Topic-focus and salience

Hajičová, Eva; Sgall, Petr

doi:10.3115/1073012.1073048

Cited by 4 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The following rules determine which lexical items (CB or NB) belong to the Topic or to the Focus of the sentence (Hajičová et al, 1998;Hajičová and Sgall, 2001):…”

Section: Topic-focus Articulation (Tfa)mentioning

confidence: 99%

Data-driven approaches for information structure identification

Postolache

Kruijff-Korbayová

Kruijff

2005

Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing - HLT '05

View full text Add to dashboard Cite

This paper investigates automatic identification of Information Structure (IS) in texts. The experiments use the Prague Dependency Treebank which is annotated with IS following the Praguian approach of Topic Focus Articulation. We automatically detect t(opic) and f(ocus), using node attributes from the treebank as basic features and derived features inspired by the annotation guidelines. We present the performance of decision trees (C4.5), maximum entropy, and rule induction (RIPPER) classifiers on all tectogrammatical nodes. We compare the results against a baseline system that always assigns f(ocus) and against a rule-based system. The best system achieves an accuracy of 90.69%, which is a 44.73% improvement over the baseline (62.66%).

show abstract

“…The following rules determine which lexical items (CB or NB) belong to the Topic or to the Focus of the sentence (Hajičová et al, 1998;Hajičová and Sgall, 2001):…”

Section: Topic-focus Articulation (Tfa)mentioning

confidence: 99%

Data-driven approaches for information structure identification

Postolache

Kruijff-Korbayová

Kruijff

2005

Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing - HLT '05

View full text Add to dashboard Cite

show abstract

“…The following rules determine which lexical items (CB or NB) belong to the Topic or to the Focus (Hajičová et al, 1998;Hajičová and Sgall, 2001):…”

Section: Theorymentioning

confidence: 99%

Learning information structure in the Prague treebank

Postolache

2005

Proceedings of the ACL Student Research Workshop on - ACL '05

View full text Add to dashboard Cite

This paper investigates the automatic identification of aspects of Information Structure (IS) in texts. The experiments use the Prague Dependency Treebank which is annotated with IS following the Praguian approach of Topic Focus Articulation. We automatically detect t(opic) and f(ocus), using node attributes from the treebank as basic features and derived features inspired by the annotation guidelines. We show the performance of C4.5, Bagging, and Ripper classifiers on several classes of instances such as nouns and pronouns, only nouns, only pronouns. A baseline system assigning always f(ocus) has an F-score of 42.5%. Our best system obtains 82.04%.

show abstract

“…The development of salience reduction of the referents most frequently mentioned in ( 31) -( 34) is characterized in Tab. 1, a preliminary form of which was presented in Hajičová and Sgall (2001); it includes numbers of salience reduction degrees and of those rules from Section 3 that are the main sources of the degrees. Two further remarks may be added, concerning details of our analysis that have not been discussed above and may not be directly found in the previous publications we refer to: (a) a noun group consisting of a head with t or c and of one or more adjuncts with f constitutes a referring expression as a whole, in the prototypical case, and gets degree 0, if it occurs in F; this concerns e.g.…”

Section: 3mentioning

confidence: 99%

Dynamics in the Meaning of the Sentence and of Discourse

Sgall

2003

Meaning: The Dynamic Turn

View full text Add to dashboard Cite

From a linguistic viewpoint it may be stated that most different elements or parts of the system of language itself and of its use in communication are dynamic. The aim of the present contribution is (1) to discuss the impact of dynamics on the sentence structure, pointing out that, nevertheless, its core can be described as having a substantially simple structure, so that the relative easiness of the child's acquisition of language may be described as based on a pattern not far more complex than systems that are understood as innate on independent reasons, and (2) to illustrate how the dynamics of the discourse patterns can be seen as connected with a finite mechanism enabling the herarer to identify the coreferential antecedents.

show abstract

Topic-focus and salience

Cited by 4 publications

References 4 publications

Data-driven approaches for information structure identification

Data-driven approaches for information structure identification

Learning information structure in the Prague treebank

Dynamics in the Meaning of the Sentence and of Discourse

Contact Info

Product

Resources

About