Jun.-Prof. Dr. Henning Wachsmuth - Contact (Paderborn University)

Identifying Feedback Types to Augment Feedback Comment Generation

M. Stahl, H. Wachsmuth, in: Proceedings of the 16th International Natural Language Generation Conference, 2023

In the context of language learning, feedback comment generation is the task of generating hints or explanatory notes for learner texts that help understand why a part of text is erroneous. This paper presents our approach to the Feedback Comment Generation Shared Task, collocated with the 16th International Natural Language Generation Conference (INLG 2023). The approach augments the generation of feedback comments by a self-supervised identification of feedback types in a multitask-learning setting. Within the shared task, other approaches performed more effective, yet the combined modeling of feedback type classification and feedback comment generation is superior to performing feedback generation only.

The Moral Debater: A Study on the Computational Generation of Morally Framed Arguments

M. Alshomary, R. El Baff, T. Gurcke, H. Wachsmuth, in: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, 2022, pp. 8782 - 8797

"Mama Always Had a Way of Explaining Things So I Could Understand": A Dialogue Corpus for Learning How to Explain

H. Wachsmuth, M. Alshomary, in: Proceedings of the 29th International Conference on Computational Linguistics, 2022, pp. 344 - 354

On the Role of Knowledge in Computational Argumentation

A. Lauscher, H. Wachsmuth, I. Gurevych, G. Glavaš, Transactions of the Association for Computational Linguistics (2022)

Identifying the Human Values behind Arguments

J. Kiesel, M. Alshomary, N. Handke, X. Cai, H. Wachsmuth, B. Stein, in: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, 2022, pp. 4459 - 4471

Back to the Roots: Predicting the Source Domain of Metaphors using Contrastive Learning

M. Sengupta, M. Alshomary, H. Wachsmuth, in: Proceedings of the 2022 Workshop on Figurative Language Processing, 2022

To Prefer or to Choose? Generating Agency and Power Counterfactuals Jointly for Gender Bias Mitigation

M. Stahl, M. Spliethöver, H. Wachsmuth, in: Proceedings of the Fifth Workshop on Natural Language Processing and Computational Social Science, 2022

Abstract

Gender bias may emerge from an unequal representation of agency and power, for example, by portraying women frequently as passive and powerless ("She accepted her future'') and men as proactive and powerful ("He chose his future''). When language models learn from respective texts, they may reproduce or even amplify the bias. An effective way to mitigate bias is to generate counterfactual sentences with opposite agency and power to the training. Recent work targeted agency-specific verbs from a lexicon to this end. We argue that this is insufficient, due to the interaction of agency and power and their dependence on context. In this paper, we thus develop a new rewriting model that identifies verbs with the desired agency and power in the context of the given sentence. The verbs' probability is then boosted to encourage the model to rewrite both connotations jointly. According to automatic metrics, our model effectively controls for power while being competitive in agency to the state of the art. In our evaluation, human annotators favored its counterfactuals in terms of both connotations, also deeming its meaning preservation better.

Analyzing Culture-Specific Argument Structures in Learner Essays

W. Chen, M. Chen, G. Mudgal, H. Wachsmuth, in: Proceedings of the 9th Workshop on Argument Mining (ArgMining 2022), 2022, pp. 51 - 61

Generating Contrastive Snippets for Argument Search

M. Alshomary, J. Rieskamp, H. Wachsmuth, in: Proceedings of the 9th International Conference on Computational Models of Argument, 2022, pp. 21 - 31

DOI

Investigating the argumentation structures of EFL learners from diverse language backgrounds

M. Chen, G. Mudgal, W. Chen, H. Wachsmuth. Investigating the argumentation structures of EFL learners from diverse language backgrounds. In: , 2022.

Learning From Revisions: Quality Assessment of Claims in Argumentation at Scale

G. Skitalinskaya, J. Klaff, H. Wachsmuth, in: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, 2021, pp. 1718-1729

Overview of Touché 2021: Argument Retrieval

A. Bondarenko, L. Gienapp, M. Fröbe, M. Beloucif, Y. Ajjour, A. Panchenko, C. Biemann, B. Stein, H. Wachsmuth, M. Potthast, M. Hagen, in: Proceedings of the 43rd annual European Conference on Information Retrieval Research, 2021, pp. 384-395

What Is Unclear? Computational Assessment of Task Clarity in Crowdsourcing

Z. Nouri, U. Gadiraju, G. Engels, H. Wachsmuth, in: Proceedings of the 32nd ACM Conference on Hypertext and Social Media, 2021, pp. 165-175

Download

https://dl.acm.org/doi/pdf/10.1145/3465336.3475109

Bias Silhouette Analysis: Towards Assessing the Quality of Bias Metrics for Word Embedding Models

M. Spliethöver, H. Wachsmuth, in: Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21, 2021, pp. 552-559

Abstract

Download

DOI

Word embedding models reflect bias towards genders, ethnicities, and other social groups present in the underlying training data. Metrics such as ECT, RNSB, and WEAT quantify bias in these models based on predefined word lists representing social groups and bias-conveying concepts. How suitable these lists actually are to reveal bias - let alone the bias metrics in general - remains unclear, though. In this paper, we study how to assess the quality of bias metrics for word embedding models. In particular, we present a generic method, Bias Silhouette Analysis (BSA), that quantifies the accuracy and robustness of such a metric and of the word lists used. Given a biased and an unbiased reference embedding model, BSA applies the metric systematically for several subsets of the lists to the models. The variance and rate of convergence of the bias values of each model then entail the robustness of the word lists, whereas the distance between the models' values gives indications of the general accuracy of the metric with the word lists. We demonstrate the behavior of BSA on two standard embedding models for the three mentioned metrics with several word lists from existing research.

https://www.ijcai.org/proceedings/2021/77

Generating Informative Conclusions for Argumentative Texts

S. Syed, K. Al-Khatib, M. Alshomary, H. Wachsmuth, M. Potthast, in: Proceedings of the Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021): Findings, 2021, pp. 3482-3493

Download

https://aclanthology.org/2021.findings-acl.306.pdf

Syntopical Graphs for Computational Argumentation Tasks

J. Barrow, R. Jain, N. Lipka, F. Dernoncourt, V. Morariu, V. Manjunatha, D. Oard, P. Resnik, H. Wachsmuth, in: Proceedings of the Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021), 2021, pp. 1583-1595

Download

https://aclanthology.org/2021.acl-long.126.pdf

Employing Argumentation Knowledge Graphs for Neural Argument Generation

K. Al-Khatib, L. Trautner, H. Wachsmuth, Y. Hou, B. Stein, in: Proceedings of the Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021), 2021, pp. 4744-4754

The Meant, the Said, and the Understood: Conversational Argument Search and Cognitive Biases

J. Kiesel, D. Spina, H. Wachsmuth, B. Stein, in: Proceedings of the 2021 Conversational User Interfaces Conference, 2021, pp. 1-5

Toward Audience-aware Argument Generation

M. Alshomary, H. Wachsmuth, Patterns (2021), 2(6)

Key Point Analysis via Contrastive Learning and Extractive Argument Summarization

M. Alshomary, T. Gurcke, S. Syed, P. Heinisch, M. Spliethöver, P. Cimiano, M. Potthast, H. Wachsmuth, in: Proceedings of the 8th Workshop on Argument Mining, 2021, pp. 184 - 189

iClarify - A Tool to Help Requesters Iteratively Improve Task Descriptions in Crowdsourcing

Z. Nouri, N. Prakash, U. Gadiraju, H. Wachsmuth, in: Proceedings of the Ninth AAAI Conference on Human Computation and Crowdsourcing, HCOMP 2021, 2021

Assessing the Sufficiency of Arguments through Conclusion Generation

T. Gurcke, M. Alshomary, H. Wachsmuth, in: Proceedings of the 8th Workshop on Argument Mining, 2021, pp. 67 - 77

Belief-based Generation of Argumentative Claims

M. Alshomary, W. Chen, T. Gurcke, H. Wachsmuth, in: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, Association for Computational Linguistics, 2021, pp. 224-223

Abstract

When engaging in argumentative discourse, skilled human debaters tailor claims to the beliefs of the audience, to construct effective arguments. Recently, the field of computational argumentation witnessed extensive effort to address the automatic generation of arguments. However, existing approaches do not perform any audience-specific adaptation. In this work, we aim to bridge this gap by studying the task of belief-based claim generation: Given a controversial topic and a set of beliefs, generate an argumentative claim tailored to the beliefs. To tackle this task, we model the people's prior beliefs through their stances on controversial topics and extend state-of-the-art text generation models to generate claims conditioned on the beliefs. Our automatic evaluation confirms the ability of our approach to adapt claims to a set of given beliefs. In a manual study, we additionally evaluate the generated claims in terms of informativeness and their likelihood to be uttered by someone with a respective belief. Our results reveal the limitations of modeling users' beliefs based on their stances, but demonstrate the potential of encoding beliefs into argumentative texts, laying the ground for future exploration of audience reach.

Controlled Neural Sentence-Level Reframing of News Articles

W. Chen, K. Al Khatib, B. Stein, H. Wachsmuth, in: Findings of the Association for Computational Linguistics: EMNLP 2021, 2021, pp. 2683 - 2693

Argument Undermining: Counter-Argument Generation by Attacking Weak Premises

M. Alshomary, S. Syed, M. Potthast, H. Wachsmuth, in: Proceedings of the Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021), Association for Computational Linguistics, 2021, pp. 1816–1827

DOI

Explanation as a Social Practice: Toward a Conceptual Framework for the Social Design of AI Systems

K.J. Rohlfing, P. Cimiano, I. Scharlau, T. Matzner, H.M. Buhl, H. Buschmeier, E. Esposito, A. Grimminger, B. Hammer, R. Häb-Umbach, I. Horwath, E. Hüllermeier, F. Kern, S. Kopp, K. Thommes, A. Ngonga Ngomo, C. Schulte, H. Wachsmuth, P. Wagner, B. Wrede, IEEE Transactions on Cognitive and Developmental Systems (2021), 13(3), pp. 717-728

DOI

Explanation as a Social Practice: Toward a Conceptual Framework for the Social Design of Al Systems

K.J. Rohlfing, P. Cimiano, I. Scharlau, T. Matzner, H.M. Buhl, H. Buschmeier, E. Esposito, A. Grimminger, B. Hammer, R. Haeb-Umbach, I. Horwath, E. Huellermeier, F. Kern, S. Kopp, K. Thommes, A. Ngonga Ngomo, C. Schulte, H. Wachsmuth, P. Wagner, B. Wrede, IEEE Transactions on Cognitive and Development Systems (2021), 13(3), pp. 717-728

Abstract

Download

DOI

The recent surge of interest in explainability in artificial intelligence (XAI) is propelled by not only technological advancements in machine learning but also by regulatory initiatives to foster transparency in algorithmic decision making. In this article, we revise the current concept of explainability and identify three limitations: passive explainee, narrow view on the social process, and undifferentiated assessment of explainee’s understanding. In order to overcome these limitations, we present explanation as a social practice in which explainer and explainee co-construct understanding on the microlevel. We view the co-construction on a microlevel as embedded into a macrolevel, yielding expectations concerning, e.g., social roles or partner models: typically, the role of the explainer is to provide an explanation and to adapt it to the current level of explainee’s understanding; the explainee, in turn, is expected to provide cues that direct the explainer. Building on explanations being a social practice, we present a conceptual framework that aims to guide future research in XAI. The framework relies on the key concepts of monitoring and scaffolding to capture the development of interaction. We relate our conceptual framework and our new perspective on explaining to transparency and autonomy as objectives considered for XAI.

article_09_2021_haebumbach.pdf -

Mining Crowdsourcing Problems from Discussion Forums of Workers

Z. Nouri, H. Wachsmuth, G. Engels, in: Proceedings of COLING 2020, the 28th International Conference on Computational Linguistics, 2020, pp. 6264-6276

Persuasiveness of News Editorials depending on Ideology and Personality

R. El Baff, K. Al-Khatib, B. Stein, H. Wachsmuth, in: Third Workshop on Computational Modeling of People's Opinions, Personality, and Emotions in Social Media (PEOPLES 2020), 2020, pp. 29-40

Argument from Old Man's View: Assessing Social Bias in Argumentation

M. Spliethöver, H. Wachsmuth, in: Proceedings of the 7th Workshop on Argument Mining (ArgMining 2020), 2020, pp. 76-87

Download

https://www.aclweb.org/anthology/2020.argmining-1.9

Semi-Supervised Cleansing of Web Argument Corpora

J. Dorsch, H. Wachsmuth, in: Proceedings of the 7th Workshop on Argument Mining (ArgMining 2020), 2020, pp. 19-29

Overview of Touché 2020: Argument Retrieval

A. Bondarenko, M. Fröbe, M. Beloucif, L. Gienapp, Y. Ajjour, A. Panchenko, C. Biemann, B. Stein, H. Wachsmuth, M. Potthast, M. Hagen, in: CEUR Workshop Proceedings, 2020, pp. 384-395

Intrinsic Quality Assessment of Arguments

H. Wachsmuth, T. Werner, in: Proceedings of COLING 2020, the 28th International Conference on Computational Linguistics, 2020, pp. 6739-6745

Analyzing the Persuasive Effect of Style in News Editorial Argumentation

R. El Baff, H. Wachsmuth, K. Al-Khatib, B. Stein, in: Proceedings of 58th Annual Meeting of the Association for Computational Linguistics, 2020, pp. 553-564

Extractive Snippet Generation for Arguments

M. Alshomary, N. Düsterhus, H. Wachsmuth, in: Proceedings of 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2020, pp. 1969-1972

End-to-End Argumentation Knowledge Graph Construction

K. Al-Khatib, Y. Hou, H. Wachsmuth, C. Jochim, F. Bonin, B. Stein, in: Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020), 2020, pp. 7367 - 7374

Touché: First Shared Task on Argument Retrieval

A. Bondarenko, M. Hagen, M. Potthast, H. Wachsmuth, M. Beloucif, C. Biemann, A. Panchenko, B. Stein, in: Proceedings of the 42nd European Conference on Information Retrieval (ECIR 2020), 2020, pp. 517-523

Investigating Expectations for Voice-based and Conversational Argument Search on the Web

J. Kiesel, K. Lang, H. Wachsmuth, E. Hornecker, B. Stein, in: Proceedings of the 2020 ACM SIGIR Conference on Human Information Interaction & Retrieval (CHIIR 2020), 2020, pp. 53-62

Visual Analysis of Argumentation in Essays

D. Kiesel, P. Riehmann, H. Wachsmuth, B. Stein, B. Fröhlich, IEEE Transactions of Visualization & Computer Graphics (2020), 27(2), pp. 1139-1148

Analyzing Political Bias and Unfairness in News Articles at Different Levels of Granularity

W. Chen, K. Al-Khatib, H. Wachsmuth, B. Stein, in: Proceedings of the Fourth Workshop on Natural Language Processing and Computational Social Science, 2020, pp. 149-154

Task Proposal: Abstractive Snippet Generation for Web Pages

S. Syed, W. Chen, M. Hagen, B. Stein, H. Wachsmuth, M. Potthast, in: Proceedings of the 13th International Conference on Natural Language Generation (INLG 2020), 2020, pp. 237-241

Detecting Media Bias in News Articles using Gaussian Bias Distributions

W. Chen, K. Al-Khatib, B. Stein, H. Wachsmuth, in: Findings of the Association for Computational Linguistics: EMNLP 2020, 2020, pp. 4290-4300

Target Inference in Argument Conclusion Generation

M. Alshomary, S. Syed, M. Potthast, H. Wachsmuth, in: Proceedings of 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020), Association for Computational Linguistics, 2020, pp. 4334-4345

CauseNet: Towards a Causality Graph Extracted from the Web

S. Heindorf, Y. Scholten, H. Wachsmuth, A. Ngonga Ngomo, M. Potthast, in: Proceedings of the 28th ACM International Conference on Information and Knowledge Management (CIKM 2020), 2020, pp. 3023-3030

Download

DOI

https://papers.dice-research.org/2020/CIKM-20/heindorf_2020a_public.pdf

Argument Search: Assessing Argument Relevance

M. Potthast, L. Gienapp, F. Euchner, N. Heilenkötter, N. Weidmann, H. Wachsmuth, B. Stein, M. Hagen, in: 42nd International ACM Conference on Research and Development in Information Retrieval (SIGIR 2019), ACM, 2019, pp. 1117 - 1120

DOI

Book Review: Argumentation Mining

H. Wachsmuth, Computational Linguistics, ACL (2019), pp. 603 - 606

Data Acquisition for Argument Search: The args.me Corpus

Y. Ajjour, H. Wachsmuth, J. Kiesel, M. Potthast, M. Hagen, B. Stein, in: Proceedings of the 42nd Edition of the German Conference on Artificial Intelligence, 2019, pp. 48-59

Modeling Frames in Argumentation

Y. Ajjour, M. Alshomary, H. Wachsmuth, B. Stein, in: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, 2019, pp. 2915 - 2925

Proceedings of the 6th Workshop on Argument Mining

B. Stein, H. Wachsmuth, Association for Computational Linguistics, 2019

Computational Argumentation Synthesis as a Language Modeling Task

R. El Baff, H. Wachsmuth, K. Al-Khatib, M. Stede, B. Stein, in: Proceedings of the 12th International Conference on Natural Language Generation, Association for Computational Linguistics, 2019, pp. 54-64

Wikipedia Text Reuse: Within and Without

M. Alshomary, M. Völske, T. Licht, H. Wachsmuth, B. Stein, M. Hagen, M. Potthast, in: Advances in Information Retrieval, Springer International Publishing, 2019, pp. 747-754

Abstract

We study text reuse related to Wikipedia at scale by compiling the first corpus of text reuse cases within Wikipedia as well as without (i.e., reuse of Wikipedia text in a sample of the Common Crawl). To discover reuse beyond verbatim copy and paste, we employ state-of-the-art text reuse detection technology, scaling it for the first time to process the entire Wikipedia as part of a distributed retrieval pipeline. We further report on a pilot analysis of the 100 million reuse cases inside, and the 1.6 million reuse cases outside Wikipedia that we discovered. Text reuse inside Wikipedia gives rise to new tasks such as article template induction, fixing quality flaws, or complementing Wikipedia's ontology. Text reuse outside Wikipedia yields a tangible metric for the emerging field of quantifying Wikipedia's influence on the web. To foster future research into these tasks, and for reproducibility's sake, the Wikipedia text reuse corpus and the retrieval pipeline are made freely available.

Unraveling the Search Space of Abusive Language in Wikipedia with Dynamic Lexicon Acquisition

W. Chen, K. Al-Khatib, M. Hagen, H. Wachsmuth, B. Stein, in: Proceedings of the Second Workshop on Natural Language Processing for Internet Freedom, 2019, pp. 76-82

The Argument Reasoning Comprehension Task: Identification and Reconstruction of Implicit Warrants

I. Habernal, H. Wachsmuth, I. Gurevych, B. Stein, in: Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2018, pp. 1930–1940

Modeling Deliberative Argumentation Strategies on Wikipedia

K. Al Khatib, H. Wachsmuth, K. Lang, J. Herpel, M. Hagen, B. Stein, in: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2018, pp. 2545-2555

Before Name-Calling: Dynamics and Triggers of Ad Hominem Fallacies in Web Argumentation

I. Habernal, H. Wachsmuth, I. Gurevych, B. Stein, in: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), 2018, pp. 386-396

SemEval-2018 Task 12: The Argument Reasoning Comprehension Task

I. Habernal, H. Wachsmuth, I. Gurevych, B. Stein, in: Proceedings of The 12th International Workshop on Semantic Evaluation, 2018, pp. 763-772

Retrieval of the Best Counterargument without Prior Topic Knowledge

H. Wachsmuth, S. Syed, B. Stein, in: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2018, pp. 241-251

Argumentation Synthesis following Rhetorical Strategies

H. Wachsmuth, M. Stede, R. El Baff, K. Al Khatib, M. Skeppstedt, B. Stein, in: Proceedings of the 27th International Conference on Computational Linguistics, 2018, pp. 3753-3765

Downloads

Visualization of the Topic Space of Argument Search Results in args. me

Y. Ajjour, H. Wachsmuth, D. Kiesel, P. Riehmann, F. Fan, G. Castiglia, R. Adejoh, B. Fröhlich, B. Stein, in: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, 2018, pp. 60-65

Challenge or Empower: Revisiting Argumentation Quality in a News Editorial Corpus

R. El Baff, H. Wachsmuth, K. Al Khatib, B. Stein, in: Proceedings of the 22nd Conference on Computational Natural Language Learning, Association for Computational Linguistics, 2018, pp. 454-464

Learning to Flip the Bias of News Headlines

W. Chen, H. Wachsmuth, K. Al Khatib, B. Stein, in: Proceedings of the 11th International Conference on Natural Language Generation, Association for Computational Linguistics, 2018, pp. 79-88

Unit Segmentation of Argumentative Texts

Y. Ajjour, W. Chen, J. Kiesel, H. Wachsmuth, B. Stein, in: Proceedings of the 4th Workshop on Argument Mining, 2017, pp. 118-128

Patterns of Argumentation Strategies across Topics

K. Al Khatib, H. Wachsmuth, M. Hagen, B. Stein, in: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, 2017, pp. 1362-1368

WAT-SL: A Customizable Web Annotation Tool for Segment Labeling

J. Kiesel, H. Wachsmuth, K. Al Khatib, B. Stein, in: Proceedings of the Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics, 2017, pp. 13-16

"Page Rank'' for Argument Relevance

H. Wachsmuth, B. Stein, Y. Ajjour, in: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, 2017, pp. 1117-1127

Building an Argument Search Engine for the Web

H. Wachsmuth, M. Potthast, K. Al-Khatib, Y. Ajjour, J. Puschmann, J. Qu, J. Dorsch, V. Morari, J. Bevendorff, B. Stein, in: Proceedings of the 4th Workshop on Argument Mining, 2017, pp. 49-59

The Impact of Modeling Overall Argumentation with Tree Kernels

H. Wachsmuth, G. Da San Martino, D. Kiesel, B. Stein, in: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, 2017, pp. 2369-2379

Computational Argumentation Quality Assessment in Natural Language

H. Wachsmuth, N. Naderi, Y. Hou, Y. Bilu, V. Prabhakaran, T.A. Thijm, G. Hirst, B. Stein, in: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, 2017, pp. 176-187

A Universal Model for Discourse-Level Argumentation Analysis

H. Wachsmuth, B. Stein, Special Section of the ACM Transactions on Internet Technology: Argumentation in Social Media (2017)(3), pp. 1-24

Argumentation Quality Assessment: Theory vs. Practice

H. Wachsmuth, N. Naderi, I. Habernal, Y. Hou, G. Hirst, I. Gurevych, B. Stein, in: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2017, pp. 250-255

DOI

A News Editorial Corpus for Mining Argumentation Strategies

K. Al Khatib, H. Wachsmuth, J. Kiesel, M. Hagen, B. Stein, in: Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, 2016, pp. 3433-3443

Cross-Domain Mining of Argumentative Text through Distant Supervision

K. Al-Khatib, H. Wachsmuth, M. Hagen, J. Köhler, B. Stein, in: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2016, pp. 1395-1404

DOI

Using Argument Mining to Assess the Argumentation Quality of Essays

H. Wachsmuth, K. Al Khatib, B. Stein, in: Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, 2016, pp. 1680-1691

Pipelines Für Effiziente und Robuste Ad-hoc Textanalyse

H. Wachsmuth, in: Ausgezeichnete Informatikdissertationen 2015, 2016, pp. 329-338

Sentiment Flow - A General Model of Web Review Argumentation

H. Wachsmuth, J. Kiesel, B. Stein, in: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, 2015, pp. 601-611

DOI

Text Analysis Pipelines - Towards Ad-hoc Large-scale Text Mining

H. Wachsmuth, 2015

DOI

Pipelines for Ad-hoc Large-scale Text Mining

H. Wachsmuth, 2015

Abstract

Download

Today's web search and big data analytics applications aim to address information needs~(typically given in the form of search queries) ad-hoc on large numbers of texts. In order to directly return relevant information instead of only returning potentially relevant texts, these applications have begun to employ text mining. The term text mining covers tasks that deal with the inference of structured high-quality information from collections and streams of unstructured input texts. Text mining requires task-specific text analysis processes that may consist of several interdependent steps. These processes are realized with sequences of algorithms from information extraction, text classification, and natural language processing. However, the use of such text analysis pipelines is still restricted to addressing a few predefined information needs. We argue that the reasons behind are three-fold: First, text analysis pipelines are usually made manually in respect of the given information need and input texts, because their design requires expert knowledge about the algorithms to be employed. When information needs have to be addressed that are unknown beforehand, text mining hence cannot be performed ad-hoc. Second, text analysis pipelines tend to be inefficient in terms of run-time, because their execution often includes analyzing texts with computationally expensive algorithms. When information needs have to be addressed ad-hoc, text mining hence cannot be performed in the large. And third, text analysis pipelines tend not to robustly achieve high effectiveness on all texts, because their results are often inferred by algorithms that rely on domain-dependent features of texts. Hence, text mining currently cannot guarantee to infer high-quality information. In this thesis, we contribute to the question of how to address information needs from text mining ad-hoc in an efficient and domain-robust manner. We observe that knowledge about a text analysis process and information obtained within the process help to improve the design, the execution, and the results of the pipeline that realizes the process. To this end, we apply different techniques from classical and statistical artificial intelligence. In particular, we first develop knowledge-based approaches for an ad-hoc pipeline construction and for an optimal execution of a pipeline on its input. Then, we show theoretically and practically how to optimize and adapt the schedule of the algorithms in a pipeline based on information in the analyzed input texts in order to maximize execution efficiency. Finally, we learn patterns in the argumentation structures of texts statistically that remain strongly invariant across domains and that, thereby, allow for more robust analysis results in a restricted set of tasks. We formally analyze all developed approaches and we implement them as open-source software applications. Based on these applications, we evaluate the approaches on established and on newly created collections of texts for scientifically and industrially important text analysis tasks, such as financial event extraction and fine-grained sentiment analysis. Our findings show that text analysis pipelines can be designed automatically, which process only portions of text that are relevant for the information need at hand. Through scheduling, the run-time efficiency of pipelines can be improved by up to more than one order of magnitude while maintaining effectiveness. Moreover, we provide evidence that a pipeline's domain robustness substantially benefits from focusing on argumentation structure in tasks like sentiment analysis. We conclude that our approaches denote essential building blocks of enabling ad-hoc large-scale text mining in web search and big data analytics applications.

https://webis.de/downloads/publications/papers/wachsmuth_2013.pdf - (confirmation)

A Review Corpus for Argumentation Analysis

H. Wachsmuth, M. Trenkmann, B. Stein, G. Engels, T. Palakarska, in: Proceedings of the 15th International Conference on Intelligent Text Processing and Computational Linguistics, 2014, pp. 115–127

PBlaman: performance blame analysis based on Palladio contracts

F. Brüseke, H. Wachsmuth, G. Engels, S. Becker, in: Proceedings of the 4th International Symposium on Autonomous Minirobots for Research and Edutainment, 2014, pp. 1975-2004

Modeling Review Argumentation for Robust Sentiment Analysis

H. Wachsmuth, M. Trenkmann, B. Stein, G. Engels, in: Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers, 2014, pp. 553-564

Learning Efficient Information Extraction on Heterogeneous Texts

H. Wachsmuth, B. Stein, G. Engels, in: Proceedings of the Sixth International Joint Conference on Natural Language Processing, 2013, pp. 534-542

Information Extraction as a Filtering Task

H. Wachsmuth, B. Stein, G. Engels, in: Proceedings of the 22nd ACM International Conference on Conference on Information & Knowledge Management, 2013, pp. 2049-2058

Automatic Pipeline Construction for Real-Time Annotation

H. Wachsmuth, M. Rose, G. Engels, in: 14th International Conference on Intelligent Text Processing and Computational Linguistics, 2013, pp. 38-49

Optimal Scheduling of Information Extraction Algorithms

H. Wachsmuth, B. Stein, in: Proceedings of COLING 2012: Posters, 2012, pp. 1281-1290

Back to the Roots of Genres: Text Classification by Language Function

H. Wachsmuth, K. Bujna, in: Proceedings of 5th International Joint Conference on Natural Language Processing, 2011, pp. 632-640

Constructing Efficient Information Extraction Pipelines

H. Wachsmuth, B. Stein, G. Engels, in: 20th ACM International Conference on Information and Knowledge Management, 2011, pp. 2237-2240

Efficient Statement Identification for Automatic Market Forecasting

H. Wachsmuth, P. Prettenhofer, B. Stein, in: Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010), 2010, pp. 1128-1136

Smart Teams: Simulating Large Robotic Swarms in Vast Environments

S. Arens, A. Buss, H. Deck, M. Dynia, M. Fischer, H. Hagedorn, P. Isaak, J. Kutylowski, F. Meyer auf der Heide, V. Nesterow, A. Ogiermann, B. Stobbe, T. Storm, H. Wachsmuth, in: Proceedings of the 4th International Symposium on Autonomous Minirobots for Research and Edutainment, Heinz Nixdorf Institut, University of Paderborn, 2007, pp. 215-222

Abstract

We consider the problem of exploring an unknown environment using a swarm of autonomous robots with collective behavior emerging from their local rules. Each robot has only a very restricted view on the environment which makes cooperation difficult. We introduce a software system which is capable of simulating a large number of such robots (e.g. 1000) on highly complex terrains with millions of obstacles. Its main purpose is to easily integrate and evaluate any kind of algorithm for controlling the robot behavior. The simulation may be observed in real-time via a visualization that displays both the individual and the collective progress of the robots. We present the system design, its main features and underlying concepts.