%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% MEDICAL DOMAIN THEMEN Bis zu 4 mögliche Vorträge: -Gehe auf https://sites.google.com/view/mediqa2019 Erkläre im Vortrag das Problem genau, fasse zusammen, was es an Arbeiten/Techniken gibt. 1) NLI 2) RQA 3) QA 1 Vortrag "Multi-label natural language processing to identify diagnosis and procedure codes from MIMIC-III inpatient notes" https://arxiv.org/abs/2003.07507 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% Bis zu 7 mögliche Vorträge: Gehe auf https://trec.nist.gov/pubs/call2018.html Dort finden sich 7 Tasks, s.u. Erkläre kurz das Anliegen der TEXT RETRIEVAL CONFERENCE. Beschreibe, um was es in diesem Task geht. Recherchiere, ob es Literatur zu diesem Problem gibt. Erkläre im Vortrag das Problem genau, fasse zusammen, was es an Arbeiten/Techniken gibt. (1) CENTRE Track (2) Common Core Track (3) Complex Answer Retrieval Track (4) Incident Streams Track (5) News Track (6) Precision Medicine Track (7) Real-Time Summarization Track %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% 1-2 Vorträge Inter-Coder Agreement for Computational Linguistics. Computational Linguistics, 2008. http://www.mitpressjournals.org/doi/pdf/10.1162/coli.07-034-R2 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% 2 Vorträge zu Algorithmen bei der Websuche: PageRank und Hits (oder Hubs and authorities) (Literatur siehe Web): %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% Vortragscluster mit 1-6 Vorträgen: http://www.paulmckevitt.com/docs/readings/spoken_dialogue_technology.pdf 1. Dialogsysteme Spoken Dialogue Technology: Enabling the Conversational User Interface MICHAEL F. MC TEAR Smart Enough to Talk With Us? Foundations and Challenges for Dialogue Capable AI Systems Barbara J. Grosz Computational Linguistics March 2018, Vol. 44, No. 1, pp. 1–15 1 Vortrag; Identifying and Avoiding Confusion in Dialogue with People with Alzheimer's Disease Hamidreza Chinaei, Leila Chan Currie, Andrew Danks, Hubert Lin, Tejas Mehta, and Frank Rudzicz Computational Linguistics June 2017, Vol. 43, No. 2, pp. 377–406 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% 1-2 Vorträge: Was sind Multiword expressions? https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00302 Multiword Expression Processing: A Survey Mathieu Constant, Gülşen Eryiğit, Johanna Monti, Lonneke van der Plas, Carlos Ramisch, Michael Rosner, and Amalia Todirascu Computational Linguistics December 2017, Vol. 43, No. 4, pp. 837–892 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% Unbestimmte Zahl möglicher Vorträge: Der nächste Themenkomplex befasst sich mit der Frage: welchen Nutzen kann man aus der Wikipedia für computerlinguistische Aufgaben oder für Aufgaben im Bereich des Information Retrieval ziehen? Unten genannt sind einige Referenzen, die nicht mehr ganz taufrisch sind. Bitte selbst auchz nach aktuellerer Literatur zu diesem Thema schauen!! Razvan Bunescu and Marius Pasca. Using Encyclopedic Knowledge for Na- med Entity Disambiguation. In Proceedings of EACL, pages 79–85, Sheffield, UK, 2006. Silviu Cucerzan. Large-Scale Named Entity Disambiguation Based on Wi- kipedia Data. In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pages 708–716, Prague, Czech Republic, June 2007. Asso- ciation for Computational Linguistics. Iryna Gurevych, Christof Müller, and Torsten Zesch. What to be? - Electronic Career Guidance Based on Semantic Relatedness. In Proceedings of the 45th An- nual Meeting of the Association for Computational Linguistics, pages 1032–1039, Prague, Czech Republic, Jun 2007. Association for Computational Linguistics. Jochen L. Leidner. Toponym Resolution in Text: “Which Sheffield ist it?”. In Proceedings of the the 27th Annual International ACM SIGIR Conference (SIGIR 2004), Sheffield, UK, 2004. K. Nakayama, T. Hara, and S. Nishio. A Thesaurus Construction Method from Large Scale Web Dictionaries. In Proceedings of IEEE International Confe- rence on Advanced Information Networking and Applications (IEEE AINA), pages 932–939, 2007. K. Nakayama, T. Hara, and S. Nishio. Wikipedia Mining - Wikipedia as a Cor- pus for Knowledge Extraction. In Proceedings of Annual Wikipedia Conference (Wikimania), 2008. %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% 1-2 Vorträge zu verwandtem Thema: Gehe auf die Webseite der Wikimedia Conference 2018 fasse zusammen, was auf der Konferenz passiert. Was ist für CL relevant? %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% 1 Vortrag zu folgendem Problem: Wie sieht eine gute Interaktion bei der Suche in Dokumentenbeständen oder im Web aus? Welche Probleme und Fragen stellen sich, welche Möglichkeiten gibt es, diese Interaktion interessant zu gestalten? Ausgangspunkt siehe Session 2a in https://dl.acm.org/citation.cfm?id=3077136 Man kann nur die Abstracts sehen, aber das reicht...) Man kann von dort ausgehend nach weiterer Literatur zu Search Engine Interfaces suchen.... %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% Wortähnlichkeit: Levenshtein-Abstand, Wagner-Fischer-Algorithmus (beigelegtes Sript) und Brill-Moore ("An improved error model for noisy channel spelling correction", leicht im Web zu finden) %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% 1-2 Vorträge Frage: Wie kann man in OCR-Dokumenten historischer Texte mit statistischen und linguistischen Methoden vermutete Klassen von OCR-Fehlern finden Ulrich Reffle and Christoph Ringlstetter, Unsupervised profiling of OCRed historical documents %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% Automatic quality evaluation and (semi-) automatic improvement of {OCR} models for historical printings, Springmann, Uwe and Fink, Florian and Schulz, Klaus U., ArXiv e-prints, http://arxiv.org/abs/1606.05157 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%