Treebank

常見(jiàn)例句

• The Treebank has size of 1000 thousand Chinese characters.
  該樹(shù)庫(kù)目前已有100萬(wàn)漢字的規(guī)模。
• Experiments show that small addition of converted treebank can improve the performance of dependency parser, while large addition will bring it down.
  經(jīng)過(guò)細(xì)致分析，我們認(rèn)為，作為一種利用多種樹(shù)庫(kù)提高依存句法分析器性能的方法，短語(yǔ)轉(zhuǎn)依存還存在很多需要深入研究的方面。
• Comparative experiments on Hit Chinese Treebank corpus show that the new method shows better performance than current Chinese dependency methods, with precision reaching to 86.4%.
  在對(duì)哈工大中文樹(shù)庫(kù)語(yǔ)料上的對(duì)比測(cè)試結(jié)果表明，該方法的依存分析精度達(dá)到86.;4%25，具有很強(qiáng)的依存分析能力。
• In this paper, we compare action-based dependency parsers with complex parsing methods such as generative and discriminative parsers on the standard data set of Penn Chinese Treebank.
  本文將決策式句法分析同產(chǎn)生式、判別式句法分析這些復(fù)雜模型做了比較，試驗(yàn)數(shù)據(jù)采用賓州中文樹(shù)庫(kù)。
• An F1 score of 85.5% is achieved by using the evaluation dataset of Chinese treebank of Beijing university, and obviously better than those of hidden Markov model and maximum entropy Markov model.
  使用北京大學(xué)中文樹(shù)庫(kù)的測(cè)試結(jié)果為F1=85.;5%25，高于隱馬爾可夫模型和最大熵馬爾可夫模型。
• With the support of our Chinese treebank including 64426 words, this paper designs and implements a method for automatic prediction of Chinese phrase boundary location based on neural network.
  在一個(gè)含有64426詞的漢語(yǔ)樹(shù)庫(kù)的支持下，本文設(shè)計(jì)并實(shí)現(xiàn)了基于神經(jīng)元網(wǎng)絡(luò)的漢語(yǔ)短語(yǔ)邊界自動(dòng)識(shí)別模型。
返回 Treebank