1、 自然语言处理的新需求、新资源、新技术董振 董强东e-mail: http:/Tel: (8610) 6287-5641 Tel: (8610) 6676-8816 Intel China Research Forum北京 2000/10/11提纲差距与反思- 成就是过去时，不足是将来时知网- 一种新的资源 - 新资源促进新技术差距与反思层次浅语境窄知识颗粒度小流行技术的极限音字转换 信息过滤 文本分析语音识别 文本分类 歧义排除OCR 信息检索 文本理解语法检查 自动文摘 机器翻译音字转换系统（输入法）上这摊某被立即送往医院，但终因史学过多，不止身亡。伤者谭某被立即送往医院，但终因失血过多，
2、不治身亡。上这里某被立即送往医院，但终因留学过多，不止身亡。伤者李某被立即送往医院，但终因流血过多，不治身亡。唐非情此获准。唐飞请辞获准。语法检查In a few years time, there will be no Internet companies - there will just be companies - and all companies that are going to operate in the economics of a few years, in the future, are going to be Internet companies. - Andrew
3、S. Grove(1) areThe world will little note, nor long remember what we say here, but it can never forget what they did here.- Abraham Lincon(1)world wills / worlds will(2)will little neither note, nor / will no little note, orIt would be something that we actually will almost take for granted and wond
4、er how business was done before we incorporated this in a very deep way- Bill Gates(1) wonders信息检索华 华 ，新华 北 北 ，北 ， 北 学 ， 自动文摘Advances in Automatic Text SummarizationWith the rapid growth of the World Wide Web and electronic information services, information is becoming available on-line at an incred
5、ible rate. One result is the oft-decried information overload. No one has time to read everything, yet we often have to make critical decisions based on what we are able to assimilate. The technology of automatic text summarization is becoming indispensable for dealing with this problem. Text summar
6、ization is the process of distilling the most important information from a source to produce an abridged version for a particular user or task. Until now there has been no state-of-the-art collection of the most important writings in automatic text summarization. This book presents the key developme
7、nts in the field in an integrated framework and suggests future research areas. The book is organized into six sections: Classical Approaches, Corpus-Based Approaches, Exploiting Discourse Structure, Knowledge-Rich Approaches, Evaluation Methods, and New Summarization Problem Areas. （55%）自动翻译Do you
8、think I could stay here and become nothing to you? Do you think, because I am poor, and obscure and plain, that I am soulless and heartless? I have as much soul as you and fully as much heart. And if God had gifted me with wealth and beauty I should have made it as hard for you to leave me as it is
9、now for me to leave you. There I have spoken my heart and let me go.这里 留 东 成 ，因 ， currency1， 是“ 情的currency1fiAS多 fl分 多。时 上 ” 因 。 里 的 去。(1988 的系统) 这里留 成 ? 因 是 不 , 是 fi的 情? 多 多. 上 ”的 , 留 的 .里 的 去。(1999 的系统)知网- 一种新的资源知网的 与知网的HowNet How knowledge is represented and acquired?How meaning can be formalized and calculated?How meaning is expressed and conveyed?知网 的 知网2000 与1999 的不2000 1999 语种 （GB）- 语 GB + Big5 器 + 本 知识 11 6 新 修订10,000余加 文多义义项例 内容扩 事件系与角色转换库知网- 文信息结构库
