Using the web in machine learning for other-anaphora resolution

Modjeska, Natalia N.; Markert, Katja; Nissim, Malvina

doi:10.3115/1119355.1119378

Cited by 31 publications

(20 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Volk (2001) proposed a method for resolving PP attachment ambiguities based upon Web data. Modjeska et al (2003) used the Web for resolving nominal anaphora. Lapata and Keller (2005) investigated the performance of web-based models for a wide range of NLP tasks, such as MT candidate selection, article generation, and countability detection.…”

Section: Related Workmentioning

confidence: 99%

“…Very large corpora obtained from the Web have been successfully utilized for many natural language processing (NLP) applications, such as prepositional phrase (PP) attachment, other-anaphora resolution, spelling correction, confusable word set disambiguation and machine translation (Volk, 2001;Modjeska et al, 2003;Lapata and Keller, 2005;Atterer and Schütze, 2006;Brants et al, 2007).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The effect of corpus size on case frame acquisition for discourse analysis

Sasano

Kawahara

Kurohashi

2009

Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Com

View full text Add to dashboard Cite

This paper reports the effect of corpus size on case frame acquisition for discourse analysis in Japanese. For this study, we collected a Japanese corpus consisting of up to 100 billion words, and constructed case frames from corpora of six different sizes. Then, we applied these case frames to syntactic and case structure analysis, and zero anaphora resolution. We obtained better results by using case frames constructed from larger corpora; the performance was not saturated even with a corpus size of 100 billion words.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

The effect of corpus size on case frame acquisition for discourse analysis

Sasano

Kawahara

Kurohashi

2009

Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Com

View full text Add to dashboard Cite

show abstract

“…Now-a-days, many web corpora are present and researchers successfully utilize web data including machine translation [9], prepositional phrase attachment [10] and other anaphora resolution [11] to evaluate NLP systems. One problem in evaluating domain-specific NLP systems with a web corpus is the discrepancy between the domain of the corpus and the domain of the system [14].…”

Section: Related Workmentioning

confidence: 99%

A Corpus-based evaluation of lexical components of a domain-specific text to Knowledge Mapping prototype

Shams

Elsayed

2008

2008 11th International Conference on Computer and Information Technology

View full text Add to dashboard Cite

The aim of this paper is to evaluate the lexical components of a Text to Knowledge Mapping (TKM) prototype. The prototype is domain-specific, the purpose of which is to map instructional text onto a knowledge domain. The context of the knowledge domain of the prototype is physics, specifically DC electrical circuits. During development, the prototype has been tested with a limited data set from the domain. The prototype now reached a stage where it needs to be evaluated with a representative linguistic data set called corpus. A corpus is a collection of text drawn from typical sources which can be used as a test data set to evaluate NLP systems. As there is no available corpus for the domain, we developed a representative corpus and annotated it with linguistic information. The evaluation of the prototype considers one of its two main components-lexical knowledge base. With the corpus, the evaluation enriches the lexical knowledge resources like vocabulary and grammar structure. This leads the prototype to parse a reasonable amount of sentences in the corpus.

show abstract

“…We follow our previous work (Hou et al, 2013b) and restrict bridging to non-coreferential cases. We also exclude comparative anaphora (Modjeska et al, 2003).…”

Section: Introductionmentioning

confidence: 99%

A Rule-Based System for Unrestricted Bridging Resolution: Recognizing Bridging Anaphora and Finding Links to Antecedents

Hou

Markert

Strube

2014

Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Self Cite

View full text Add to dashboard Cite

Bridging resolution plays an important role in establishing (local) entity coherence. This paper proposes a rule-based approach for the challenging task of unrestricted bridging resolution, where bridging anaphors are not limited to definite NPs and semantic relations between anaphors and their antecedents are not restricted to meronymic relations. The system consists of eight rules which target different relations based on linguistic insights. Our rule-based system significantly outperforms a reimplementation of a previous rule-based system (Vieira and Poesio, 2000). Furthermore, it performs better than a learning-based approach which has access to the same knowledge resources as the rule-based system. Additionally, incorporating the rules and more features into the learning-based system yields a minor improvement over the rule-based system.

show abstract

Using the web in machine learning for other-anaphora resolution

Cited by 31 publications

References 10 publications

The effect of corpus size on case frame acquisition for discourse analysis

The effect of corpus size on case frame acquisition for discourse analysis

A Corpus-based evaluation of lexical components of a domain-specific text to Knowledge Mapping prototype

A Rule-Based System for Unrestricted Bridging Resolution: Recognizing Bridging Anaphora and Finding Links to Antecedents

Contact Info

Product

Resources

About