Natural Language Question Answering over Large-scale Linked Data

Size: px

Start display at page:

Download "Natural Language Question Answering over Large-scale Linked Data"

诉梁
5 years ago
Views:

1 Natural Language Question Answering over Large- scale Linked Data Kang Liu National Laboratory of Pattern Recognition (NLPR) Institute of Automation, Chinese Academy of Sciences 8/30/2014 Kun Ming

2 Knowledge Graph: Linked Data 超过 5.7 亿实体超过 18 亿条事实 ( 关系 ) 百度知心 2,653,873 概念搜狗知立方

3 More Linked Data

4 How to access these Linked Data Which software has been developed by organizations founded in California, USA? Experts or Developer SELECT DISTINCT?uri WHERE {?uri rdf:type dbo:software.?uri dbo:developer?x1.?x1 rdf:type dbo:company.?x1 dbo:foundationplace dbr:california. } SPARQL 2(Integer) version Android {Answer} developer Google foundationplace Apache_License license type programmedin California Java Software developer Oracle Linked Data

5 How to access these Linked Data Which software has been developed by organizations founded in California, USA? QA System SELECT DISTINCT?uri WHERE {?uri rdf:type dbo:software.?uri dbo:developer?x1.?x1 rdf:type dbo:company.?x1 dbo:foundationplace dbr:california. } SPARQL 2(Integer) version Android {Answer} developer Google foundationplace Apache_License license type programmedin California Java Software developer Oracle Linked Data

6 Pipeline Process Which software has been developed by organizations founded in California, USA? Question software, developed by, organizations, founded in, California Phrase dbo:software, dbo:developer, dbo:company, dbo:foundationplace, dbr:california. Semantic Item <dbo:software, dbo:developer, dbo:company> <dbo:company, dbo:foundationplace, dbr:california> Semantic Triple SELECT DISTINCT?uri WHERE {?uri rdf:type dbo:software.?uri dbo:developer?x1.?x1 rdf:type dbo:company.?x1 dbo:foundationplace dbr:california. } SPARQL

7 Challenges Manually designed patterns Phrase detenction rules NN NNP:Entity NN:Class Property VB:Property Semantic item grouping patterns (syntactic patterns) Verb and its arguments Adjectives and its arguments Prepositionally modified tokens and its objects (?x, dbo:productor, dbo:film)

8 Challenges Manually designed patterns Phrase detenction rules NN NNP:Entity NN:Class Property VB:Property Semantic item grouping patterns (syntactic patterns) Verb and its arguments Adjectives and its arguments Prepositionally modified tokens and its objects Can we automatically learn rules or (?x, patterns? dbo:productor, dbo:film)

9 Challenges Ambiguities Phrase Detection: { California }, { California, USA } Which software has been developed by organizations founded in California, USA? Phrase Mapping: California: {California_State}, {California_Film} Semantic Item Grouping: {dbo:software, dbo:developer, dbo:company} {dbo:software, dbo:foundationplace, dbo:company}

10 Challenges Ambiguities Phrase Detection: { California }, { California, USA } Which software has been developed by organizations founded in California, USA? Phrase Mapping: California: {California_State}, {California_Film} Semantic Item Grouping: {dbo:software, dbo:developer, dbo:company} {dbo:software, dbo:foundationplace, dbo:company} Can we make joint inference?

11 Our Solution Pattern Learning Meta patterns Not only verb and its arguments All syntactic paths maybe possible Joint Inference First-order logic formulas Markov Logic Network p1(a,b) p3(a,a) p2(a) p2(b) p3(b,b) 1 φi p( y) = exp( w fc ( y)) Z φ i ( φi, wi ) L c C n i p4(a) p1(b,a) p4(b)

12 Predicates Hidden Predicates Observed Predicates hasphrase(i) hasresource(i, j) hasrelation (ri, rj, rr) The ith candidate phrase has been chosen The ith phrase is mapped to the jth semantic item The semantic item ri and rj can be grouped together with the relation type rr

13 Predicates Hidden Predicates Observed Predicates hasphrase(i) hasresource(i, j) hasrelation (ri, rj, rr) The ith candidate phrase has been chosen The ith phrase is mapped to the jth semantic item The semantic item ri and rj can be grouped together with the relation type rr

14 Hard Formulas Formulas

15 Soft Formulas Formulas

16 Soft Formulas Formulas

17 Framework 问题预处理 : 问题类型 Focus 去除无用词等问句 In which movies directed by Garry Marshall was Julia Roberts starring? DBpedia Wikipedia Word2vec Reverb&Patty 统计信息短语检测 & 资源映射 & 特征提取问句 MLN 模型谓词和公式 MLN 联合消岐构造查询图资源映射候选结构匹配候选资源映射结果结构匹配结果查询图生成查询 SPARQL 语句 10

18 Framework 问题预处理 : 问题类型 Focus 去除无用词等问句 In which movies directed by Garry Marshall was Julia Roberts starring? movies directed by Garry Marshall was Julia Roberts starring in DBpedia Wikipedia Word2vec Reverb&Patty 统计信息短语检测 & 资源映射 & 特征提取问句 MLN 模型谓词和公式 MLN 联合消岐构造查询图资源映射候选结构匹配候选资源映射结果结构匹配结果查询图生成查询 SPARQL 语句 10

19 Framework 问题预处理 : 问题类型 Focus 去除无用词等问句 In which movies directed by Garry Marshall was Julia Roberts starring? movies directed by Garry Marshall was Julia Roberts starring in DBpedia Wikipedia Word2vec Reverb&Patty 统计信息 MLN 模型谓词和公式短语检测 & 资源映射 & 特征提取 MLN 联合消岐构造查询图问句资源映射候选结构匹配候选资源映射结果结构匹配结果 >hascandidateresource >hasheadpos movies" "dbo:film " movies " "NNS "directed by" "dbo:director "directed" "VBN" "by" "dbo:publisher" "Garry Marshall " "NNP "Garry Marshall " "dbr:garry_marshall >hasdeppath >hasresourcetype " movies " "directed by" "nsubj- prep" "dbo:film" "Concept "directed by" "Garry Marshall" "pobj- nn "dbo:director" "Property >istypecompatible "dbr:garry_marshall""concept "dbo:film" "dbo:director" "1_1" "dbo:director" "dbr:garry_marshall " "2_1 查询图生成查询 SPARQL 语句 10

20 Framework 问题预处理 : 问题类型 Focus 去除无用词等问句 In which movies directed by Garry Marshall was Julia Roberts starring? movies directed by Garry Marshall was Julia Roberts starring in DBpedia Wikipedia Word2vec Reverb&Patty 统计信息 MLN 模型谓词和公式短语检测 & 资源映射 & 特征提取 MLN 联合消岐构造查询图问句资源映射候选结构匹配候选资源映射结果结构匹配结果 >hascandidateresource >hasheadpos movies" "dbo:film " movies " "NNS "directed by" "dbo:director "directed" "VBN" "by" "dbo:publisher" "Garry Marshall " "NNP "Garry Marshall " "dbr:garry_marshall >hasdeppath >hasresourcetype " movies " "directed by" "nsubj- prep" "dbo:film" "Concept "directed by" "Garry Marshall" "pobj- nn "dbo:director" "Property >istypecompatible "dbr:garry_marshall""concept "dbo:film" "dbo:director" "1_1" "dbo:director" "dbr:garry_marshall " "2_1 >hasresource " movies " "dbo:film" "directed by" "dbo:director" "Garry Marshall " "dbr:garry_marshall" "Julia Roberts" "dbr:julia_roberts" "starring in" "dbo:starring > hasrelation "dbo:film" "dbo:director" "1_1" "dbo:film" "dbo:starring" "1_1" "dbo:director " "dbr:garry_marshall " "2_1" "dbr:julia_roberts " "dbo:starring " "1_2" 查询图生成查询 SPARQL 语句 10

21 Framework 问题预处理 : 问题类型 Focus 去除无用词等问句 In which movies directed by Garry Marshall was Julia Roberts starring? movies directed by Garry Marshall was Julia Roberts starring in DBpedia Wikipedia Word2vec Reverb&Patty 统计信息 MLN 模型谓词和公式短语检测 & 资源映射 & 特征提取 MLN 联合消岐构造查询图问句资源映射候选结构匹配候选资源映射结果结构匹配结果 >hascandidateresource >hasheadpos movies" "dbo:film " movies " "NNS "directed by" "dbo:director "directed" "VBN" "by" "dbo:publisher" "Garry Marshall " "NNP "Garry Marshall " "dbr:garry_marshall >hasdeppath >hasresourcetype " movies " "directed by" "nsubj- prep" "dbo:film" "Concept "directed by" "Garry Marshall" "pobj- nn "dbo:director" "Property >istypecompatible "dbr:garry_marshall""concept "dbo:film" "dbo:director" "1_1" "dbo:director" "dbr:garry_marshall " "2_1 >hasresource " movies " "dbo:film" "directed by" "dbo:director" "Garry Marshall " "dbr:garry_marshall" "Julia Roberts" "dbr:julia_roberts" "starring in" "dbo:starring > hasrelation "dbo:film" "dbo:director" "1_1" "dbo:film" "dbo:starring" "1_1" "dbo:director " "dbr:garry_marshall " "2_1" "dbr:julia_roberts " "dbo:starring " "1_2" 查询图生成查询 SPARQL 语句 10

22 Framework 问题预处理 : 问题类型 Focus 去除无用词等问句 In which movies directed by Garry Marshall was Julia Roberts starring? movies directed by Garry Marshall was Julia Roberts starring in DBpedia Wikipedia Word2vec Reverb&Patty 统计信息 MLN 模型谓词和公式短语检测 & 资源映射 & 特征提取 MLN 联合消岐构造查询图问句资源映射候选结构匹配候选资源映射结果结构匹配结果 >hascandidateresource >hasheadpos movies" "dbo:film " movies " "NNS "directed by" "dbo:director "directed" "VBN" "by" "dbo:publisher" "Garry Marshall " "NNP "Garry Marshall " "dbr:garry_marshall >hasdeppath >hasresourcetype " movies " "directed by" "nsubj- prep" "dbo:film" "Concept "directed by" "Garry Marshall" "pobj- nn "dbo:director" "Property >istypecompatible "dbr:garry_marshall""concept "dbo:film" "dbo:director" "1_1" "dbo:director" "dbr:garry_marshall " "2_1 >hasresource " movies " "dbo:film" "directed by" "dbo:director" "Garry Marshall " "dbr:garry_marshall" "Julia Roberts" "dbr:julia_roberts" "starring in" "dbo:starring > hasrelation "dbo:film" "dbo:director" "1_1" "dbo:film" "dbo:starring" "1_1" "dbo:director " "dbr:garry_marshall " "2_1" "dbr:julia_roberts " "dbo:starring " "1_2" 生成查询查询图 SPARQL 语句 10 SELECT DISTINCT?uri WHERE {?uri rdf:type dbo:film.?uri dbo:starring res:julia_roberts.?uri dbo:director res:garry_marshall. }

23 Experiments Questions three collections of questions from QALD QALD1, QALD3, QALD4 Linked Data: DBpedia, YAGO MLN: thebeast toolkit inference algorithm: cutting plane approach[3] weights learning algorithm: MIRA

24 Effect of Pattern Learning

25 Effect of Joint Inference

26 Effect of Joint Inference

27 Ours vs. state- of- the- art

28 Conclusion and Future work Pattern learning is needed for parsing a question over large- scale linked data Joint inference can effective for improving the performance of natural language question answering Scaled up to multiple interlinked knowledge bases Labeled data is insufficient to build up a robust model More robust solutions to find the implicit properties in questions

29 Reference: Questioning Answering over Linked Data Using Markov First- order Logic, To appear in Proceedings of EMNLP 2014, Doha, Qatar, October, Thanks : 刘康 _ 自动化所 Homepage:

腾讯.key

腾讯.key 面向大规模开放域知识库问答系统刘康中国科学院自动化研究所模式识别国家重点实验室 2015 年 3 月 25 日搜索急需一场变革 IDC 统计, 全球数据量以每年 58% 的速度增长,2020 年将达到 40ZB, 是 2011 年数据总量的 22 倍交互方式的转变需要信息服务模式的转变移动互联网以及可穿戴设备的飞速发展需要高效准确的自然语言形式的信息服务方式问答系统是下