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{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{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{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",
}