The automatic creation of concept maps from documents written using morphologically rich languages
نویسندگان
چکیده
منابع مشابه
The automatic creation of concept maps from documents written using morphologically rich languages
A concept map is a graphical tool for representing knowledge. They have been used in many different areas, including education, knowledge management, business and intelligence. Manually constructing concept maps can be a complex task; the unskilled person may encounter difficulties in determining and positioning concepts relevant to the problem area. An application that recommends concept candi...
متن کاملAutomatic Error Analysis for Morphologically Rich Languages
This paper presents AMEANA, an opensource tool for error analysis for natural language processing tasks targeting morphologically rich languages. Unlike standard evaluation metrics such as BLEU or WER, AMEANA automatically provides a detailed error analysis that can help researchers and developers better understand the strengths and weaknesses of their systems. AMEANA is easily adaptable to any...
متن کاملSyntactic Parsing of Morphologically Rich Languages Using Deep Neural Networks
This paper presents parsing results for the constituency track of the SPMRL shared task. We use the recurrent neural network model of (Legrand and Collobert, 2015) which leverages a new RNN-based compositional sub-tree representation. Results are provided for different scenarios were models are trained on the full corpus or on a subset of 5k sentences, using either the gold or the predicted POS...
متن کاملStatistical Stemming of Morphologically Rich Languages
We analyze current machine translation into Russian, a morphologically rich language, and present a technique for unsupervised statistical stemming. An initial pass is based on intuitions, and uses a CUDA kernel. As a later pass, we run EM. Since our model is relatively simple, the EM probabilities factorize into components that can be solved independently. While our results were not exactly gr...
متن کاملProbabilistic modelling of morphologically rich languages
This thesis investigates how the sub-structure of words can be accounted for in probabilistic models of language. Such models play an important role in natural language processing tasks such as translation or speech recognition, but often rely on the simplistic assumption that words are opaque symbols. This assumption does not fit morphologically complex language well, where words can have rich...
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: 2012
ISSN: 0957-4174
DOI: 10.1016/j.eswa.2012.04.065