欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
句子间语义相似性的计算已成为自然语言处理领域的重要研究内容,如何有效地对句子建立语义模型已成为释义识别、文本相似性计算、问答和文本蕴涵等自然语言处理应用的基础任务.文中提出了一种并行的卷积神经网络模型,该模型的两个卷积网络不仅对句子对中的单个句子建立句子向量表示,还对句子经卷积池化后的特征进行相似性度量,并获得句子间的相似性特征.采用释义识别及文本相似性两项任务进行模型性能的实验评测,结果显示,该模型能够较好地表示句子语义信息,其释义识别F1值相比基准实验提高了7.4个百分点,语义相似性评测的皮尔森相关系数比逻辑回归方法有7.1个百分点的提高.
英文摘要：
Computing the semantic similarity between two sentences is an important research issue in natural lan-guage processing field, and,constructing an effective semantic model of sentences is the core task of natural lan-guage processing for paraphrase identification, textual similarity computation, question/answer and textual entail- ment. In this paper, a parallel convolutional neural network model is proposed to represent sentences with fixed- length vectors, and a similarity layer is used to measure the similarity of sentence pairs. Then,two tasks,namely paraphrase identification and textual similarity test, are used to evaluate the performance of the proposed model. Experimental results show that the proposed model can capture sentenced semantic information effectively; and that, in comparison with the state-of-the-art baseline, the proposed model improves the -score in paraphrase identification by 7. 4 percentage points, while in comparison with the logistic regression method, it improves the Pearson correlation coefficient in semantic similarity by 7. 1 percentage points.
同期刊论文项目
同项目期刊论文
期刊信息
位置：