Extracting Chainese word consisted of 2 characters (word base) and affix from a Chainese characters string in metallurgy

DOI Web Site 1 Citations 5 References

Bibliographic Information

Other Title
  • 金属工学における漢字文字列から2字漢語(語基)と接辞の抽出
  • キンゾク コウガク ニ オケル カンジ モジレツ カラ 2ジ カンゴ ゴキ ト

Search this article

Abstract

At first the string of 2 characters that intervended the string of 3 characters was segmented and pick up automatically by a computer. Those were discriminated the semantic aptitude as a word (word base) of the character string. Then the greater part were the apt Chinese word consisted of 2 characters. In addition the apt affixes, the unsuitable affixes and the independent words consisted of a character from each the characters string were segmented and pick up and those were pigionholded. The new Chinese words consisted of the 2 characters that could get to owe crossing to the affix words off the string of 3 characters didn't include the string of 2 characters were able to be segmented and pick up. Next the apt Chinese word consisted of 2 characters with all the string of 2 characters segmented and pick up automatically and excepted the duplication. Then by investigating and discriminating the string of not duplicate character and verifing the semantic aptitude, the Chinese word consisted of 2 characters as the word base could increased. Futher more the new Chinese word consisted of 2 characters by crossing the Chinese word consisted of 2 characters off a compound word automatically could be extracted easily.

Journal

Citations (1)*help

See more

References(5)*help

See more

Keywords

Details 詳細情報について

Report a problem

Back to top