Since January 2019, Michael Wiegand is the new group leader of the research Area A “Natural Language Processing & Annotation Science”.
Before that, Michael Wiegand worked as a postdoctoral researcher of the Spoken Language Systems Group at Saarland University. Between 2016 and 2018 he has already published several publications in close cooperation with the LiMo (see publication list).
We are very glad to have him in our team!
Homepage of Michael Wiegand
On November 10, Anette Frank gave an invited talk at the Event Semantics Workshop 2018 (EvSem 2018, 9./10.11.2018), organized by HULC Lab at the Mathematikon in Heidelberg. She presented new work on “Resolving Abstract Anaphors in Discourse — Uphill Battles with Neural Networks and Automatic Data Generation”.
On October 22, at 18:15, Maria Becker will give a public talk at the Interdisciplinary Forum of Digital Textual Sciences (InFoDiTex) with the title “Detecting Controversial Concepts within Discourses Using Quantitative Methods”.
Abstract:
We investigate a corpus of 72.000 German newspaper articles on climate change by applying quantitative methods such as keyword analysis or semantic tagging in order to find controversial topics and concepts. Our approach is divided into four steps with varying granularity: (a) Detecting Central Topics, (b) Detecting Central Subtopics, (c) Detecting Controversial Topics & Concepts and (d) Detecting Central Controversial Texts. Our contributions are twofold: (1) We reveal interesting insights into central controversial topics, actors, foci and points of view and styles of discussion and (2) we suggest a method for detecting Controversial Concepts within Textual Corpora using quantitative methods which we consider to be applicable to any other kind of discourse.
For more information, see here.
The paper “Distinguishing affixoid formations from compounds” by Josef Ruppenhofer, Michael Wiegand, Rebecca Wilm and Katja Markert received the Best Paper Award in the category “Best linguistic analysis” at COLING 2018 , which will take place in Santa Fe, New Mexico.
The paper will be presented on Friday, August 24, 2018 (see COLING 2018 – Conference program).
We congratulate the authors for their excellent work.
Juri Opitz joined the LiMo team on April 1, 2018.
Our newest member completed his Bachelor of Arts in Computational Linguistics at University of Heidelberg. His research interests lie in the fields of Semantics, Knowledge Graphs and NLP for historic texts.
He will be part of the research Area C “Applications in empirical linguistics & Digital Humanities”.
We are very pleased to welcome him on our team!
Homepage of Juri Opitz
Prof. Dr. Anette Frank gives a Keynote Speech at the Final Action Conference of the TextLink COST Action Initiative, in Toulouse, 19 March 2018.
Prof. Dr. Anette Frank gives a Keynote Speech at the Annual Conference of the German Society of Linguistics (DGfS) in Stuttgart, 9th of March 2018.
The title of the keynote is “Classifying Common Sense Knowledge Relations and Using them in NLP Tasks”.
On March 8, 2018, the Leibniz ScienceCampus LiMo will present its current research projects in a poster session at the 40th Annual Conference of the German Linguistic Society (DGfS):
The DGfS Annual Meeting will take place at the University of Stuttgart (Campus City Center) on March 7 and 9, 2018.
On March 14, 2018, the Leibniz ScienceCampus LiMo will present its current research in a short lecture and in a poster session at the 54th Annual Meeting of the Institute for German Language (IDS, Mannheim). The IDS Annual Meeting with the title “Neues vom heutigen Deutsch: Empirisch – methodisch – theoretisch” will take place in the Congress Center Rosengarten Mannheim on March 13 and 15, 2018.
Interested persons can view the LiMo posters on March 14, between 16:15 and 17:30 (in Querfoyer in front of the meeting rooms) without IDS Annual Meeting registration.
The paper “Analysis of the Impact of Negative Sampling on Link Prediction in Knowledge Graphs” by Bhushan Kotnis and Vivi Nastase has received the Best Paper Award at the 1st Workshop on Knowledge Base Construction, Reasoning and Mining (KBCOM 2018) in Los Angeles, California.
The paper will be presented on Friday, February 9, at 15:30.
We congratulate the authors for their excellent work.