Treebank

基本解釋

The Treebank has size of 1000 thousand Chinese characters.
該樹庫目前已有100萬漢字的槼模。
Experiments show that small addition of converted treebank can improve the performance of dependency parser, while large addition will bring it down.
經(jīng)過細(xì)致分析，我們認(rèn)爲(wèi)，作爲(wèi)一種利用多種樹庫提高依存句法分析器性能的方法，短語轉(zhuǎn)依存還存在很多需要深入研究的方麪。
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%.
在對哈工大中文樹庫語料上的對比測試結(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産生式、判別式句法分析這些複襍模型做了比較，試騐數(shù)據(jù)採用賓州中文樹庫。
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)中文樹庫的測試結(jié)果爲(wèi)F1=85.;5%25，高於隱馬爾可夫模型和最大熵馬爾可夫模型。