Joint project between Prof. Anette Frank (ICL, Heidelberg University) and Prof. Heiner Stuckenschmidt (University of Mannheim) within the DFG priority program RATIO: Robust Argumentation Machines

The project will uncover missing explanatory links in argumentative texts, fill in automatically acquired knowledge that makes the structure of the argument explicit and establish and verify the knowledge-enhanced argumentation structure with a combination of formal reasoning and machine learning.

People:

PIs: Prof. Dr. Anette Frank, Heidelberg University, Prof. Dr. Heiner Stuckenschmidt, University of Mannheim

Post-doctoral researchers: Dr. Viviane Nastase, Heidelberg University, Dr. Ioana Hulpus, Univ. Mannheim, Dr. Christian Meilicke, Univ. Mannheim

Doctoral researchers: Maria Becker, M.A. and Juri Opitz, B.A., Heidelberg University; Jonathan Kobbe, MSc., Univ. Mannheim

Selected Publications:

• Hulpus, I., Kobbe, J., Becker, M., Opitz, J., Hirst, G., Meilicke, C., Nastase, N., Stuckenschmidt, H. and Frank, A. (2019): Towards Explaining Natural Language Arguments with Background Knowledge, Proceedings of the 1st Workshop on Semantic Explainability – co-located with the 18th International Semantic Web Conference (ISWC 2019), Christchurch, New Zealand.
• Kobbe, J., Opitz, J., Becker, M., Hulpus, I., Stuckenschmidt, H. and Frank, A. (2019): Exploiting Background Knowledge for Argumentative Relation Classification, Second Conference on Language, Data and Knowledge (LDK 2019). Best Student Paper Award.
• Opitz, J. and Frank, A. (2019): Dissecting Content and Context in Argumentative Relation Analysis. Proceedings of the Sixth Workshop on Argument Mining (co-located with ACL 2019), Florence, Italy.
• Becker, M., Staniek, M., Nastase, V., and Frank, A. (2019): Assessing the Difficulty of Classifying ConceptNet Relations in a Multi-Label Classification Setting. RELATIONS - Workshop on meaning relations between phrases and sentences (co-located with IWCS).
• Opitz, J. and Frank, A. (2019): Automatic Accuracy Prediction for AMR Parsing. Proceedings of The Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019), Minneapolis, Minnesota, pp. 212–-223.

PIs: Prof. Dr. Anette Frank, Prof. Dr. Katja Markert, Prof. Dr. Andreas Witt
Coordinator: Antonina Werthmann, M.A.

Group Leaders:
Area A: Dr. Josef Ruppenhofer
Area B: Dr. Ines Rehbein
Area C: Dr. Viviane Nastase

PhD students:
Esther van den Berg
Ngoc Bich Do
Angel Daza
Maria Becker
Bhushan Kotnis
Juri Opitz

Published Resources: LiMo Dataverse

Selected Publications (with PI and supervisor Anette Frank):

• Daza, A. and Frank, A. (2019): Translate and Label! An Encoder-Decoder Approach for Cross-lingual Semantic Role Labeling. in: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (IJCNLP-EMNLP), Hong Kong, China, pp. 603–615.
• Nastase, V. and Kotnis, B. (2019): Abstract Graphs and Abstract Paths for Knowledge Graph Completion. Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019), Minneapolis, Minnesota, pp. 147--157.
• Opitz, J. and Frank, A. (2019): An Argument-Marker Model for Syntax-Agnostic Proto-Role Labeling. Proceedings of The Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019), pp. 224–234, Minneapolis, Minnesota.
• Daza, A. and Frank, A. (2018): A Sequence-to-Sequence Model for Semantic Role Labeling. Proceedings of the 3rd Workshop on Representation Learning for NLP, RepL4NLP@ACL 2018, Melbourne, Australia, pp. 207--216.
• Nastase, V., Fritz, D., Frank, A. (2018): DeModify: A Dataset for Analyzing Contextual Constraints on Modifier Deletion. Proceedings of the 11th International Conference on Language Resources and Evaluation, 7-12 May 2018, Miyazaki, Japan.
• Becker, M., Staniek, M., Nastase, V., Palmer, A., and Frank, A. (2017): Classifying Semantic Clause Types: Modeling Context and Genre Characteristics with Recurrent Neural Networks and Attention. Proceedings of *SEM (Joint Conference on Lexical and Computational Semantics), Vancouver, Canada.
• Becker, M., Staniek, M., Nastase, V., and Frank, A. (2017): Enriching Argumentative Texts with Implicit Knowledge. Frasinca, F., Ittoo, A., Nguyen, L., and Metais, E. (eds.), Applications of Natural Language to Data Bases (NLDB) - Natural Language Processing and Information Systems, Lecture Notes in Computer Science, Springer.
• Becker, M., Palmer, A., and Frank, A. (2017): Semantic Clause Types and Modality as Features for Argument Analysis. Argument & Computation, Special Issue on Language and Argumentation.
• Do, B.-N., Rehbein, I., and Frank, A. (2017): What Do We Need to Know about an Unknown Word When Parsing German. Proceedings of the 1st Workshop on Subword and Character Level Models in NLP, Vancouver, Canada.
• Becker, M., Palmer, A., and Frank, A. (2016): Clause Types and Modality in Argumentative Microtexts. Workshop on Foundations of the Language of Argumentation (in conjunction with COMMA 2016), Potsdam, Germany, pp. 1--9.
• Becker, M., Palmer, A., and Frank, A. (2016): Argumentative texts and clause types. Proceedings of the 3rd Workshop on Argument Mining (ArgMining2016), Berlin, Germany, pp. 21--30.
• Sikos, J., Versley, Y., and Frank, A. (2016): Implicit Semantic Roles in a Multilingual Setting. Proceedings of the Fifth Joint Conference on Lexical and Computational Semantics (* SEM 2016), Berlin, Germany, 11-12 August, pp. 45--54.
• Marasović, A., Zhou, M., Palmer, A., and Frank, A. (2016): Modal Sense Classification At Large: Paraphrase-Driven Sense Projection, Semantically Enriched Classification Models and Cross-Genre Evaluations. Linguistic Issues in Language Technology, Special issue on Modality in Natural Language Understanding, Stanford, CA., vol. 14 (2), CSLI Publications.
• Zhou, M., Frank, A., Friedrich, A., and Palmer, A. (2015): Semantically Enriched Models for Modal Sense Classification. Proceedings of the EMNLP 2015 Workshop LSDSem: Linking Models of Lexical, Sentential and Discourse-level Semantics, Lisbon, Portugal, September.

People

Speaker: Prof. Dr. Iryna Gurevych, TU Darmstadt
Co-Speaker: Prof. Dr. Anette Frank, Heidelberg University

Research Area A: Graph-based Discourse Processing

A1: PI: Prof. Dr. Michael Strube, HITS, PhD researcher: Benjamin Heinzerling, M.A., HITS

A2: PI: Prof. Dr. Anette Frank, UHD, PhD researcher: Todor Mihaylov, M.Sc., Heidelberg University

A3: PI: Prof. Dr. Anette Frank and Prof. Dr. Michael Strube, PhD researcher: Ana Marasovic, M.Sc., Heidelberg University

For full information, areas and people see AIPHES project web page at TU Darmstadt.

Published Resources: Heidelberg NLPGroup's GitHub, AIPHES on HeiData and AIPHES GitHub

Publications

Guiding theme A2: Identification of Complex Event Structures in Discourse

• Mihaylov, T. and Frank, A. (2019): Discourse-Aware Semantic Self-Attention For Narrative Reading Comprehension. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019, Hong Kong, China, pp. 2541--2552.
• Mihaylov, T. and Frank, A. (2018): Knowledgeable Reader: Enhancing Cloze-Style Reading Comprehension with External Commonsense Knowledge. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Melbourne, Australia, pp. 821--832.
• Mihaylov, T. and Frank, A. (2017): Story Cloze Ending Selection Baselines and Data Examination. Proceedings of the Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics – Shared Task, Valencia, Spain.
• Mihaylov, T. and Frank, A. (2016): Discourse Relation Sense Classification Using Cross-argument Semantic Similarity Based on Word Embeddings. Proceedings of the Twentieth Conference on Computational Natural Language Learning - Shared Task, Berlin, Germany, pp. 100--107.
• Mihaylov, T. and Frank, A. (2016): AIPHES-HD system at TAC KBP 2016: Neural Event Trigger Span Detection and Event Type and Realis Disambiguation with Word Embeddings. Proceedings of the Twentieth Conference on Computational Natural Language Learning - Shared Task.

• Paul, D. and Frank, A. (2019): Ranking and Selecting Multi-Hop Knowledge Paths to Better Predict Human Needs. Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics, Minneapolis, Minnesota, USA, pp. 3671--3681.
• Marasović, A. and Frank, A. (2017): SRL4ORL: Improving Opinion Role Labelling using Multi-task Learning with Semantic Role Labeling”. In: Learning with Limited Labeled Data Workshop (NIPS), Long Beach, CA, USA.
• Marasović, A., Born, L., Opitz, J., and Frank, A. (2017): A Mention-Ranking Model for Abstract Anaphora Resolution. Proceedings of EMNLP 2017, Copenhagen, Denmark, pp. 221--232.
• Marasović, A. and Frank, A. (2016): Multilingual Modal Sense Classification using a Convolutional Neural Network. Proceedings of the 1st Workshop on Representation Learning for NLP, Berlin, Germany, pp. 111--120.
• Marasović, A., Zhou, M., Palmer, A., and Frank, A. (2016): Modal Sense Classification At Large: Paraphrase-Driven Sense Projection, Semantically Enriched Classification Models and Cross-Genre Evaluations. Linguistic Issues in Language Technology, Special issue on Modality in Natural Language Understanding, Stanford, CA., vol. 14 (2), CSLI Publications.

CLARIN-D is a new cooperation project funded by the BMBF that aims at realizing a sustainable research infrastructure offering language resources, tools and services for German language processing, to support research in the Humanities. The CLARIN-D consortium is led by the University of Tübingen.

ICL Heidelberg leads a focused CLARIN-D action group specializing on language resources and tools for research in Applied and Computational Linguistics.

During the project phase (2011 – 2016), three curation projects (CP 1-3) were conducted under coordination of Prof. Dr. Anette Frank.

More information can be found on the local project website as well as on the official F-AG7 web pages hosted by CLARIN-D.

Researchers (F-AG7 coordinators)

• Prof. Dr. Anette Frank, ICL Heidelberg
• Dr. Nils Reiter, formerly ICL Heidelberg, now IMS Stuttgart
• Éva Mújdricza-Maydt, ICL Heidelberg

Publications

• CP 3: "Semantische Annotation für Digital Humantities"
• Hartmann, S., Mújdricza-Maydt, E., Kuznetsov, I., Gurevych, I., and Frank, A. (2017): Assessing SRL Frameworks with Automatic Training Data Expansion. In Proceedings of the 11th Linguistic Annotation Workshop (LAW-XI 2017).
• Eckart de Castilho, R., Mújdricza-Maydt, É., Yimam, S.M., Hartmann, S., Gurevych, I., Frank, A. and Biemann, C. (2016): A Web-based Tool for the Integrated Annotation of Semantic and Syntactic Structures. In Proceedings of the LT4DH workshop at COLING 2016, Osaka, Japan
• Mújdricza-Maydt, É., Hartmann, S., Gurevych, I. and Frank, A. (2016): Combining Semantic Annotation of Word Sense & Semantic Roles: A Novel Annotation Scheme for VerbNet Roles on German Language Data. In Proceedings of LREC, Portorož, Slovenia, May.
• CP 2: "Linguistische Annotation von Nichtstandardvarietäten – Guidelines und Best Practices"
• Dipper, S., Lüdeling, A., and Reznicek, M. (2013): NoSta-D: A Corpus of German Non-Standard Varieties. In: Zampieri, Marcos & Diwersy, Sascha (Hrsg.): Non-standard Data Sources in Corpus-based Research. Aachen: Shaker Verlag. S. 69 – 76.
• CP 1: "Implementierung einer webbasierten Annotationsplatform für linguistische Annotationen"
• Eckart de Castilho, R., Biemann, C., Gurevych, I., and Yimam, S.M. (2014): WebAnno: a flexible, web-based annotation tool for CLARIN, In: Proceedings of the CLARIN Annual Conference (CAC) 2014, October 2014.
• Yimam , S.M., Eckart de Castilho, R., Gurevych, I., and Biemann C. (2014): Automatic Annotation Suggestions and Custom Annotation Layers in WebAnno, In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. System Demonstrations, p. 91--96, Association for Computational Linguistics, June 2014.
• Biemann, C., Bontcheva, K., Eckart de Castilho, R., Gurevych, I., and Yimam, S.M. (2014): Collaborative Web-based Tools for Multi-layer Text Annotation, In: Nancy Ide and James Pustejovsky: Text, Speech, and Technology book series, The Handbook of Linguistic Annotation, Springer, 2014.
• Yimam, S.M., Gurevych, I., Eckart de Castilho, R., and Biemann, C. (2013): WebAnno: A Flexible,Web-based and Visually Supported System for Distributed Annotations, In: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (System Demonstrations) (ACL 2013), ACL, p. 1-6, Association for Computational Linguistics, August 2013.

ICL runs a doctoral college entitled Coherence in Language Processing: Semantics beyond the Sentence. The 3-year doctoral program is funded by the Landesgraduiertenförderung (LGF) and is embedded within the joint ICL and HITS doctoral program Semantic Processing.

The PhD research training group consists of 5 PhD students working on various aspects of discourse-oriented semantic NLP. The program is jointly run by professors Anette Frank, Sebastian Padó, Stefan Riezler and Michael Strube. Speaker of the program is Anette Frank.

A project funded within the Sonderforschungsbereich SFB 619: "Ritual Dynamics"

Joint project of

• Prof. Dr. Anette Frank, Department of Computational Linguistics
• Prof. Dr. Axel Michaels, South-Asia Institute, Department of Classical Indology, University of Heidelberg

Researchers:

• Nils Reiter, Department of Computational Linguistics
• Anand Mishra, South-Asia Institute, Department of Classical Indology, University of Heidelberg
• Oliver Hellwig, South-Asia Institute, Department of Classical Indology, University of Heidelberg

Dissertation:

• Nils Reiter: Discovering Structural Similarities in Narrative Texts using Event Alignment Algorithms, Institut für Computerlinguistik, Universität Heidelberg, 2014 Supervisor: Prof. Dr. Anette Frank, Institut für Computerlinguistik, Heidelberg Co-Reviewer: Prof. Dr. Sebastian Padó, Institut für Maschinelle Sprachverarbeitung, Stuttgart

Publications:

• Reiter, N., Frank, A., and Hellwig, O. (2014): An NLP-based Cross-Document Approach to Narrative Structure Discovery. Literary and Linguistic Computing, Special Issue on Computational Models of Narrative.
• Frank, A., Bögel, T., Hellwig, O., and Reiter, N. (2012): Semantic Annotation for the Digital Humanities - Using Markov Logic Networks for Annotation Consistency Control. Linguistic Issues in Language Technology, 7, 1-21.
• Reiter, N., Hellwig, O., Frank, A., Gossmann, I., Larios, B. M., Rodrigues, J. and Zeller, B. (2011): Adapting NLP Tools and Frame-Semantic Resources for the Semantic Analysis of Ritual Descriptions. in: Sporleder, C., van den Bosch, A., and Zervanou, K. A. (eds.), Language Technology for Cultural Heritage, Foundations of Human Language Processing and Technology, Springer.
• Reiter, N., Hellwig, O., and Frank, A. (2011): Semi-Automatic Semantic Analysis of Rituals: Chances and Challenges. in: Felder, E., Müller, M., and Vogel, F. (eds.), Thematische Korpora als Basis diskurslinguistischer Analysen von Texten und Gesprächen, Korpuspragmatik, De Gruyter.
• Reiter, N., Hellwig, O., Mishra, A., Gossmann, I., Larios, B. M., Rodrigues, J., Zeller, B., and Frank, A. (2010): Adapting Standard NLP Tools and Resources to the Processing of Ritual Descriptions. Proceedings of the ECAI 2010 Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities (LaTeCH), Lissabon.
• Reiter, N., Hellwig, O., Mishra, A., Frank, A., and Burkhardt, J. (2010): Using NLP Methods for the Analysis of Rituals. Proceedings of the 7th International Conference on Language Resources and Evaluation (LREC 2010), Valletta, Malta.

Talks:

• Anette Frank and Nils Reiter: Invited talk at the First AMICUS Workshop (Automated Motif Discovery in Cultural Heritage and Scientific Communication Texts), Vienna, October 21st, 2010.

The Role of Context in Language Processing (2011 – 2012)

A new cooperation project between the Department of Computational Linguistics at Heidelberg University and the Department of Computing at Macquarie University, Australia. The project is funded by the Global Networks Project of the Excellence Initiative of Heidelberg University.

Coordination: Anette Frank (Heidelberg University) and Mark Johnson (Macquarie University)

This project aims to combine methods and insights from Computational Linguistics and Psycholinguistics. The focus is on modeling the role of linguistic and extra-linguistic context in (incremental) language processing, as key factors to support the efficiency of human language processing and acquisition. The Global Networks funding supports bi-lateral travels and PhD student exchange in the years 2011 and 2012.

A project funded within the FRONTIER innovation fund of the Excellence Initiative of the University of Heidelberg

Joint project of

• Prof. Dr. Anette Frank, Department of Computational Linguistics
• Dr. Michael Strube, EML Research gGmbH (now HITS)
• Dr. Susanne Krömker, Interdisciplinary Centre for Scientific Computing, IWR
• Prof. Dr. Christiane von Stutterheim, Department for German as a Foreign Language

Researchers:

• Michael Roth, Department of Computational Linguistics (now: University of the Saarland)
• Stefanie Schuldes, EML Research gGmbH

Publications:

• Schuldes, S., Boland, K., Roth, M., Strube, M., Kroemker, S. and Frank, A. (2011): Modeling spatial knowledge for generating verbal and visual route directions. Proceedings of the 15th Annual KES Conference, Lecture Notes in Artificial Intelligence, Springer-Verlag, to appear.
• Roth, M. and Frank, A. (2010): Computing EM-based alignments of routes and route directions as a basis for natural language generation. Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010), Beijing, China, August.
• Roth, M., Haas, M., Hildebrand, E., and Matios, E. (2010): The Heidelberg GIVE-2 System. Technical report, presented at the Generation Challenges Poster Session at INLG'10.
• Roth, M., Schuldes, S., Frank, A., and Strube, M. (2009): Creating an Annotated Corpus for Generating Walking Directions. in Proceedings of the ACL 2009 Workshop on Language Generation and Summarisation, Singapore.
• Roth, M. and Frank, A. (2009): A NLG-based Application for Walking Directions. in: Companion Volume to the Proceedings of the 47th Annual Meeting of the Association for Computational Linguistics and the 4th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing (ACL-IJCNLP), Singapore.