【摘要】：本文依托國(guó)家“863”課題“泛在空間信息關(guān)聯(lián)更新與面向主題時(shí)空信息挖掘研究”,較為系統(tǒng)地探索中文文本中事件時(shí)空與屬性信息解析方法,為泛在空間信息動(dòng)態(tài)關(guān)聯(lián)更新,全球統(tǒng)一時(shí)空框架下的空間信息與知識(shí)服務(wù)提供數(shù)據(jù)和技術(shù)支持,同時(shí)為事件時(shí)空模式挖掘奠定數(shù)據(jù)基礎(chǔ),進(jìn)而為事件風(fēng)險(xiǎn)評(píng)估、公共安全等重大問(wèn)題提供決策服務(wù)。本文針對(duì)中文文本中事件時(shí)空與屬性信息描述的非結(jié)構(gòu)化、定性化和不確定性等特點(diǎn),圍繞“文本描述-規(guī)范化表達(dá)-結(jié)構(gòu)化抽取-可視化重構(gòu)”的技術(shù)主線,重點(diǎn)研究事件時(shí)空與屬性信息解析方法。主要研究?jī)?nèi)容與結(jié)論包括以下幾個(gè)方面： (1)事件時(shí)空與屬性信息的結(jié)構(gòu)化表達(dá)：通過(guò)歸納總結(jié)中文文本中事件時(shí)空與屬性信息描述的語(yǔ)言特征和語(yǔ)義結(jié)構(gòu),設(shè)計(jì)了事件時(shí)空與屬性信息的知識(shí)表達(dá)框架和標(biāo)注體系；以突發(fā)公共事件為例,以網(wǎng)絡(luò)文本為數(shù)據(jù)源,基于GATE平臺(tái)構(gòu)建了中文文本中事件時(shí)空與屬性信息標(biāo)注語(yǔ)料庫(kù),為事件時(shí)空與屬性信息抽取研究提供了標(biāo)準(zhǔn)化訓(xùn)練和測(cè)試數(shù)據(jù)。 (2)事件時(shí)空與屬性信息抽�。悍治鲋形奈谋局袝r(shí)間信息描述的規(guī)律性,實(shí)現(xiàn)了基于觸發(fā)詞和規(guī)則模型結(jié)合的時(shí)間信息抽取、推理和規(guī)范化解析,準(zhǔn)確率、召回率和F值分別達(dá)到75.00%、88.24%和40.54%；利用條件隨機(jī)場(chǎng)模型和規(guī)則模型,實(shí)現(xiàn)了事件名稱識(shí)別和空間位置(包括地名和空間關(guān)系)信息抽取,其中事件名稱識(shí)別準(zhǔn)確率、召回率和F值分別為82.08%、80.18%和81.12%；設(shè)計(jì)了基于Bootstrapping的事件屬性信息抽取算法,量詞性的屬性信息抽取準(zhǔn)確率和召回率達(dá)到80.80%和85.16%。 (3)時(shí)空驅(qū)動(dòng)的事件分類方法：通過(guò)分析事件時(shí)空認(rèn)知和表達(dá)特性,提出一種融合時(shí)間、空間、屬性、事件名稱、觸發(fā)詞匯等多種上下文語(yǔ)義和語(yǔ)境信息的事件分類方法。按照句子、段落、篇章三個(gè)語(yǔ)言單元等級(jí),探討了事件替代性名稱的推理方法。實(shí)驗(yàn)結(jié)果表明,事件分類準(zhǔn)確率在封閉和開放測(cè)試中分別達(dá)到92.30%和80.60%。 (4)事件時(shí)空信息匹配與可視化：以地名數(shù)據(jù)庫(kù)為空間數(shù)據(jù)源,提出了定性時(shí)空信息(地名、空間關(guān)系和時(shí)間信息)的匹配和可視化表達(dá)方法,探索了基于“時(shí)間-空間-概念類型”多重一致性約束的主題事件判斷和時(shí)空過(guò)程重構(gòu)方法,實(shí)現(xiàn)了事件信息在時(shí)空信息系統(tǒng)中有機(jī)的、直觀的可視化表達(dá),并對(duì)事件時(shí)空信息分布模式進(jìn)行了聚類分析。 研究結(jié)果表明,采用規(guī)則模型和統(tǒng)計(jì)模型結(jié)合的方式可以有效實(shí)現(xiàn)中文文本中事件時(shí)空與屬性信息抽取,但是特征項(xiàng)的設(shè)置在統(tǒng)計(jì)模型的學(xué)習(xí)過(guò)程中起到舉足輕重的作用；不同類型事件的時(shí)間、地名、空間關(guān)系、事件名稱和類型等信息抽取模型具有通用性和可移植性,而屬性信息存在較大差異,需要針對(duì)具體類型事件構(gòu)建相應(yīng)知識(shí)庫(kù)和學(xué)習(xí)模型；事件類型判斷存在靈活、復(fù)雜、語(yǔ)義模糊、不確定性特點(diǎn),且屬于多標(biāo)記分類,融合詞性、觸發(fā)詞匯、時(shí)間、空間、屬性和事件名稱等多種上下文語(yǔ)義和語(yǔ)境信息,可以有效提高事件分類效果；空間數(shù)據(jù)的覆蓋范圍和數(shù)據(jù)質(zhì)量,以及空間關(guān)系解析模型,對(duì)事件時(shí)空與屬性信息匹配、時(shí)空過(guò)程重構(gòu)性能具有較大的影響。
[Abstract]:Based on the national "863" topic "Research on Spatial Information Association updating and topic oriented spatio-temporal information mining", this paper systematically explores the analysis method of event space-time and attribute information in Chinese text, providing data and data for spatial information and knowledge services under the global unified space-time framework. Technology support provides a data base for event spatio-temporal pattern mining, and then provides decision-making services for event risk assessment, public security and other major issues. This paper focuses on the unstructured, qualitative and uncertain features of event spatiotemporal and attribute information described in Chinese text, and the text description - normalized expression - structured extraction The main line of research is to take visual refactoring, focusing on temporal spatial and attribute information analysis methods. The main research contents and conclusions include the following aspects:
(1) structured expression of event space-time and attribute information: by summarizing the linguistic features and semantic structures of event spatiotemporal and attribute information described in Chinese text, the knowledge expression framework and tagging system of event space-time and attribute information are designed, and a public event is taken as an example, the network text is the data source, and the GATE platform is constructed. The corpus of event temporal and attribute information in Chinese text is built, which provides standardized training and test data for the research of event space time and attribute information extraction.
(2) event spatiotemporal and attribute information extraction: analyzing the regularity of time information description in Chinese text, realizing time information extraction based on the combination of trigger word and rule model, reasoning and normalization analysis, accuracy rate, recall rate and F value reached 75%, 88.24% and 40.54% respectively, and realized the use of conditional random field model and rule model. Event name recognition and spatial location (including place name and spatial relationship) information extraction, of which event name recognition accuracy, recall rate and F value are 82.08%, 80.18% and 81.12% respectively. Bootstrapping based event attribute information extraction algorithm is designed, and the accuracy rate and recall rate of word based attribute information extraction are 80.80% and 85.16%.
(3) time and space driven classification of events: by analyzing time and space cognition and expression characteristics of events, an event classification method is proposed, which combines time, space, attribute, event name, triggering vocabulary and other contextual and contextual information. According to the sentence, paragraph, text, three language unit levels, this paper discusses the push of event substitutes. Experimental results show that the accuracy of event classification is 92.30% and 80.60%. respectively in closed and open tests.
(4) the matching and visualization of event space-time information: using the geographical name database as the spatial data source, the method of matching and visualizing the qualitative spatio-temporal information (place name, spatial relationship and time information) is proposed. The method of subject event judgment and time space process reconstruction based on the multiple consistency of time space concept type is explored and the method of time and space process reconfiguration is realized. The organic and intuitive visual expression of event information in spatiotemporal information system is analyzed, and the temporal and spatial information distribution patterns of events are clustered.
The research results show that the combination of rule model and statistical model can effectively implement the information extraction of event spatiotemporal and attribute information in Chinese text, but the setting of feature items plays an important role in the learning process of statistical models; time, place name, spatial relation, event name and type of events of different types of events The extraction model has generality and portability, and there are great differences in attribute information. The corresponding knowledge base and learning model should be constructed for specific types of events. The event type judgment has the characteristics of flexible, complex, semantic fuzzy and uncertainty, and it belongs to multi label classification, fusion of words, triggering vocabulary, time, space, attribute and event name. A variety of contextual semantic and contextual information can effectively improve the effect of event classification; the coverage and data quality of spatial data, as well as the spatial relationship analytic model, have a great influence on the matching of event space-time and attribute information and the performance of time and space process reconfiguration.
【學(xué)位授予單位】：南京師范大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2013
【分類號(hào)】：P208;TP391.1

【參考文獻(xiàn)】

相關(guān)期刊論文 前4條

1 丁信善;語(yǔ)料庫(kù)語(yǔ)言學(xué)的發(fā)展及研究現(xiàn)狀[J];當(dāng)代語(yǔ)言學(xué);1998年01期

2 許榮華;吳剛;李培峰;朱巧明;;基于事件框架的主題事件融合研究[J];計(jì)算機(jī)應(yīng)用研究;2009年12期

3 方經(jīng)民;;漢語(yǔ)空間方位參照的認(rèn)知結(jié)構(gòu)[J];世界漢語(yǔ)教學(xué);1999年04期

4 樂(lè)小虬;楊崇俊;于文洋;;基于空間語(yǔ)義角色的自然語(yǔ)言空間概念提取[J];武漢大學(xué)學(xué)報(bào)(信息科學(xué)版);2005年12期

相關(guān)碩士學(xué)位論文 前1條

1 王宇;基于網(wǎng)絡(luò)文本的地名空間模糊建模[D];南京師范大學(xué);2012年

，

本文編號(hào)：2138011