A customised grammar framework for query classification
نویسندگان
چکیده
منابع مشابه
Implementing a customised meta-search interface for user query personalisation
Nowadays it is commonly accepted that the web is structured in a chaotic way. Due to the fact that it grows exponentially, it is a difficult task to efficiently locate specific information. This paper presents a User-defined Meta-Search Engine (UMSE), adaptable to user preferences. UMSE utilises up to 9 known search engines according to a user-defined ranking, submits its queries in parallel an...
متن کاملA Framework For Grammar Acquisition
Robust grammars yielding a deep syntactic analysis for unrestricted text remain yet to be developed. The approach of manual grammar-coding usually leads to the problems of undergeneration and lack of robustness. Furthermore the complexity of manually coded rule-systems often reaches a level hard to maintain or expand as its coverage of realistic data is increased. On the other hand, purely stat...
متن کاملa framework for identifying and prioritizing factors affecting customers’ online shopping behavior in iran
the purpose of this study is identifying effective factors which make customers shop online in iran and investigating the importance of discovered factors in online customers’ decision. in the identifying phase, to discover the factors affecting online shopping behavior of customers in iran, the derived reference model summarizing antecedents of online shopping proposed by change et al. was us...
15 صفحه اولA Unified Framework for Grammar Error Correction
In this paper we describe the PKU system for the CoNLL-2014 grammar error correction shared task. We propose a unified framework for correcting all types of errors. We use unlabeled news texts instead of large amount of human annotated texts as training data. Based on these data, a tri-gram language model is used to correct the replacement errors while two extra classification models are traine...
متن کاملA Generation Framework for Grammar Development
We developed a general framework for the development of a symbolic (hand-written) feature-based lexicalised tree-adjoining grammar (FB-LTAG). We choose natural language generation, surface realisation in particular, to question the capabilities of the grammar in terms of both accuracy and robustness. Our framework combines an optimised surface realiser with efficient error mining techniques. Wh...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Expert Systems with Applications
سال: 2019
ISSN: 0957-4174
DOI: 10.1016/j.eswa.2019.06.010