Question classifier is a system that assigns a label to each question. There exist different ways of solving this problem such as rule-based, machine learning, and hybrid approaches. This paper provides a better solution for QC using machine-learning approaches. Three methods of feature extraction...
A subset of the Li and Roth (2005) answer types 其次,需要有一个Question classifier来完成分类。这个可以通过人工书写规则或者机器学习。Webclopedia QA Typology就是一个通过人工规则录入的classifier。但是现在更常用的基本都是机器学习的方法:利用Features来让机器自动寻找合适的配对。「常见的Feature包括问题中的...
以kernel的形式提交. 比赛分为两个阶段, 第一阶段的测试数据占15%, 然后kaggle会在第一阶段结束后重新运行参赛者提交的kernel, 预测得到剩下85%数据的预测值作为最终提交. 如果kernel开GPU则限制时长2小时, 不开GPU则为6小时. 所以首先要保证kernel能在规定时间完成模型的训练和测试, 这样才能取得有效的成绩. 最...
In order to evaluate contributions of question focus, a classifier using question focus is designed and implemented in a practical QA system in restricted domain of computer hardware. Experimental result shows efficiency of question focus and contributions to improve accuracy of question classification ...
It is shown that, in the context of ques- tion classification, augmenting the input of the classifier with appropriate semantic cat- egory information results in significant im- provements to classification accuracy. 展开 关键词: Practical/ classification learning (artificial intelligence) natural ...
This paper presents an integrated method on question classification for Chinese cuisine question answering (QA) system. First, we exploit the domain knowledge to enrich question preprocessing, then classification features are extracted by means of domain attributes and the rule-based classifier is constru...
In this paper, a method of Chinese question classification based on ensemble learning is proposed. Words and Bi-gram are extracted from question as classific features and feature classifiers are constructed. The classifiers are kinds of simple classifier and their generalization ability are not strong...
Then, in each learning round, the classifier is refined by choosing the labeled examples with high confidence from the target domain. Experimental results indicate that the proposed method can effectively explore the training data from the different domain and improve the performance of question ...
In this paper, we present a classifier based on the Support Vector Machine (SVM) machine learning algorithm, and develop a variety of lexical and semantic features for this task. Our experimental results, obtained from a large scale evaluation over thousands of real questions, show the ...
This paper presents and evaluates a rule-based question classifier that partially founds its performance in the detection of the question headword and in its mapping into the target category through the use of WordNet. Moreover, we use the rule-based classifier as a features’ provider of a ...