Refine
Year of publication
Document Type
- Conference Proceeding (7)
- Report (4)
- Article (2)
- Diploma Thesis (1)
- Doctoral Thesis (1)
- Lecture (1)
- Review (1)
Has Fulltext
- yes (17)
Is part of the Bibliography
- no (17)
Keywords
Institute
- Informatik (14)
- Gesellschaftswissenschaften (2)
Coreference-Based Summarization and Question Answering: a Case for High Precision Anaphor Resolution
(2003)
Approaches to Text Summarization and Question Answering are known to benefit from the availability of coreference information. Based on an analysis of its contributions, a more detailed look at coreference processing for these applications will be proposed: it should be considered as a task of anaphor resolution rather than coreference resolution. It will be further argued that high precision approaches to anaphor resolution optimally match the specific requirements. Three such approaches will be described and empirically evaluated, and the implications for Text Summarization and Question Answering will be discussed.
In the last years, much effort went into the design of robust anaphor resolution algorithms. Many algorithms are based on antecedent filtering and preference strategies that are manually designed. Along a different line of research, corpus-based approaches have been investigated that employ machine-learning techniques for deriving strategies automatically. Since the knowledge-engineering effort for designing and optimizing the strategies is reduced, the latter approaches are considered particularly attractive. Since, however, the hand-coding of robust antecedent filtering strategies such as syntactic disjoint reference and agreement in person, number, and gender constitutes a once-for-all effort, the question arises whether at all they should be derived automatically. In this paper, it is investigated what might be gained by combining the best of two worlds: designing the universally valid antecedent filtering strategies manually, in a once-for-all fashion, and deriving the (potentially genre-specific) antecedent selection strategies automatically by applying machine-learning techniques. An anaphor resolution system ROSANA-ML, which follows this paradigm, is designed and implemented. Through a series of formal evaluations, it is shown that, while exhibiting additional advantages, ROSANAML reaches a performance level that compares with the performance of its manually designed ancestor ROSANA.
In the last decade, much effort went into the design of robust third-person pronominal anaphor resolution algorithms. Typical approaches are reported to achieve an accuracy of 60-85%. Recent research addresses the question of how to deal with the remaining difficult-toresolve anaphors. Lappin (2004) proposes a sequenced model of anaphor resolution according to which a cascade of processing modules employing knowledge and inferencing techniques of increasing complexity should be applied. The individual modules should only deal with and, hence, recognize the subset of anaphors for which they are competent. It will be shown that the problem of focusing on the competence cases is equivalent to the problem of giving precision precedence over recall. Three systems for high precision robust knowledge-poor anaphor resolution will be designed and compared: a ruleset-based approach, a salience threshold approach, and a machine-learning-based approach. According to corpus-based evaluation, there is no unique best approach. Which approach scores highest depends upon type of pronominal anaphor as well as upon text genre.
Algorithmic approaches to anaphor resolution are known to benefit substantially from syntactic disjoint reference filters. Typically, however, there is a considerable gap between the scope of the formal model of grammar employed for deriving referential evidence and its implementation. While accounting for many subtleties of language, such formal models at most partially address the algorithmic aspects of referential processing. This paper investigates the issue of implementing syntactic disjoint reference for robust anaphor resolution. An algorithmic account of binding condition verification will be developed that, on one hand, captures the theoretical subtleties, and, on the other hand, exhibits computational efficiency and fulfils the robustness requirements. Taking as input the potentially fragmentary parses of a robust state-of-the-art parser, the practical performance of this algorithm will be evaluated with respect to the task of anaphor resolution and shown to be nearly optimal.
Syntactic coindexing restrictions are by now known to be of central importance to practical anaphor resolution approaches. Since, in particular due to structural ambiguity, the assumption of the availability of a unique syntactic reading proves to be unrealistic, robust anaphor resolution relies on techniques to overcome this deficiency.
This paper describes the ROSANA approach, which generalizes the verification of coindexing restrictions in order to make it applicable to the deficient syntactic descriptions that are provided by a robust state-of-the-art parser. By a formal evaluation on two corpora that differ with respect to text genre and domain, it is shown that ROSANA achieves high-quality robust coreference resolution. Moreover, by an in-depth analysis, it is proven that the robust implementation of syntactic disjoint reference is nearly optimal. The study reveals that, compared with approaches that rely on shallow preprocessing, the largely nonheuristic disjoint reference algorithmization opens up the possibility/or a slight improvement. Furthermore, it is shown that more significant gains are to be expected elsewhere, particularly from a text-genre-specific choice of preference strategies.
The performance study of the ROSANA system crucially rests on an enhanced evaluation methodology for coreference resolution systems, the development of which constitutes the second major contribution o/the paper. As a supplement to the model-theoretic scoring scheme that was developed for the Message Understanding Conference (MUC) evaluations, additional evaluation measures are defined that, on one hand, support the developer of anaphor resolution systems, and, on the other hand, shed light on application aspects of pronoun interpretation.