發(fā)布時(shí)間：2018-10-05 07:10

【摘要】：提出了一種基于有序詞語移動(dòng)距離的中文文本蘊(yùn)含識(shí)別方法,該方法基于word2vec詞向量計(jì)算有序詞語移動(dòng)距離特征,進(jìn)而利用有序詞語移動(dòng)距離特征和傳統(tǒng)語言學(xué)特征通過支持向量機(jī)生成分類模型,然后使用分類模型進(jìn)行蘊(yùn)含識(shí)別,最終得到蘊(yùn)含結(jié)果.該方法在RITE-VAL評(píng)測(cè)任務(wù)的CS數(shù)據(jù)上的Macro F1為0.629,超過RITEVAL的最優(yōu)評(píng)測(cè)結(jié)果(BUPTTeam,0.615).實(shí)驗(yàn)結(jié)果表明,該方法可以提升中文文本蘊(yùn)含識(shí)別系統(tǒng)的性能.
[Abstract]:A Chinese text implication recognition method based on the moving distance of ordered words is proposed. The method calculates the moving distance of ordered words based on word2vec word vector. Then, the classification model is generated by support vector machine (SVM) using the moving distance feature of ordered words and the traditional linguistic feature, and then the implication recognition is carried out by using the classification model, and the implication result is finally obtained. The Macro F1 on the CS data of RITE-VAL evaluation task is 0.629, which is higher than the optimal evaluation result (BUPTTeam,0.615) of RITEVAL. Experimental results show that this method can improve the performance of Chinese text implication recognition system.
【作者單位】： 北京郵電大學(xué)計(jì)算機(jī)學(xué)院;
【基金】：國(guó)家自然科學(xué)基金項(xiàng)目(U1536121,61370195)
【分類號(hào)】：TP391.1
，

本文編號(hào)：2252477