Open AccessProceedings Article
A probabilistic genre-independent model of pronominalization
Michael Strube,Maria Wolters +1 more
- pp 18-25
Reads0
Chats0
TLDR
Results based on the annotation of twelve texts from four genres show that only a few factors have a strong influence on pronominalization across genres, i.e. distance from last mention, agreement, and form of the antecedent.Abstract:
Our aim in this paper is to identify genreindependent factors that influence the decision to pronominalize. Results based on the annotation of twelve texts from four genres show that only a few factors have a strong influence on pronominalization across genres, i.e. distance from last mention, agreement, and form of the antecedent. Finally, we describe a probabilistic model of pronominalization derived from our data.read more
Citations
More filters
Proceedings Article
Statistical generation: three methods compared and evaluated
TL;DR: Treebank-training of generators, an alternative method for building statistical models for NL G from raw corpora, and two different ways of using treebank-trained models during generation are looked at.
Referential choices in language production: The role of accessibility
TL;DR: Vogels et al. as discussed by the authors investigated the effect of visual saliency (foregrounding) in interaction with linguistic salience (subjecthood) of two story characters both on the choice of referent and on the choosing of referring expression.
Proceedings ArticleDOI
Learning attribute selections for non-pronominal expressions
TL;DR: This paper reports results from using machine learning to train and test a nominal-expression generator on a set of 393 nominal descriptions from the COCONUT corpus of task-oriented design dialogues.
Book Chapter
Modeling Referential Choice in Discourse: A Cognitive Calculative Approach and a Neural Network Approach
André Grüning,Andrej A. Kibrik +1 more
TL;DR: A mathematically more sophisticated neural network approach to the same set of data was developed and revealed that out of ten input factors five were sufficient to predict the data almost correctly, and that the logical structure of the remaining factors can be simplified.
Journal ArticleDOI
Referential Choice: Predictability and Its Limits.
Andrej A. Kibrik,Andrej A. Kibrik,Mariya V. Khudyakova,Grigory B. Dobrov,Anastasia Linnik,Dmitrij A. Zalmanov +5 more
TL;DR: A study of referential choice in discourse production, understood as the choice between various types of refereNTial devices, such as pronouns and full noun phrases, to predict referentials choice, and to explore to what extent such prediction is possible.
References
More filters
Journal ArticleDOI
A new look at the statistical model identification
TL;DR: In this article, a new estimate minimum information theoretical criterion estimate (MAICE) is introduced for the purpose of statistical identification, which is free from the ambiguities inherent in the application of conventional hypothesis testing procedure.
Journal ArticleDOI
A Coefficient of agreement for nominal Scales
TL;DR: In this article, the authors present a procedure for having two or more judges independently categorize a sample of units and determine the degree, significance, and significance of the units. But they do not discuss the extent to which these judgments are reproducible, i.e., reliable.
Journal ArticleDOI
Classification and Regression Trees.
Book
Classification and regression trees
TL;DR: The methodology used to construct tree structured rules is the focus of a monograph as mentioned in this paper, covering the use of trees as a data analysis method, and in a more mathematical framework, proving some of their fundamental properties.
Journal ArticleDOI
WordNet : an electronic lexical database
TL;DR: The lexical database: nouns in WordNet, Katherine J. Miller a semantic network of English verbs, and applications of WordNet: building semantic concordances are presented.