Presentation is loading. Please wait.

Presentation is loading. Please wait.

开题报告: 一种基于文本蕴含的选择题问题求解方法

Similar presentations


Presentation on theme: "开题报告: 一种基于文本蕴含的选择题问题求解方法"— Presentation transcript:

1 开题报告: 一种基于文本蕴含的选择题问题求解方法
朱维希 指导老师:程龚 2015/11/01

2 来源、目标与意义 来源 目标 意义 瞿裕忠老师主持的863课题“开放域知识集成、推理与检索关键技术及系 统”
采用基于文本蕴含的问题求解方法,解决高考地理一部分选择题。 意义 进一步地发展文本蕴含技术,探索类人智能的实现技术。

3 文本蕴含 定义 给定文本对<T, H>,从T中识别假设文本H是否成立,即是否存在 T∧B ⊨H(B即常识、知识库等背景知识) 举例 T:X painted Y H:Y is the work of X 则:T蕴含H,反之不行(Y未必是画作) 应用 问答(高考地理选择题求解) 举例:

4 文本蕴含 百度百科:地理信息系统 T B H

5 文本蕴含 基于逻辑的方法 举例 自然语言 形式化逻辑表示
采用一些逻辑蕴含检测技术(比如使用”theorem provers”(Rinaldi et al., 2003; Bos & Markert, 2005; Tatu & Moldovan, 2005, 2007)) 举例 “assassinate” is hyponym (下位概念) of “kill” in WordNet 公理(Axiom) : ∀x ∀y assassinate(x, y) ⇒ kill(x, y)

6 文本蕴含 向量空间模型(VSM) (Clarke, 2009) 表面字符串相似度 (Surface String Similarity)
组合多种字符串相似度测量方法 (Malakasiotis & Androutsopoulos, 2007) : 编辑距离 (Levenshtein distance) 曼哈顿距离 (Manhattan distance) 余弦相似度 (Cosine similarity) 该文说明了VSM的方法适用于textual entailment,是因为字面意思已经包含了语义信息(meaning as context) Combine to features in Machine learning

7 文本蕴含 句法/符号相似度 (Syntactic/Symbolic Similarity)
依存树相似度(Malakasiotis, 2009) 树的编辑距离 (Iftene & Balahur-Dobrescu, 2007) 图例是syntactic的句法树,symbolic一般就是语义的层级关系,例如assassinate就是kill的一个特例,kill是assassinate的泛义

8 文本蕴含 使用机器学习算法 (Malakasiotis, 2009)

9 进度计划

10 参考文献 Rinaldi, F., Dowdall, J., Kaljurand, K., Hess, M., & Molla, D. (2003). Exploiting paraphrases in a question answering system. In Proc. of the 2nd Int. Workshop in Paraphrasing, pp. 25–32, Saporo, Japan. Bos, J., & Markert, K. (2005). Recognising textual entailment with logical inference. In Proc. of the Conf. on HLT and EMNLP, pp. 628–635, Vancouver, BC, Canada. Tatu, M., & Moldovan, D. (2005). A semantic approach to recognizing textual entailment. In Proc. of the Conf. on HLT and EMNLP, pp. 371–378, Vancouver, Canada. Tatu, M., & Moldovan, D. (2007). COGEX at RTE 3. In Proc. of the ACL- PASCAL Workshop on Textual Entailment and Paraphrasing, pp. 22–27, Prague, Czech Republic. Malakasiotis, P., & Androutsopoulos, I. (2007). Learning textual entailment using SVMs and string similarity measures. In Proc. of the ACL- PASCAL Workshop on Textual Entailment and Paraphrasing, pp. 42–47, Prague. ACL. Malakasiotis, P. (2009). Paraphrase recognition using machine learning to combine similarity measures. In Proc. of the 47th Annual Meeting of ACL and the 4th Int. Joint Conf. on Nat. Lang. Processing of AFNLP, Singapore. Iftene, A., & Balahur-Dobrescu, A. (2007). Hypothesis transformation and semantic variability rules used in recognizing textual entailment. In Proc. of the ACL- PASCAL Workshop on Textual Entailment and Paraphrasing, pp. 125–130, Prague, Czech Republic.

11 Q&A


Download ppt "开题报告: 一种基于文本蕴含的选择题问题求解方法"

Similar presentations


Ads by Google