Assigning Grammatical Relations With A Back-Off Model
نویسنده
چکیده
This paper presents a corpus-based method to assign grammatical subject/object relations to ambiguous German constructs. It makes use of an unsupervised learning procedure to collect training and test data, and the back-off model to make assignment decisions.
منابع مشابه
Assigning Grammatical Relations with a Back-off Model
This paper presents a corpus-based method to assign grammatical subject/object relations to ambiguous German constructs. It makes use of an unsupervised learning procedure to collect training and test data, and the back-off model to make assignment decisions.
متن کاملSelective back-off smoothing for incorporating grammatical constraints into the n-gram language model
Spoken queries submitted to question answering systems usually consist of query contents (e.g. about newspaper articles) and frozen patterns (e.g. WH-words), which can be modeled with N-gram models and grammar-based models, respectively. We propose a method to integrate those different types of models into a single N-gram model. We represent the two types of language models in a single word net...
متن کاملA Computational Evaluation of Case-Assignment Algorithms
This project seeks to evaluate how successfully a new theory based on syntactic structure models the distribution of morphological case in Icelandic. This algorithm for case assignment will be tested against a traditional, grammatical-function-based theory on a large number of sentences from a corpus. Morphological case is a noun’s syntactic license to appear in its environment based on depende...
متن کاملInvestigating the relationship among complexity, range, and strength of grammatical knowledge of EFL students
Assessment of grammatical knowledge is a rather neglected area of research in the field with many open questions (Purpura, 2004). The present research incorporates recent proposals about the nature of grammatical development to create a framework consisting of dimensions of complexity, range and strength, and studies which dimension(s) can best predict the stat...
متن کاملSelective Back-off Smoothing for Inc Constraints into the N-gram
Spoken queries submitted to question answering systems usually consist of query contents (e.g. about newspaper articles) and frozen patterns (e.g. WH-words), which can be modeled with N-gram models and grammar-based models, respectively. We propose a method to integrate those different types of models into a single N-gram model. We represent the two types of language models in a single word net...
متن کامل