Anders Björkelund


2020

pdf bib
Integrating Graph-Based and Transition-Based Dependency Parsers in the Deep Contextualized Era
Agnieszka Falenska | Anders Björkelund | Jonas Kuhn
Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies

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.

2017

pdf bib
IMS at the CoNLL 2017 UD Shared Task: CRFs and Perceptrons Meet Neural Networks
Anders Björkelund | Agnieszka Falenska | Xiang Yu | Jonas Kuhn
Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies

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.

2016

pdf bib
How to Train Dependency Parsers with Inexact Search for Joint Sentence Boundary Detection and Parsing of Entire Documents
Anders Björkelund | Agnieszka Faleńska | Wolfgang Seeker | Jonas Kuhn
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

2015

pdf bib
Non-Deterministic Oracles for Unrestricted Non-Projective Transition-Based Dependency Parsing
Anders Björkelund | Joakim Nivre
Proceedings of the 14th International Conference on Parsing Technologies

pdf bib
Stacking or Supertagging for Dependency Parsing – What’s the Difference?
Agnieszka Faleńska | Anders Björkelund | Özlem Çetinoğlu | Wolfgang Seeker
Proceedings of the 14th International Conference on Parsing Technologies

2014

pdf bib
A Graphical Interface for Automatic Error Mining in Corpora
Gregor Thiele | Wolfgang Seeker | Markus Gärtner | Anders Björkelund | Jonas Kuhn
Proceedings of the Demonstrations at the 14th Conference of the European Chapter of the Association for Computational Linguistics

pdf bib
The Extended DIRNDL Corpus as a Resource for Coreference and Bridging Resolution
Anders Björkelund | Kerstin Eckart | Arndt Riester | Nadja Schauffler | Katrin Schweitzer
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)

DIRNDL is a spoken and written corpus based on German radio news, which features coreference and information-status annotation (including bridging anaphora and their antecedents), as well as prosodic information. We have recently extended DIRNDL with a fine-grained two-dimensional information status labeling scheme. We have also applied a state-of-the-art part-of-speech and morphology tagger to the corpus, as well as highly accurate constituency and dependency parsers. In the light of this development we believe that DIRNDL is an interesting resource for NLP researchers working on automatic coreference and bridging resolution. In order to enable and promote usage of the data, we make it available for download in an accessible tabular format, compatible with the formats used in the CoNLL and SemEval shared tasks on automatic coreference resolution.

pdf bib
Introducing the IMS-Wrocław-Szeged-CIS entry at the SPMRL 2014 Shared Task: Reranking and Morpho-syntax meet Unlabeled Data
Anders Björkelund | Özlem Çetinoğlu | Agnieszka Faleńska | Richárd Farkas | Thomas Mueller | Wolfgang Seeker | Zsolt Szántó
Proceedings of the First Joint Workshop on Statistical Parsing of Morphologically Rich Languages and Syntactic Analysis of Non-Canonical Languages

pdf bib
Learning Structured Perceptrons for Coreference Resolution with Latent Antecedents and Non-local Features
Anders Björkelund | Jonas Kuhn
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf bib
Visualization, Search, and Error Analysis for Coreference Annotations
Markus Gärtner | Anders Björkelund | Gregor Thiele | Wolfgang Seeker | Jonas Kuhn
Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations

2013

pdf bib
Towards Robust Linguistic Analysis using OntoNotes
Sameer Pradhan | Alessandro Moschitti | Nianwen Xue | Hwee Tou Ng | Anders Björkelund | Olga Uryupina | Yuchen Zhang | Zhi Zhong
Proceedings of the Seventeenth Conference on Computational Natural Language Learning

pdf bib
(Re)ranking Meets Morphosyntax: State-of-the-art Results from the SPMRL 2013 Shared Task
Anders Björkelund | Özlem Çetinoğlu | Richárd Farkas | Thomas Mueller | Wolfgang Seeker
Proceedings of the Fourth Workshop on Statistical Parsing of Morphologically-Rich Languages

pdf bib
ICARUS – An Extensible Graphical Search Tool for Dependency Treebanks
Markus Gärtner | Gregor Thiele | Wolfgang Seeker | Anders Björkelund | Jonas Kuhn
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics: System Demonstrations

2012

pdf bib
Comparing Non-projective Strategies for Labeled Graph-Based Dependency Parsing
Anders Björkelund | Jonas Kuhn
Proceedings of COLING 2012: Posters

pdf bib
Phrase Structures and Dependencies for End-to-End Coreference Resolution
Anders Björkelund | Jonas Kuhn
Proceedings of COLING 2012: Posters

pdf bib
Data-driven Multilingual Coreference Resolution using Resolver Stacking
Anders Björkelund | Richárd Farkas
Joint Conference on EMNLP and CoNLL - Shared Task

pdf bib
Generating Non-Projective Word Order in Statistical Linearization
Bernd Bohnet | Anders Björkelund | Jonas Kuhn | Wolfgang Seeker | Sina Zarriess
Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning

2011

pdf bib
Exploring Lexicalized Features for Coreference Resolution
Anders Björkelund | Pierre Nugues
Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task

2010

pdf bib
A High-Performance Syntactic and Semantic Dependency Parser
Anders Björkelund | Bernd Bohnet | Love Hafdell | Pierre Nugues
Coling 2010: Demonstrations

2009

pdf bib
Multilingual Semantic Role Labeling
Anders Björkelund | Love Hafdell | Pierre Nugues
Proceedings of the Thirteenth Conference on Computational Natural Language Learning (CoNLL 2009): Shared Task