Brielen Madureira (she/her)

✉ madureiralasota (at) uni - potsdam . de

🔎 About me

I have been a research assistant doing a Ph.D. at the University of Potsdam, Germany, as a member of Prof. David Schlangen's Computational Linguistics Lab (colabPotsdam). My current research interests are building common ground in multimodal dialogue, incremental processing, and understanding the limits of current neural network models to process dialogue phenomena. I'm more broadly interested in bridging NLP and cognitive science, as well as all aspects of evaluation of language technologies and in Ethics in NLP. I also enjoy doing data analysis. The title of my thesis is "Incrementally Enriching the Common Ground: Cognitively Motivated Evaluative Approaches to Dialogue Processing with Deep Learning Models". I got my M.Sc. degree in Language Science and Technology at the University of Saarland, Germany. My master thesis was a project in the scope of the SFB1102 Project A3 with Prof. Alexander Koller. I applied semi-supervised learning methods to extract script knowledge from texts. Before that, I received my B.Sc. in Applied and Computational Mathematics at the Institute of Mathematics and Statistics of the University of São Paulo, Brazil.

📚 Publications

2024

• Brielen Madureira & David Schlangen (2024). It Couldn't Help But Overhear: On the Limits of Modelling Meta-Communicative Grounding Acts with Supervised Learning. SIGdial 2024 (upcoming). link
• Brielen Madureira (2024). Avaliação de Tecnologias de Linguagem. In: Caseli, H.M.; Nunes, M.G.V. (org.) Processamento de Linguagem Natural: Conceitos, Técnicas e Aplicações em Português. 2 ed. BPLN, 2024. link
• Brielen Madureira (2024). Diálogo e Interatividade. In: Caseli, H.M.; Nunes, M.G.V. (org.) Processamento de Linguagem Natural: Conceitos, Técnicas e Aplicações em Português. 2 ed. BPLN, 2024. link
• Brielen Madureira, Patrick Kahardipraja & David Schlangen (2024). When Only Time Will Tell: Interpreting How Transformers Process Local Ambiguities Through the Lens of Restart-Incrementality. ACL 2024 (upcoming). link
• Brielen Madureira & David Schlangen (2024). Taking Action Towards Graceful Interaction: The Effects of Performing Actions on Modelling Policies for Instruction Clarification Requests. In: Proceedings of the Third Workshop on Understanding Implicit and Underspecified Language. link

2023

• Patrick Kahardipraja, Brielen Madureira & David Schlangen (2023). TAPIR: Learning Adaptive Revision for Incremental Natural Language Understanding with a Two-Pass Model. In: Findings of the 61st Annual Meeting of the Association for Computational Linguistics. link
• Brielen Madureira & David Schlangen (2023). Instruction Clarification Requests in Multimodal Collaborative Dialogue Games: Tasks, and an Analysis of the CoDraw Dataset. In: Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics. link
• Brielen Madureira, Patrick Kahardipraja & David Schlangen (2023). The Road to Quality is Paved with Good Revisions: A Detailed Evaluation Methodology for Revision Policies in Incremental Sequence Labelling. In: In Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue. link
• Brielen Madureira & David Schlangen (2023). "Are you telling me to put glasses on the dog?" Content-Grounded Annotation of Instruction Clarification Requests in the CoDraw Dataset. Extended abstract presented as a posted in the 26th Workshop on the Semantics and Pragmatics of Dialogue. link to full version
• Kranti Chalamalasetti, Jana Götze, Sherzod Hakimov, Brielen Madureira, Philipp Sadler & David Schlangen (2023). clembench: Using Game Play to Evaluate Chat-Optimized Language Models as Conversational Agents. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. link
• Brielen Madureira, Pelin Çelikkol & David Schlangen (2023). Revising with a Backward Glance: Regressions and Skips during Reading as Cognitive Signals for Revision Policies in Incremental Processing. In: Proceedings of the 2023 SIGNLL Conference on Computational Natural Language Learning. Awarded honourable mention. link
• Brielen Madureira & Lucas Lasota (2023). On the Inquietudes of Language Technologies. Chapter in: Law and Bioethics, v.4 (New Technologies), org. Alegre, Mariana. link (in Portuguese).
• Brielen Madureira (2023). Incrementally Enriching the Common Ground: A Research Path. In Proceedings of the 19th Annual Meeting of the Young Reseachers' Roundtable on Spoken Dialogue Systems, pages 57–58, Prague, Czechia. Association for Computational Linguistics. link

2022

• Brielen Madureira & David Schlangen (2022). Can Visual Dialogue Models Do Scorekeeping? Exploring How Dialogue Representations Incrementally Encode Shared Knowledge. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 651-664, Dublin, Ireland. Association for Computational Linguistics. link
• Samuel Louvan, Andrea Madotto & Brielen Madureira (2022). Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop. Association for Computational Linguistics, Dublin, Ireland, edition. link

2021

• Patrick Kahardipraja, Brielen Madureira & David Schlangen (2021). Towards Incremental Transformers: An Empirical Analysis of Transformer Models for Incremental NLU. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. link
• Brielen Madureira (2021). Flamingos and Hedgehogs in the Croquet-Ground: Teaching Evaluation of NLP Systems for Undergraduate Students. In Proceedings of the Fifth Workshop on Teaching NLP, pages 87-91, Online. Association for Computational Linguistics. link

2020

• Brielen Madureira & David Schlangen (2020). Incremental Processing in the Age of Non-Incremental Encoders: An Empirical Assessment of Bidirectional Models for Incremental NLU. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 357-374, Online. Association for Computational Linguistics. link
• Brielen Madureira & David Schlangen (2020). An Overview of Natural Language State Representation for Reinforcement Learning. Presented at the ICML 2020 Workshop on Language in Reinforcement Learning (LaReL), Viena, Austria (moved online). link

👩‍🏫 Teaching

WS24

• Computerlinguistische Techniken, together with Prof. David Schlangen [B.Sc]

SS23

• Seminar: Dialogue Modeling, together with Jana Götze [B.Sc. and M.Sc.]
• Programmiersprache (Python) [B.Sc.]

WS22/23

• Seminar: Evaluation of NLP Systems [B.Sc.]
• Advanced Natural Language Processing, together with Sherzod Hakimov [M.Sc.]

SS22

• Seminar: Deep Learning for Natural Language Processing, together with Philipp Sadler [M.Sc.]
• Programmiersprache (Python), together with Anne Beyer [B.Sc.]

WS21/22

• Seminar: Mathematical Foundations of Language Modelling [B.Sc.]
• Advanced Natural Language Processing, together with Prof. David Schlangen and Jana Götze [M.Sc.]

SS221

• Seminar: Doing Science and Conducting Research [M.Sc.]
• Programmiersprache (Python), together with Anne Beyer [B.Sc.]

WS20/21

• Seminar: Evaluation of NLP Systems [B.Sc.]
• Computerlinguistische Techniken, together with Prof. David Schlangen [B.Sc]
• Basic Programming (Python), together with Berfin Aktas [M.Sc]

SS20

• Seminar: Reinforcement Learning for Natural Language Processing [M.Sc.]
• Programmiersprache (Python), together with Robin Rojowiec [B.Sc.]

WS18/19

• Tutorial for Prof. Alexander Koller's Computational Linguistics course [M.Sc.]

1/2015

• Tutorial for Prof. José Carlos Simon de Miranda's Introduction to Probability and Statistics [B.Sc.]

2/2014

• Tutorial for Prof. Marcelo Queiroz's Linear Programming course [B.Sc.]

1/2013

• Tutorial for Prof. Marcelo Queiroz's Linear Programming course [B.Sc.]

💬 Talks

• Buscando Momentos de Significado. NILC, ICMC USP São Carlos, Brazil. June 27, 2024.
• Are you telling me to put glasses on the dog? Queen Mary University of London. June 19, 2024.
• Incrementally Enriching the Common Ground. Computational Linguistics Colloquium at the University of Potsdam. May 14, 2024.
• Code Documentation. Youth Hacking 4 Freedom. March 14, 2024.
• What is going on at colab Potsdam (and why research on dialogue games is cool). DFKI Saarbrücken. March 7, 2023.
• Demistifying Neural Networks. Part of the Workshop on the Basics of Artificial Neural Networks / Deep Learning, organised by the SFB 1287 - Project B01. August 23, 2022.
• Desmistificando as Redes Neurais (Demistifying Neural Networks). Committee of Bioethics and Biolaw of the Brazilian Order of Attorneys. June 17, 2022.
• Incremental Processing in the Age of Non-Incremental Encoders. NLPhD Speaker Series at LST, University of Saarland. March 23, 2021.
• Relation Extraktion Software SotA. Research Seminar Semantic Technologies. June 21, 2019.

🙌 Engagement in CL/NLP community (and others)

• Service as reviewer (conferences): ARR (Jan 2022, Aug 2023, Oct 2023, Dez 2023), ACL 2023 (emergency), EMNLP (2023), EACL (2023), SDS (2023, 2024), SIGdial (2024), TeachingNLP (2024), CoNLL (2024).
• Outstanding reviewer awards: EACL 2023, ACL 2023.
• Service as reviewer (journals): Dialogue & Discourse, Linguamática.
• Service as secondary reviewer: COLING 2022.
• Co-chair of the Student Research Workshop at ACL 2022.
• Volunteer at EACL 2021. link
• Local organizer of SemDial 2021 (website and proceedings).
• Co-organiser of the YRRSDS Workshop 2024, co-located with SIGdial.
• Prof. Helena Caseli and I founded the group Brazilian Women in NLP in 2020. I collaborated in the organisation and board until 2023. I'm now a member.
• Jury member of the Youth Hacking 4 Freedom 2023.

📄 Thesis Co-Supervision and Review

• D. J. S. [M.Sc.] Generating Instruction Clarification Request in the CoDraw Dataset. (University of Potsdam, 2024)
• F. S. [M.Sc.] Evaluating the Incremental Performance of Pre-Trained Models for Reference Resolution. (University of Potsdam, 2024)
• P. K. [M.Sc.] Learning Adaptive Revision for Incremental Processing with a Two-Pass Model. (University of Potsdam, June, 2022)
• L. L. [M.Sc.] Towards a Corpus of Multimodal Joint Difference Detection Dialogues. (University of Potsdam, January, 2022)
• V. O. [M.Sc.] An Incremental Dialogue Model for the SMCalFlow Dataset. (University of Potsdam, November, 2021)
• E. L. [M.Sc.] Reinforcement Learning in Text-Based Games for NLP: Ablation Study and Analysis on a Game-Playing Agent. (University of Potsdam, March, 2021)
• H. G. [B.Sc.] Gaming the Ground: A Game-Based Approach to the Evaluation of Common Ground in Chat-Optimized Language Models. (University of Potsdam, 2024)
• O. L. [B.Sc.] Playing with Words: A Comparative Study of Human and Language Model Performance at clembench Games (Wordle and Picture Reference Game) (University of Potsdam, 2024)
• S. S.P. [B.Sc.] Human vs. LLM Performance at the Clembench Dialogue Games Taboo and Drawing Game: A Linguistic Analysis (University of Potsdam, 2024)
• M. L. [B.Sc.] Dialogue Games: Exploration and Navigation in a Simple Visual Environment. (University of Potsdam, December, 2020)
• R. Y. [Invididual research module] TBD.
• L. K. [Invididual research module] Learn and Evaluate Referential Contextual Embeddings. (University of Potsdam, 2023)
• J. L. [Invididual research module] Rewarding Actions of Reinforcement Learning agents on MapWorld. (University of Potsdam, 2022)
• P. K. [Invididual research module] Towards Incremental Transformers: An Empirical Analysis of Transformer Models for Incremental NLU. (University of Potsdam, 2021)
• L. S. [Invididual research module] Automated Concept Map Creation from Speech Transcripts with PropS. (University of Potsdam, 2021)