DramaCoref: A Hybrid Coreference Resolution System for German Theater Plays

In this paper, we describe a system for coreference resolution and emphasize the role of evaluation for its design. The goal of the system is to group referring expressions (identified beforehand in narrative texts) into sets of coreferring expressions that correspond to discourse entities. Several knowledge sources are distinguished, such as referential compatibility between a referring expression and a discourse entity, activation factors for discourse entities, size of working memory, or meta-rules for the creation of discourse entities. For each of them, the theoretical analysis of its relevance is compared to scores obtained through evaluation. After looping through all knowledge sources, an optimal behavior is chosen, then evaluated on test data. The paper also discusses evaluation measures as well as data annotation, and compares the present approach to others in the field.

Download Full-text

Toward Gender-Inclusive Coreference Resolution: An Analysis of Gender and Bias throughout the Machine Learning Lifecyle

Computational Linguistics ◽

10.1162/coli_a_00413 ◽

2021 ◽

pp. 1-47

Author(s):

Yang Trista Cao ◽

Hal Daumé

Keyword(s):

Machine Learning ◽

Quality Of Service ◽

English Text ◽

Coreference Resolution ◽

Resolution System ◽

Building Systems ◽

Systematic Biases ◽

Build Systems

Abstract Correctly resolving textual mentions of people fundamentally entails making inferences about those people. Such inferences raise the risk of systematic biases in coreference resolution systems, including biases that can harm binary and non-binary trans and cis stakeholders. To better understand such biases, we foreground nuanced conceptualizations of gender from sociology and sociolinguistics, and investigate where in the machine learning pipeline such biases can enter a coreference resolution system. We inspect many existing datasets for trans-exclusionary biases, and develop two new datasets for interrogating bias in both crowd annotations and in existing coreference resolution systems. Through these studies, conducted on English text, we confirm that without acknowledging and building systems that recognize the complexity of gender, we will build systems that fail for: quality of service, stereotyping, and over- or under-representation, especially for binary and non-binary trans users.

Download Full-text

Knowledge Derived From Wikipedia For Computing Semantic Relatedness

Journal of Artificial Intelligence Research ◽

10.1613/jair.2308 ◽

2007 ◽

Vol 30 ◽

pp. 181-212 ◽

Cited By ~ 91

Author(s):

S. P. Ponzetto ◽

M. Strube

Keyword(s):

Machine Learning ◽

Knowledge Base ◽

Search Engine ◽

Semantic Network ◽

Semantic Relatedness ◽

Coreference Resolution ◽

Valuable Resource ◽

Resolution System

Wikipedia provides a semantic network for computing semantic relatedness in a more structured fashion than a search engine and with more coverage than WordNet. We present experiments on using Wikipedia for computing semantic relatedness and compare it to WordNet on various benchmarking datasets. Existing relatedness measures perform better using Wikipedia than a baseline given by Google counts, and we show that Wikipedia outperforms WordNet on some datasets. We also address the question whether and how Wikipedia can be integrated into NLP applications as a knowledge base. Including Wikipedia improves the performance of a machine learning based coreference resolution system, indicating that it represents a valuable resource for NLP applications. Finally, we show that our method can be easily used for languages other than English by computing semantic relatedness for a German dataset.

Download Full-text

Multi-pass Sieve Coreference Resolution System for Polish

Lecture Notes in Computer Science - Language, Data, and Knowledge ◽

10.1007/978-3-319-59888-8_20 ◽

2017 ◽

pp. 222-236

Author(s):

Bartłomiej Nitoń ◽

Maciej Ogrodniczuk

Keyword(s):

Coreference Resolution ◽

Resolution System

Download Full-text

Disambiguation and Filtering Methods in Using Web Knowledge for Coreference Resolution

Cross-Disciplinary Advances in Applied Natural Language Processing ◽

10.4018/978-1-61350-447-5.ch013 ◽

2012 ◽

pp. 185-201 ◽

Cited By ~ 1

Author(s):

Olga Uryupina ◽

Massimo Poesio ◽

Claudio Giuliano ◽

Kateryna Tymoshenko

Keyword(s):

Semantic Information ◽

Knowledge Bases ◽

Coreference Resolution ◽

Number Of Solutions ◽

Web Resources ◽

Percentage Points ◽

Resolution System ◽

Semantic Compatibility ◽

Additional Constraints ◽

Web Knowledge

The authors investigate two publicly available Web knowledge bases, Wikipedia and Yago, in an attempt to leverage semantic information and increase the performance level of a state-of-the-art coreference resolution engine. They extract semantic compatibility and aliasing information from Wikipedia and Yago, and incorporate it into a coreference resolution system. The authors show that using such knowledge with no disambiguation and filtering does not bring any improvement over the baseline, mirroring the previous findings (Ponzetto & Poesio, 2009). They propose, therefore, a number of solutions to reduce the amount of noise coming from Web resources: using disambiguation tools for Wikipedia, pruning Yago to eliminate the most generic categories and imposing additional constraints on affected mentions. The evaluation experiments on the ACE-02 corpus show that the knowledge, extracted from Wikipedia and Yago, improves the system’s performance by 2-3 percentage points.

Download Full-text