, including the activation of procedural knowledge. Procedural knowledge means knowing how to solve a task. With a higher degree of experience this kind of knowledge will become more automated and allows persons to successfully engage in more demanding cognitive tasks. Problem Solving requires this automation in procedural knowledge and test takers will differ in their degree of automation. This study shows how the degree of automation is related to success in problem solving tasks. To this end, we use data from the 'Programme for the International Assessment of Adult Competencies' (PIAAC). We first identify routine steps in PIAAC problem solving tasks that can be accomplished by activation of automated procedural knowledge. We measure the degree of automation through the time subjects need to take these routine steps. Logistic regression models are used to calculate the relation between the time taken and the probability of success on the task. First results show that indeed probability of success is highest, when subjects need only little time to take routine steps, presumably due to a high degree of automation.
DIPF-Departments:
Bildungsqualität und Evaluation; Informationszentrum Bildung
Comparative exploration of document collections. A visual analytics approach
Oelke, Daniela; Strobelt, Hendrik; Rohrdantz, Christian; Gurevych, Iryna; Deussen, Oliver
Journal Article
| In: Computer Graphics Forum | 2014
34578 Endnote
Author(s):
Oelke, Daniela; Strobelt, Hendrik; Rohrdantz, Christian; Gurevych, Iryna; Deussen, Oliver
Title:
Comparative exploration of document collections. A visual analytics approach
In:
Computer Graphics Forum, 33 (2014) 3, S. 201-210
DOI:
10.1111/cgf.12376
Publication Type:
3a. Beiträge in begutachteten Zeitschriften; Aufsatz (keine besondere Kategorie)
Language:
Englisch
Keywords:
Automatisierung; Computergrafik; Computerlinguistik; Informationssystem; Methode; Modellierung; Semantik; Textanalyse; Vergleich; Visualisierung
Abstract:
We present an analysis and visualization method for computing what distinguishes a given document collection from others. We determine topics that discriminate a subset of collections from the remaining ones by applying probabilistic topic modeling and subsequently approximating the two relevant criteria distinctiveness and characteristicness algorithmically through a set of heuristics. Furthermore, we suggest a novel visualization method called DiTop-View, in which topics are represented by glyphs (topic coins) that are arranged on a 2D plane. Topic coins are designed to encode all information necessary for performing comparative analyses such as the class membership of a topic, its most probable terms and the discriminative relations. We evaluate our topic analysis using statistical measures and a small user experiment and present an expert case study with researchers from political sciences analyzing two real-world datasets. (DIPF/Orig.)
DIPF-Departments:
Informationszentrum Bildung
DKPro TC. A Java-based framework for supervised learning experiments on textual data
Daxenberger, Johannes; Ferschke, Oliver; Gurevych, Iryna; Zesch, Torsten
Book Chapter
| Aus: Bontcheva, Kalina; Jingbo, Zhu (Hrsg.): Proceedings of COLING 2014: System demonstrations | Stroudsburg; PA: Association for Computational Linguistics | 2014
34721 Endnote
Author(s):
Daxenberger, Johannes; Ferschke, Oliver; Gurevych, Iryna; Zesch, Torsten
Title:
DKPro TC. A Java-based framework for supervised learning experiments on textual data
In:
Bontcheva, Kalina; Jingbo, Zhu (Hrsg.): Proceedings of COLING 2014: System demonstrations, Stroudsburg; PA: Association for Computational Linguistics, 2014 , S. 61-66
URL:
http://aclweb.org/anthology/P/P14/P14-5011.pdf
Publication Type:
4. Beiträge in Sammelbänden; Tagungsband/Konferenzbeitrag/Proceedings
Language:
Englisch
Keywords:
Automatisierung; Computerlinguistik; Computerprogramm; Data Mining; Datenverarbeitung; Klassifikation; Programmiersprache; Text; Textanalyse
Abstract:
We present DKPro TC, a framework for supervised learning experiments on textual data. The main goal of DKPro TC is to enable researchers to focus on the actual research task behind the learning problem and let the framework handle the rest. It enables rapid prototyping of experiments by relying on an easy-to-use workflow engine and standardized document preprocessing based on the Apache Unstructured Information Management Architecture (Ferrucci and Lally, 2004). It ships with standard feature extraction modules, while at the same time allowing the user to add customized extractors. The extensive reporting and logging facilities make DKPro TC experiments fully replicable. (DIPF/Orig.)
DIPF-Departments:
Informationszentrum Bildung
Unselect matches
Select all matches
Export
<
1
2
3
4
...
6
>
Show all
(54)