Comprehension across Application Domains and Languages
نویسندگان
چکیده
This work demonstrates that our natural language understanding framework can be applied across application domains and languages with ease. Approaches towards language understanding generally involve much handcrafting, e.g. in writing grammars or annotating corpora, hence portability is a desirable trait in the development of language understanding systems. Our framework for natural language understanding couples semantic tagging with Belief Networks for communicative goal inference, and has delivered promising results in the ATIS (Air Travel Information Systems) domain. This work applies the approach to the stocks domain. Furthermore, the approach is extended to Chinese, to support a biliteral / trilingual (English with two Chinese dialects) spoken dialog system known as ISIS. We introduce the transformationbased parsing technique for language understanding, and found that it is effective in disambiguating among the various kinds of numeric expressions prevalent in the stocks domain, as well as infer possible semantic categories for out-of-vocabulary words. The nonterminal categories produced by parsing are fed to Belief Networks trained on English or Chinese queries for inferring the user’s communicative goal. Our experiments gave a goal identification performance of 94% and 93% for Chinese and English respectively.
منابع مشابه
Intervention Analysis in Teaching Reading Comprehension through Dynamic Assessment: Heron’s Perspective
Teachers’ verbal behavior is a key contributor to provision of appropriate indirect intervention in language learning contexts; however, it is surprising that professionals in ELT, to date, have not proposed a structured oral/verbal framework to deliver intervention and assistance in language learning contexts. To help redress this gap, Heron’s Six-Category Intervention Analysis was adapted to ...
متن کاملAn Investigation into the Effective Factors in Comprehending English Garden-Path Sentences by EFL Learners
The present study aimed at highlighting the possible effects of age, proficiency level, and the structural composition of Garden-Path (GP) sentences on EFL learners' comprehension. 80 Iranian EFL learners were recruited from the initial pool of 114 participants based on the results of an English proficiency test; 40 advanced, and 40 intermediate learners were selected. Moreover, two age...
متن کاملThe extended argument dependency model: a neurocognitive approach to sentence comprehension across languages.
Real-time language comprehension is a principal cognitive ability and thereby relates to central properties of the human cognitive architecture. Yet how do the presumably universal cognitive and neural substrates of language processing relate to the astounding diversity of human languages (over 5,000)? The authors present a neurocognitive model of online comprehension, the extended argument dep...
متن کاملSelecting the Best Fit Model in Cognitive Diagnostic Assessment: Differential Item Functioning Detection in the Reading Comprehension of the PhD Nationwide Admission Test
This study was an attemptto provide detailed information of the strengths and weaknesses of test takers‟ real ability through cognitive diagnostic assessment, and to detect differential item functioning in each test item. The rationale for using CDA was that it estimates an item‟s discrimination power, whereas clas- sical test theory or item response theory depicts between rather within item mu...
متن کامل