BibTeX
@InProceedings{bjorkelund-etal:2014:spmrl-sancl,
author = {Bj{ö}rkelund, Anders and c {C}etino u {g}lu, {Ö}zlem and Fale{n}ska,
Agnieszka and Farkas, Rich{á}rd and Mueller, Thomas and Seeker,
Wolfgang and Sz{á}nt{ó}, Zsolt},
title = {{Introducing the IMS-Wroc{l}aw-Szeged-CIS entry at the SPMRL 2014
Shared Task: Reranking and Morpho-syntax meet Unlabeled Data}},
booktitle = {Proceedings of the First Joint Workshop on Statistical Parsing of
Morphologically Rich Languages and Syntactic Analysis of Non-Canonical
Languages},
year = {2014},
pages = {97-102},
address = {Dublin, Ireland},
month = {August},
publisher = {Dublin City University},
keywords = {gcl,sfb732-d8,sfb732-d2},
url = {https://www.aclweb.org/anthology/W14-6110}
}
@InProceedings{bjorkelund-EtAl:2016:P16-1,
author = {Bj{o}rkelund, Anders and Fale{n}ska, Agnieszka and Seeker, Wolfgang and Kuhn, Jonas},
title = {How to Train Dependency Parsers with Inexact Search for Joint Sentence Boundary Detection and Parsing of Entire Documents},
booktitle = {Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
month = {August},
year = 2016,
address = {Berlin, Germany},
publisher = {Association for Computational Linguistics},
pages = {1924-1934},
url = {https://www.aclweb.org/anthology/P16-1181}
}
@InProceedings{bjorkelund-EtAl:2017:K17-3,
author = {Bj{o}rkelund, Anders and Falenska, Agnieszka and Yu, Xiang and Kuhn, Jonas},
title = {IMS at the CoNLL 2017 UD Shared Task: CRFs and Perceptrons Meet Neural Networks},
booktitle = {Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies},
month = {August},
year = 2017,
address = {Vancouver, Canada},
publisher = {Association for Computational Linguistics},
pages = {40-51},
abstract = {This paper presents the IMS contribution to the CoNLL 2017 Shared Task. In the
preprocessing step we employed a CRF POS/morphological tagger and a neural
tagger predicting supertags. On some languages, we also applied word
segmentation with the CRF tagger and sentence segmentation with a
perceptron-based parser. For parsing we took an ensemble approach by blending
multiple instances of three parsers with very different architectures. Our
system achieved the third place overall and the second place for the surprise
languages.},
url = {https://www.aclweb.org/anthology/K17-3004}
}
@inproceedings{chen-etal-2024-go,
abstract = {Authorship Profiling (AP) aims to predict the demographic attributes (such as gender and age) of authors based on their writing styles. Ever-improving models mean that this task is gaining interest and application possibilities. However, with greater use also comes the risk that authors are misclassified more frequently, and it remains unclear to what extent the better models can capture the bias and who is affected by the models{'} mistakes. In this paper, we investigate three established datasets for AP as well as classical and neural classifiers for this task. Our analyses show that it is often possible to predict the demographic information of the authors based on textual features. However, some features learned by the models are specific to datasets. Moreover, models are prone to errors based on stereotypes associated with topical bias.},
address = {Bangkok, Thailand},
author = {Chen, Hongyu and Roth, Michael and Falenska, Agnieszka},
booktitle = {Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP)},
editor = {Fale{n}ska, Agnieszka and Basta, Christine and Costa juss{à}, Marta and Goldfarb-Tarrant, Seraphina and Nozza, Debora},
month = {08},
pages = {150-166},
publisher = {Association for Computational Linguistics},
title = {What Can Go Wrong in Authorship Profiling: Cross-Domain Analysis of Gender and Age Prediction},
url = {https://aclanthology.org/2024.gebnlp-1.9},
year = 2024
}
@inproceedings{costa-jussa-etal-2024-overview,
abstract = {We describe the details of the Shared Task of the 5th ACL Workshop on Gender Bias in Natural Language Processing (GeBNLP 2024). The task uses dataset to investigate the quality of Machine Translation systems on a particular case of gender robustness. We report baseline results as well as the results of the first participants. The shared task will be permanently available in the Dynabench platform.},
address = {Bangkok, Thailand},
author = {Costa juss{à}, Marta and Andrews, Pierre and Basta, Christine and Ciro, Juan and Falenska, Agnieszka and Goldfarb-Tarrant, Seraphina and Mosquera, Rafael and Nozza, Debora and S{á}nchez, Eduardo},
booktitle = {Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP)},
editor = {Fale{n}ska, Agnieszka and Basta, Christine and Costa juss{à}, Marta and Goldfarb-Tarrant, Seraphina and Nozza, Debora},
month = {08},
pages = {399-404},
publisher = {Association for Computational Linguistics},
title = {Overview of the Shared Task on Machine Translation Gender Bias Evaluation with Multilingual Holistic Bias},
url = {https://aclanthology.org/2024.gebnlp-1.26},
year = 2024
}
@inproceedings{donmez-etal-2024-please,
abstract = {Offensive speech is highly prevalent on online platforms. Being trained on online data, Large Language Models (LLMs) display undesirable behaviors, such as generating harmful text or failing to recognize it. Despite these shortcomings, the models are becoming a part of our everyday lives by being used as tools for information search, content creation, writing assistance, and many more. Furthermore, the research explores using LLMs in applications with immense social risk, such as late-life companions and online content moderators. Despite the potential harms from LLMs in such applications, whether LLMs can reliably identify offensive speech and how they behave when they fail are open questions. This work addresses these questions by probing sixteen widely used LLMs and showing that most fail to identify (non-)offensive online language. Our experiments reveal undesirable behavior patterns in the context of offensive speech detection, such as erroneous response generation, over-reliance on profanity, and failure to recognize stereotypes. Our work highlights the need for extensive documentation of model reliability, particularly in terms of the ability to detect offensive language.},
address = {Miami, Florida, USA},
author = {D{ö}nmez, Esra and Vu, Thang and Falenska, Agnieszka},
booktitle = {Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing},
editor = {Al-Onaizan, Yaser and Bansal, Mohit and Chen, Yun-Nung},
month = {11},
pages = {18340-18357},
publisher = {Association for Computational Linguistics},
title = {Please note that {I}{'}m just an {AI}: Analysis of Behavior Patterns of {LLM}s in (Non-)offensive Speech Identification},
url = {https://aclanthology.org/2024.emnlp-main.1019},
year = 2024
}
@article{erhard2024popbert,
abstract = {The rise of populism concerns many political scientists and practitioners, yet the detection of its underlying language remains fragmentary. This paper aims to provide a reliable, valid, and scalable approach to measure populist rhetoric. For that purpose, we created an annotated dataset based on parliamentary speeches of the German Bundestag (2013â2021). Following the ideational definition of populism, we label moralizing references to âthe virtuous peopleâ or âthe corrupt eliteâ as core dimensions of populist language. To identify, in addition, how the thin ideology of populism is âthickened,â we annotate how populist statements are attached to left-wing or right-wing host ideologies. We then train a transformer-based model (PopBERT) as a multilabel classifier to detect and quantify each dimension. A battery of validation checks reveals that the model has a strong predictive accuracy, provides high qualitative face validity, matches party rankings of expert surveys, and detects out-of-sample text snippets correctly. PopBERT enables dynamic analyses of how German-speaking politicians and parties use populist language as a strategic device. Furthermore, the annotator-level data may also be applied in cross-domain applications or to develop related classifiers.},
author = {Erhard, Lukas and Hanke, Sara and Remer, Uwe and Falenska, Agnieszka and Heiberger, Raphael Heiko},
booktitle = {Political Analysis},
doi = {DOI: 10.1017/pan.2024.12},
issn = {10471987},
pages = {1-17--},
publisher = {Cambridge University Press},
title = {PopBERT. Detecting Populism and Its Host Ideologies in the German Bundestag},
url = {https://www.cambridge.org/core/article/popbert-detecting-populism-and-its-host-ideologies-in-the-german-bundestag/06C14C50B50D5A7AB45C4A7C8A5AD945},
year = 2024
}
@proceedings{gebnlp-2024-gender,
address = {Bangkok, Thailand},
editor = {Fale{n}ska, Agnieszka and Basta, Christine and Costa juss{à}, Marta and Goldfarb-Tarrant, Seraphina and Nozza, Debora},
month = {08},
publisher = {Association for Computational Linguistics},
title = {Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP)},
url = {https://aclanthology.org/2024.gebnlp-1.0},
year = 2024
}
@InProceedings{falenska-EtAl:2015:IWPT,
author = {Fale{n}ska, Agnieszka and Bj{o}rkelund, Anders and c {C}etino u {g}lu, {O}zlem and Seeker, Wolfgang},
title = {Stacking or Supertagging for Dependency Parsing -- What's the Difference?},
booktitle = {Proceedings of the 14th International Conference on Parsing Technologies},
month = {July},
year = 2015,
address = {Bilbao, Spain},
publisher = {Association for Computational Linguistics},
pages = {118-129},
url = {https://www.aclweb.org/anthology/W15-2215}
}
@InProceedings{falenska-etal-2020-integrating,
title = "Integrating Graph-Based and Transition-Based Dependency Parsers in the Deep Contextualized Era",
author = {Falenska, Agnieszka and
Bj{ö}rkelund, Anders and
Kuhn, Jonas},
booktitle = "Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/2020.iwpt-1.4",
doi = "10.18653/v1/2020.iwpt-1.4",
pages = "25-39",
abstract = "Graph-based and transition-based dependency parsers used to have different strengths and weaknesses. Therefore, combining the outputs of parsers from both paradigms used to be the standard approach to improve or analyze their performance. However, with the recent adoption of deep contextualized word representations, the chief weakness of graph-based models, i.e., their limited scope of features, has been mitigated. Through two popular combination techniques {--} blending and stacking {--} we demonstrate that the remaining diversity in the parsing models is reduced below the level of models trained with different random seeds. Thus, an integration no longer leads to increased accuracy. When both parsers depend on BiLSTMs, the graph-based architecture has a consistent advantage. This advantage stems from globally-trained BiLSTM representations, which capture more distant look-ahead syntactic relations. Such representations can be exploited through multi-task learning, which improves the transition-based parser, especially on treebanks with a high ratio of right-headed dependencies.",
}
@InProceedings{falenska-ccetinouglu:2017:IWPT,
author = {Falenska, Agnieszka and c {C}etino u {g}lu, {O}zlem},
title = {Lexicalized vs. Delexicalized Parsing in Low-Resource Scenarios},
booktitle = {Proceedings of the 15th International Conference on Parsing Technologies},
month = {September},
year = {2017},
address = {Pisa, Italy},
publisher = {Association for Computational Linguistics},
pages = {18-24},
abstract = {We present a systematic analysis of lexicalized vs. delexicalized parsing in
low-resource scenarios, and propose a methodology to choose one method over
another under certain conditions. We create a set of simulation experiments on
41 languages and apply our findings to 9 low-resource languages. Experimental
results show that our methodology chooses the best approach in 8 out of 9
cases.},
url = {https://www.aclweb.org/anthology/W17-6303}
}
@InProceedings{falenska-EtAl:2020:LREC,
author = {Falenska, Agnieszka and Czesznak, Zolt{á}n and Jung, Kerstin and V{ö}lkel, Moritz and Seeker, Wolfgang and Kuhn, Jonas},
title = {GRAIN-S: Manually Annotated Syntax for German Interviews},
booktitle = {Proceedings of The 12th Language Resources and Evaluation Conference},
month = {May},
year = {2020},
address = {Marseille, France},
publisher = {European Language Resources Association},
pages = {5169-5177},
abstract = {We present GRAIN-S, a set of manually created syntactic annotations for radio interviews in German. The dataset extends an existing corpus GRAIN and comes with constituency and dependency trees for six interviews. The rare combination of gold- and silver-standard annotation layers coming from GRAIN with high-quality syntax trees can serve as a useful resource for speech- and text-based research. Moreover, since interviews can be put between carefully prepared speech and spontaneous conversational speech, they cover phenomena not seen in traditional newspaper-based treebanks. Therefore, GRAIN-S can contribute to research into techniques for model adaptation and for building more corpus-independent tools. GRAIN-S follows TIGER, one of the established syntactic treebanks of German. We describe the annotation process and discuss decisions necessary to adapt the original TIGER guidelines to the interviews domain. Next, we give details on the conversion from TIGER-style trees to dependency trees. We provide data statistics and demonstrate differences between the new dataset and existing out-of-domain test sets annotated with TIGER syntactic structures. Finally, we provide baseline parsing results for further comparison.},
url = {https://www.aclweb.org/anthology/2020.lrec-1.636}
}
@InProceedings{falenska-kuhn-2019-non,
title = "The (Non-)Utility of Structural Features in {B}i{LSTM}-based Dependency Parsers",
author = "Falenska, Agnieszka and
Kuhn, Jonas",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/P19-1012",
doi = "10.18653/v1/P19-1012",
pages = "117-128",
abstract = "Classical non-neural dependency parsers put considerable effort on the design of feature functions. Especially, they benefit from information coming from structural features, such as features drawn from neighboring tokens in the dependency tree. In contrast, their BiLSTM-based successors achieve state-of-the-art performance without explicit information about the structural context. In this paper we aim to answer the question: How much structural context are the BiLSTM representations able to capture implicitly? We show that features drawn from partial subtrees become redundant when the BiLSTMs are used. We provide a deep insight into information flow in transition- and graph-based neural architectures to demonstrate where the implicit information comes from when the parsers make their decisions. Finally, with model ablations we demonstrate that the structural context is not only present in the models, but it significantly influences their performance.",
}
@inproceedings{falenska-etal-2024-self-reported,
abstract = {Research on language as interactive discourse underscores the deliberate use of demographic parameters such as gender, ethnicity, and class to shape social identities. For example, by explicitly disclosing one{'}s information and enforcing one{'}s social identity to an online community, the reception by and interaction with the said community is impacted, e.g., strengthening one{'}s opinions by depicting the speaker as credible through their experience in the subject. Here, we present a first thorough study of the role and effects of self-disclosures on online discourse dynamics, focusing on a pervasive type of self-disclosure: author gender. Concretely, we investigate the contexts and properties of gender self-disclosures and their impact on interaction dynamics in an online persuasive forum, ChangeMyView. Our contribution is twofold. At the level of the target phenomenon, we fill a research gap in the understanding of the impact of these self-disclosures on the discourse by bringing together features related to forum activity (votes, number of comments), linguistic/stylistic features from the literature, and discourse topics. At the level of the contributed resource, we enrich and release a comprehensive dataset that will provide a further impulse for research on the interplay between gender disclosures, community interaction, and persuasion in online discourse.},
address = {Torino, Italia},
author = {Falenska, Agnieszka and Vecchi, Eva Maria and Lapesa, Gabriella},
booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen},
month = {05},
pages = {14606-14621},
publisher = {ELRA and ICCL},
title = {Self-reported Demographics and Discourse Dynamics in a Persuasive Online Forum},
url = {https://aclanthology.org/2024.lrec-main.1272},
year = 2024
}
@inproceedings{fanton-etal-2023-guides,
title = "How-to Guides for Specific Audiences: A Corpus and Initial Findings",
author = "Fanton, Nicola and
Falenska, Agnieszka and
Roth, Michael",
editor = "Padmakumar, Vishakh and
Vallejo, Gisela and
Fu, Yao",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-srw.46",
doi = "10.18653/v1/2023.acl-srw.46",
pages = "321-333",
abstract = "Instructional texts for specific target groups should ideally take into account the prior knowledge and needs of the readers in order to guide them efficiently to their desired goals. However, targeting specific groups also carries the risk of reflecting disparate social norms and subtle stereotypes. In this paper, we investigate the extent to which how-to guides from one particular platform, wikiHow, differ in practice depending on the intended audience. We conduct two case studies in which we examine qualitative features of texts written for specific audiences. In a generalization study, we investigate which differences can also be systematically demonstrated using computational methods. The results of our studies show that guides from wikiHow, like other text genres, are subject to subtle biases. We aim to raise awareness of these inequalities as a first step to addressing them in future work.",
}
@inproceedings{go-falenska-2024-gender,
abstract = {In this paper, we revisit the seminal work of Garimella et al. 2019, who reported that dependency parsers learn demographically-related signals from their training data and perform differently on sentences authored by people of different genders. We re-run all the parsing experiments from Garimella et al. 2019 and find that their results are not reproducible. Additionally, the original patterns suggesting the presence of gender biases fail to generalize to other treebank and parsing architecture. Instead, our data analysis uncovers methodological shortcomings in the initial study that artificially introduced differences into female and male datasets during preprocessing. These disparities potentially compromised the validity of the original conclusions.},
address = {Bangkok, Thailand},
author = {Go, Paul and Falenska, Agnieszka},
booktitle = {Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP)},
editor = {Fale{n}ska, Agnieszka and Basta, Christine and Costa juss{à}, Marta and Goldfarb-Tarrant, Seraphina and Nozza, Debora},
month = {08},
pages = {269-279},
publisher = {Association for Computational Linguistics},
title = {Is there Gender Bias in Dependency Parsing? Revisiting {``}Women{'}s Syntactic Resilience{''}},
url = {https://aclanthology.org/2024.gebnlp-1.17},
year = 2024
}
@inproceedings{kaiser-falenska-2024-translate,
address = {Vienna, Austria},
author = {Kaiser, Jens and Falenska, Agnieszka},
booktitle = {Proceedings of the 20th Conference on Natural Language Processing (KONVENS 2024)},
editor = {Luz de Araujo, Pedro Henrique and Baumann, Andreas and Gromann, Dagmar and Krenn, Brigitte and Roth, Benjamin and Wiegand, Michael},
month = {09},
pages = {134-140},
publisher = {Association for Computational Linguistics},
title = {How to Translate {SQ}u{AD} to {G}erman? A Comparative Study of Answer Span Retrieval Methods for Question Answering Dataset Creation},
url = {https://aclanthology.org/2024.konvens-main.15},
year = 2024
}
@InProceedings{knuples2024gender,
author = {Knuple{ v {s}}, Urban and Falenska, Agnieszka and Mileti{c}, Filip},
title = {{Gender Identity in Pretrained Language Models: An Inclusive Approach to Data Creation and Probing}},
booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2024},
year = {2024},
address = {Miami, Florida, USA},
pages = {11612-11631},
}
@InProceedings{KSchweitzer/etal:2018,
title = {{German Radio Interviews: The GRAIN Release of the SFB732 Silver Standard Collection}},
author = {Katrin Schweitzer and Kerstin Eckart and Markus G{a}rtner and
Agnieszka Falenska and Arndt Riester and Ina R{o}siger and Antje Schweitzer and Sabrina Stehwien and
Jonas Kuhn},
booktitle = {Proceedings of LREC-2018, Linguistic Resources and Evaluation Conference},
address = {Miyazaki, JP},
year = {2018},
pages = {2887-2895},
url = {http://www.lrec-conf.org/proceedings/lrec2018/summaries/320.html}
}
@InProceedings{yu-etal-2019-imsurreal,
title = {{{IMS}ur{R}eal: {IMS} at the Surface Realization Shared Task 2019}},
author = "Yu, Xiang and
Falenska, Agnieszka and
Haid, Marina and
Vu, Ngoc Thang and
Kuhn, Jonas",
booktitle = "Proceedings of the 2nd Workshop on Multilingual Surface Realisation (MSR 2019)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/D19-6306",
doi = "10.18653/v1/D19-6306",
pages = "50-58",
}
@InProceedings{yu-etal-2019-dependency,
title = "Dependency Length Minimization vs. Word Order Constraints: An Empirical Study On 55 Treebanks",
author = "Yu, Xiang and
Falenska, Agnieszka and
Kuhn, Jonas",
booktitle = "Proceedings of the First Workshop on Quantitative Syntax (Quasy, SyntaxFest 2019)",
month = "26 " # aug,
year = "2019",
address = "Paris, France",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/W19-7911",
pages = "89-97",
}
@InProceedings{yu-falenska-vu:2017:SCLeM,
author = {Yu, Xiang and Falenska, Agnieszka and Vu, Ngoc Thang},
title = {A General-Purpose Tagger with Convolutional Neural Networks},
booktitle = {Proceedings of the First Workshop on Subword and Character Level Models in NLP},
month = {September},
year = 2017,
address = {Copenhagen, Denmark},
publisher = {Association for Computational Linguistics},
pages = {124-129},
abstract = {We present a general-purpose tagger based on convolutional neural networks
(CNN), used for both composing word vectors and encoding context information.
The CNN tagger is robust across different tagging tasks: without task-specific
tuning of hyper-parameters, it achieves state-of-the-art results in
part-of-speech tagging, morphological tagging and supertagging. The CNN tagger
is also robust against the out-of-vocabulary problem; it performs well on
artificially unnormalized texts.},
url = {https://www.aclweb.org/anthology/W17-4118}
}
@InProceedings{yu-etal-2019-head,
title = {{Head-First Linearization with Tree-Structured Representation}},
author = "Yu, Xiang and
Falenska, Agnieszka and
Vu, Ngoc Thang and
Kuhn, Jonas",
booktitle = "Proceedings of the 12th International Conference on Natural Language Generation",
month = oct # " - " # nov,
year = "2019",
address = "Tokyo, Japan",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/W19-8636",
pages = "279-289",
}