This paper develops a new statistical method of building language models (LMs) of Japanese dialects for automatic speech recognition (ASR). One possible application is to recognize a variety of utterances in our daily lives. The most crucial problem in training language models for dialects is the shortage of linguistic corpora in dialects. Our solution is to transform linguistic corpora into di...

AutoCor is a method for the automatic acquisition and classification of corpora of documents in closely-related languages. It is an extension and enhancement of CorpusBuilder, a system that automatically builds specific minority language corpora from a closed corpus, since some Tagalog documents retrieved by CorpusBuilder are actually documents in other closely-related Philippine languages. Aut...

Recent works in Natural Language Processing (NLP) using neural networks have focused on learning dense word representations to perform classification tasks. When dealing with phrase prediction problems, is is common practice to use special tagging schemes to identify segments boundaries. This allows these tasks to be expressed as common word tagging problems. In this paper, we propose to learn ...

abstract the word science has gone through semantic change in different historical periods and in relation to the cultural and social circumstances of the time and thus has been used in various senses. a semantic study of word in the pre- and post-islamic eras will reveal that the word has been used in different and even opposite senses. this means that, in the age of ignorance (pre-islamic era...

Contrasting predictions were made to differentiate a one-stage from a two-stage model of word-association performance in schizophrenia. Schizophrenics and normals (N = 24 each) provided word associations in response to (a) "free" versus "idiosyncratic" instructions and (5) stimulus words that typically elicit either a strong dominant association or several weak associations. Results confirmed t...

We present a machine learning approach for classifying sentences as one-liner jokes or normal sentences. We use no deep analysis of the meaning to try to see if it is humorous, instead we rely on a combination of simple features to see if these are enough to detect humor. Features such as word overlap with other jokes, presence of words common in jokes, ambiguity and word overlap with common id...

To make an interactive guidance mechanism for document retrieval systems, we developed a user-interface which presents users the visualized map of topics at each stage of retrieval process. Topic words are automatically extracted by frequency analysis and the strength of the relationships between topic words is measured by their co-occurrence. A major factor affecting a user’s impression of a g...

The purpose of this study is to examine the vocabulary included in listening texts textbooks used teaching Turkish foreigners according their types. was limited New Istanbul For International Students Course Book—A1 level. Accordingly, a total eighteen six units were analyzed. document analysis method study. purpose, words analyzed as nouns, verbs, and phrases distinction word list so...

this study strives to investigate the importance of ‘education’ and ‘gender’, as two major sociolinguistic variables, in accepting or rejecting the words coined by the iranian academy of persian language and literature (apll). a total of 500 students from state universities in tehran were chosen as subjects and provided with a questionnaire consisting of 50 apll equivalents. the respondents’ ac...

Sememes are minimum semantic units of word meanings, and the meaning of each word sense is typically composed by several sememes. Since sememes are not explicit for each word, people manually annotate word sememes and form linguistic common-sense knowledge bases. In this paper, we present that, word sememe information can improve word representation learning (WRL), which maps words into a low-d...