Corpus ID: 16472801

Extending BART to Provide a Coreference Resolution System for German

@inproceedings{Broscheit2010ExtendingBT,
  title={Extending BART to Provide a Coreference Resolution System for German},
  author={Samuel Broscheit and Simone Paolo Ponzetto and Yannick Versley and Massimo Poesio},
  booktitle={LREC},
  year={2010}
}
We present a flexible toolkit-based approach to automatic coreference resolution on German text. We start with our previous work aimed at reimplementing the system from Soon et al. (2001) for English, and extend it to duplicate a version of the state-of-the-art proposal from Klenner and Ailloud (2009). Evaluation performed on a benchmarking dataset, namely the TueBa-D/Z corpus (Hinrichs et al., 2005b), shows that machine learning based coreference resolution can be robustly performed in a… Expand

Tables and Topics from this paper

Different German and English Coreference Resolution Models for Multi-domain Content Curation Scenarios
TLDR
Three implementations for performing coreference resolution: rule-based, statistical, and projection-based (from English to German) are described and an application of these systems on German and English texts from different scenarios in digital curation is concluded. Expand
Coreference Resolution for the Basque Language with BART
TLDR
This paper explains how the coreference resolution toolkit, BART, is extended in order to enable it to process Basque and discusses some key characteristics of Basque which make it particularly challenging for coreference and draws a road map for future work. Expand
Coreference Resolution for the Basque Language
TLDR
This paper explains how the coreference resolution toolkit, BART, is extended in order to enable it to process Basque and discusses some key characteristics of Basque which make it particularly challenging for coreference and draws a road map for future work. Expand
BART: A Multilingual Anaphora Resolution System
TLDR
BART is a highly modular toolkit for coreference resolution that supports state-of-the-art statistical approaches and enables efficient feature engineering and relies on a maximum entropy-based classifier for pairs of mentions. Expand
EUSKOR: End-to-end coreference resolution system for Basque
TLDR
The process of adapting the Stanford Coreference resolution module to the Basque language, taking into account the characteristics of the language, can benefit and facilitate other languages with similar characteristics in the implementation of their coreference resolution systems. Expand
Incremental Coreference Resolution for German
TLDR
A general model for coreference is introduced and its application to German is explored, finding that a combination of both compatibility models, coupled with the coreference model, provides a large potential for improving pronoun resolution performance. Expand
Off-the-Shelf Tools
TLDR
This chapter presents the properties that are most important for the integration of coreference systems into a larger context, and describes the BART system, the dCoref system that is part of Stanford’s CoreNLP suite, as well as IMSCoref and HOTCoref as examples of state-of-the-art systems that are purely based on machine learning. Expand
ParCor 1.0: A Parallel Pronoun-Coreference Corpus to Support Statistical MT
TLDR
The corpus is intended to be used both as a resource from which to learn systematic differences inpronoun use between languages and ultimately for developing and testing informed Statistical Machine Translation systems aimed at addressing the problem of pronoun coreference in translation. Expand
IMS HotCoref DE: A Data-driven Co-reference Resolver for German
TLDR
A data-driven co-reference resolution system for German that has been adapted from IMS HotCoref, a co- reference resolver for English is presented, showing that the resolver achieves state-of-the-art performance. Expand
Resolving Coreferent Bridging in German Newspaper Text
TLDR
The case of bridges from one noun phrase to another noun phrase that is not coreferent but related (“the engine”) is generally referred to as associative anaphora, and Asher and Lascarides (1998) propose that fulfilling the given-new contract also involves computing a discourse relation. Expand
...
1
2
...

References

SHOWING 1-10 OF 45 REFERENCES
BART: A Modular Toolkit for Coreference Resolution
TLDR
B BART is presented, a highly modular toolkit for developing coreference applications that was used to extend a reimplementation of the Soon et al. (2001) proposal with a variety of additional syntactic and knowledge-based features, and experiment with alternative resolution processes, preprocessing tools, and classifiers. Expand
Improving Machine Learning Approaches to Coreference Resolution
TLDR
A noun phrase coreference system that extends the work of Soon et al. (2001) and produces the best results to date on the M UC-6 and MUC-7 coreference resolution data sets --- F-measures of 70.4 and 63.4, respectively. Expand
A Constraint-based Approach to Noun Phrase Coreference Resolution in German Newspaper Text
In this paper, we investigate the usefulness of a wide range of features for their usefulness in the resolution of nominal coreference, both as hard constraints (i.e. completely removing elementsExpand
A Mention-Synchronous Coreference Resolution Algorithm Based On the Bell Tree
This paper proposes a new approach for coreference resolution which uses the Bell tree to represent the search space and casts the coreference resolution problem as finding the best path from theExpand
Machine Learning Approaches to Coreference Resolution
This paper introduces three machine learning approaches to noun phrase coreference resolution. The first of them gives a view of coreference resolution as a clustering task. The second one applies aExpand
Coreference resolution with syntactico-semantic rules and corpus statistics
TLDR
A new hybrid approach to the coreference resolution problem is presented, which combines syntactico-semantic rules with statistics derived from an annotated corpus and is evaluated against a baseline model. Expand
A model-theoretic coreference scoring scheme
This note describes a scoring scheme for the coreference task in MUC6. It improves on the original approach by: (1) grounding the scoring scheme in terms of a model; (2) producing more intuitiveExpand
A Machine Learning Approach to Coreference Resolution of Noun Phrases
TLDR
The learning approach to coreference resolution of noun phrases in unrestricted text is presented, indicating that on the general noun phrase coreference task, the learning approach holds promise and achieves accuracy comparable to that of nonlearning approaches. Expand
On Coreference Resolution Performance Metrics
TLDR
The paper proposes a Constrained Entity-Alignment F-Measure (CEAF) for evaluating coreference resolution and shows that the best alignment is a maximum bipartite matching problem which can be solved by the Kuhn-Munkres algorithm. Expand
What Treebanks Can Do For You : Rule-based and Machine-learning Approaches to Anaphora Resolution in German .
This paper compares two approaches to computational anaphora resolution for German: (i) an adaption of the rule-based RAP algorithm that was originally developed for English by Lappin and Leass, andExpand
...
1
2
3
4
5
...