我爱自然语言处理

机器翻译新闻一则：SDL公司收购Language Weaver

52nlp — Wed, 21 Jul 2010 15:27:37 +0000

　　也许是时下流行收购吧，前天刚谈了“Google收购语义网公司Metaweb”，没想到今天又发现“SDL公司收购Language Weaver”。Language Weaver是我非常崇拜的统计机器翻译公司，曾经在这里写过”自然语言处理公司巡礼七：Language Weaver“，没想到也被收购了！以下是上述新闻摘录的要点：

　　英国梅登黑德——作为一家领先的全球信息管理方案提供商，SDL 2010年7月15日宣布已签署收购 Language Weaver Inc.（以下简称“Language Weaver”）的协议。Language Weaver 是统计机器翻译领域的先驱，对其收购不仅仅是为了将最好的自动翻译技术移植到 SDL 全球信息管理平台中，事实上它的意义远大于此。将安全的机器翻译技术集成到翻译供应链的各个环节中，可使企业和政府能更快更高效地翻译超大容量的内容，以满足当今急剧增长的网络世界对海量信息的需求。经股东同意，此次交易共购买 Language Weaver 85% 以上的资本所有权，预计将于 2010 年 7 月底完成交易。
　　．．．
　　Language Weaver 总部设在美国加利福尼亚州洛杉矶市，在美国、欧洲和日本都有办公室，拥有雇员96 名。公司与南加利福尼亚大学信息科学研究院（机器翻译研究的领军机构）合作紧密。双方科学家都在共同努力，以期进一步研究和提高统计机器翻译方法。Language Weaver 的创始人Daniel Marcu 和 Kevin Knight 均为统计机器翻译领域的领军人物，他们将继续留任公司。因为 Language Weaver 技术的品质与性能已达到全新水平，Mark Tapling新近提拔成为了 Language Weaver 的 CEO，以便进一步加强公司的商业化进程，Mark Tapling 也将继续留任公司。且当前并无对 Language Weaver 公司进行裁员的计划。
　　．．．
　　 “尽管谷歌翻译已成为消费者即时翻译的标准，但我们发现，大多数企业希望拥有自己的自动翻译技术，”Language Weaver 的董事长兼执行总裁Mark Tapling 说到，“使用Language Weaver，可保证您的内容安全、保密；它遵循翻译工作流程，而且可以很容易地集成到其他系统中。它也可以提供质量排序和受训系统，以提供值得您信赖的质量。它遵守诸如公司品牌和翻译一致性这类要求。Language Weaver的研发团队，不断推进统计机器翻译研究的极限，同时为企业和政府机构提供人际交往解决方案。SDL的收购将大大增强Language Weaver团队解决问题的能力，并向市场推出独特的高价值机器翻译产品和解决方案。”
　　．．．
　　今天，自动翻译仅占翻译市场总量的 1% 左右（据IDC提供的数据，约为100-150亿美元）但市场分析人士预计，无论是整个翻译市场，还是自动翻译的市场份额都将持续大幅度增长。SDL发现自动翻译能降低客户 30％到50％的翻译成本，与此同时，已翻译内容的市场投放时间可缩短 50% 以上。

注：转载请注明出处“我爱自然语言处理”：www.52nlp.cn

本文链接地址：http://www.52nlp.cn/机器翻译新闻一则-sdl公司收购language-weaver

语义网新闻一则：Google收购语义网公司Metaweb

52nlp — Mon, 19 Jul 2010 13:36:36 +0000

　　这几天比较重磅的消息是“Google收购语义网公司Metaweb”，关于Metaweb，这里曾在《自然语言处理公司巡礼六：Metaweb》中介绍过：Metaweb是从事语义网（Semantic Web）技术开发的风险企业，目标是开发用于Web的语义数据存储的基础结构，是曾就职于原美国网景（Netscape）、英特尔以及 AlexaInternet等公司的人才聚集在一起，于2005年7月成立，总部设在美国旧金山。

Google产品管理主管杰克·门泽尔(Jack Menzel)发表博客文章称，该公司可以处理许多搜索请求，但Metaweb的信息可以使其处理更多搜索请求，“通过推出搜索答案等功能，我们才刚刚开始将我们对互联网的理解用于改进搜索体验”，但对于部分搜索仍然无能为力，“例如，‘美国西海岸地区学费低于3万美元的大学’或‘年龄超过40岁且获得过至少一次奥斯卡奖的演员’，这些问题都很难回答。我们之所以收购Metaweb，是因为我们相信，整合Metaweb的技术将使我们能提供更好的答案”。

　　关于此次收购，国内语义网方面知名的W3CHINA（中国万维网联盟）论坛上专门开贴讨论，其中W3China站长的评论尤为精彩：

去年三月，谷歌三位重量级搜索技术专家Alon Halevy、Peter Norvig和Fernando Pereira曾共同撰文《The Unreasonable Effectiveness of Data》（发表于IEEE Intelligent System）低估语义技术的功效，引来一阵拍砖。

当时就有人声称“谷歌不搞语义”，其实在一家商业公司里，存在走不同甚至相反路线的阵营也是很正常的事。

85公里在地球上并算不上多长的路，但这段路如果被铺设在白令海峡上，那么它将贯通美洲大陆和亚欧大陆。

　　有兴趣的读者可以关注原帖：Google购买语义网公司Metaweb，迈向语义网技术领域重要一步

注：转载请注明出处“我爱自然语言处理”：www.52nlp.cn

本文链接地址：http://www.52nlp.cn/语义网新闻一则-google收购语义网公司metaweb

天佑安康，天佑父老乡亲！

52nlp — Sun, 18 Jul 2010 16:05:53 +0000

　　还有一尺，水就要到达家里的二楼了，父亲还在安慰我没事~~虽然从小生活在汉江边，见惯了每年夏天的大小洪水，但是真正的大洪水，我却并没有多少亲历：　　1983年7月安康遭遇百年不遇的特大洪水，我刚出生三个月，家里的老房子上面还过船，但是我没有任何印记；　　2005年安康10月大洪水，我在哈尔滨，等父亲告诉我的时候水已退了，那个时候的最大水位就是还有一尺水就要到家里二楼，幸好水没有再涨；　　前天给家里打电话，父母还告诉我老家没怎么下雨，等今天知道消息时，水已经到家门口了！刚刚给父亲打电话，水平了2005年的记录，不过还在慢慢涨，但是他还在安慰我说没事，让我早点休息！　　这个时候最应该陪在父母身边的是我，可是自己却远隔千里之外，只能通过一部手机还有这个网络搜寻着任何可能的消息！　　天佑安康，天佑父老乡亲！挺过今晚，一切都会好的！相关文章:博客新家，开始新的旅程！ Google’s Python Class – SOS “知行合一”与自然语言处理 “我爱自然语言处理”PageRank再次更新 5.12一周年，愿逝者安息！单词也疯狂——漂亮的“单词云” 关于计算语言学的一首词祝大家牛年一帆风顺赞一下host2ez Google’s Python Class SOS 续 –下载相关文章:

ACL 2010 Best Paper Awards

52nlp — Thu, 15 Jul 2010 14:21:19 +0000

　　ACL 2010官方主页似乎在前几天已经确定好了本次大会的Best Paper Awards，在其Awards页面里，不仅给出了本次大会的Best long paper, Best short paper, IBM Best student paper，而且包括其在会议期间Presented time.

Best long paper
Beyond NomBank: A Study of Implicit Arguments for Nominal Predicates
Matthew Gerber and Joyce Chai

Despite its substantial coverage, NomBank does not account for all within-sentence arguments and ignores extrasentential arguments altogether. These arguments, which we call implicit, are important to semantic processing, and their recovery could potentially benefit many NLP applications. We present a study of implicit arguments for a select group of frequent nominal predicates. We show that implicit arguments are pervasive for these predicates, adding 65% to the coverage of NomBank. We demonstrate the feasibility of recovering implicit arguments with a supervised classification model. Our results and analyses provide a baseline for future work on this emerging task.

Best short paper
SVD and Clustering for Unsupervised POS Tagging
Michael Lamar, Yariv Maron, Mark Johnson, Elie Bienenstock

We revisit the algorithm of Schütze (1995) for unsupervised part-of-speech tagging. The algorithm uses reduced-rank singular value decomposition followed by clustering to extract latent features from context distributions. As implemented here, it achieves state-of-the-art tagging accuracy at considerably less cost than more recent methods. It can also produce a range of finer-grained taggings, with potential applications to various tasks.

IBM Best student paper
Extracting Social Networks from Literary Fiction
David Elson, Nicholas Dames, Kathleen McKeown
（注：该文也是一篇long paper，作者是学生）

We present a method for extracting social networks from literature, namely, nineteenth-century British novels and serials. We derive the networks from dialogue interactions, and thus our method depends on the ability to determine when two characters are in conversation. Our approach involves character name chunking, quoted speech attribution and conversation detection given the set of quotes. We extract features from the social networks and examine their correlation with one another, as well as with metadata such as the novel’s setting. Our results provide evidence that the majority of novels in this time period do not fit two characterizations provided by literacy scholars. Instead, our results suggest an alternative explanation for differences in social networks.

　　Best Paper Awards是由ACL的一个专门委员会评选出的，将在大会结束时进行颁奖。ACL 2010还有一个”Lifetime Achievement Award（终生成就奖）“，不过目前还没有揭晓获奖者。关于这个奖项，ACL 2010给了一段很有意思的介绍：

The ACL Lifetime Achievement Award (LTA) was instituted on the occasion of the Association’s 40th anniversary meeting. The award is presented for scientific achievement, of both theoretical and applied nature, in the field of Computational Linguistics. Currently, an ACL committee nominates and selects at most one award recipient annually, considering the originality, depth, breadth, and impact of the entire body of the nominee’s work in the field. The award is a crystal trophy and the recipient is invited to give a 45-minute speech on his or her view of the development of Computational Linguistics at the annual meeting of the association. As of 2004, the speech has been subsequently published in the Association’s journal, Computational Linguistics. The speech is introduced by the announcement of the award winner, whose identity is not made public until that time.

　　Lifetime Achievement Award（终生成就奖）每届最多只授予一位对于自然语言处理与计算语言学有着举足轻重影响的候选者，此前获得该奖项的分别是：Aravind Joshi (2002), Makoto Nagao (2003), Karen Spärck Jones (2004), Martin Kay (2005), Eva Hajicová (2006), Lauri Karttunen (2007), Yorick Wilks (2008) and Fred Jelinek (2009).

注：转载请注明出处“我爱自然语言处理”：www.52nlp.cn

本文链接地址：http://www.52nlp.cn/acl-2010-best-paper-awards

ACL 2010文章已可下载

52nlp — Sun, 11 Jul 2010 14:30:49 +0000

　　晚上收到ACL Anthology负责人Min-Yen Kan发给ACL Anthology Google Group的邮件，通知说目前ACL 2010的文章已经可以下载，包括full papers, short papers, student research workshop papers, demonstrations, tutorial abstracts以及所有的workshops的Paper，才想起今天（7月11号）ACL 2010会议召开。以下是具体的下载地址，有兴趣的读者可以关注一下。

　　一、ACL 2010大会论文集：
　　Proceedings of the ACL 2010 conference can be found here:
　　http://www.aclweb.org/anthology/P/P10/
　　These include both volumes: (I) full papers and (II) short papers,student research workshop papers, demonstrations and tutorial abstracts.

　　二、Workshop论文集：
　　The proceedings of the workshops and conferences co-located with ACL 2010 are now online.
　　http://www.aclweb.org/anthology/W/W10/
(scroll towards the bottom of the table of contents)

* Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR
* Fourth Linguistic Annotation Workshop
* 2010 Workshop on Biomedical Natural Language Processing
* 2010 Workshop on Cognitive Modeling and Computational Linguistics
* 2010 Workshop on NLP and Linguistics: Finding the Common Ground
* 11th Meeting of the ACL Special Interest Group on Computational Morphology and Phonology
* TextGraphs-5 – 2010 Workshop on Graph-based Methods for Natural Language Processing
* 2010 Named Entities Workshop
* 2010 Workshop on Applications of Tree Automata in Natural Language Processing
* 2010 Workshop on Domain Adaptation for Natural Language Processing
* 2010 Workshop on Companionable Dialogue Systems
* 2010 Workshop on GEometrical Models of Natural Language Semantics

注：转载请注明出处“我爱自然语言处理”：www.52nlp.cn

本文链接地址：http://www.52nlp.cn/acl-2010文章已可下载

自然语言处理与世界杯

52nlp — Wed, 30 Jun 2010 13:00:36 +0000

　　自然语言处理与世界杯似乎没啥关系，不过今晚世界杯没有比赛了，我也可以回来照顾一下52nlp了。但是这两者的确没什么关系，我简单的Google了一下“自然语言处理 & 世界杯”，没有什么好的材料，就先从读者评论说起吧。
　　读者Brishen评论：“可不可以对网络上赛前的言论做sentiment analysis来预测一下比赛结果呢？” 估计Brishen对Sentiment analysis（情感分析）有比较深的认识，我个人没有任何这方面的经验，不过感觉是一个不错的方向，不仅仅对于世界杯。如果读者有这方面的经验，欢迎在这里讨论。
　　聚类在自然语言处理中也有比较重要的应用，譬如词的聚类或者文本聚类。章成志老师近期写了一篇《世界杯比赛规则与数据聚类》，大概是与世界杯相关的最具科普性的一篇博文了，和自然语言处理也能扯点关系，以下全文转载自章成志老师的博客。

　　　　　　　　　世界杯比赛规则与数据聚类

　　应该有很多博友像我一样，这段时间可能要花些时间看世界杯。有些博友还会发些心得。俺就从数据聚类的角度，来对世界杯比赛规则进行“重认识”一下，呵呵。

　　先交代下基础背景知识，内行直接跳过本段，呵呵。数据聚类包括划分聚类、层次聚类等、基于模型的聚类等基本模式。划分聚类中最经典的方法就是K-均值聚类，需要事先给定初始点和聚类类目数。层次聚类中最常用的是HAC聚类，事先两两求出相似度，将最相似的或者最不相似的连接起来呢，然后再求次相似的，一直到所有点的都被连接为止。近年来，基于模型的聚类越来越火，可以将基于竞争的聚类方法划入这个类别。07年Frey提出的AP聚类方法更是被大量引用。

　　再结合数据聚类，说下世界杯比赛规则。

　　1. 首先，小组划分，是做基于约束的划分聚类：

　　(1) 经过预选赛入围的32只球队，被划分为4个档次，其中第一档中的8支球队作为种子队（32个数据，8个聚类类目，将以往世界排名作为权重，选择初始聚类中心，当然东道主特殊，直接作为种子）；

　　(2) 剩余球队按照其档次和所在洲的约束，进行抽签划分到相应的小组中（24个数据按照一定的规则约束后，随机分配到每个聚类中心的所在组中）；

　　 2. 然后，正式比赛，是做层次聚类：

　　(1) 小组确定后，每组四个对，两两求“相似度”，就是说两两打一场，胜的权重给3，平了给1，输了给0，每小组的6场赛事结束后，得到每个队的总体权重（当然了，有可能还要考虑净胜球，相互战绩啥的），那么小组中排名前2的队作为连接点参与下一个层次的聚类。（这里，两两求相似度，完全是基于竞争的，整个比赛阶段基于竞争的层次聚类）；

　　(2) 淘汰赛阶段，直接竞争，做二分聚类，胜的参加下一轮聚类；

　　(3) 直到最后两支最牛的打决赛，冠军队成为了根节点。

　　 3. 聚类结束，参数重新分配，准备4年后的聚类，呵呵。

　　所以，世界杯做了大量的约束，注意比赛的观赏性，用了比较简单公平的方法，在较短时间内确定聚类层次关系。

　　如果是动物界打比赛，可能又是另一个场景，完全自由随机的打，最强的完全有可能因为体力不支，提早被淘汰而成不了冠军。

　　以上仅供娱乐参考，推理和比喻不当地方，请博友指出，谢谢。

　　关于自然语言处理与世界杯，不知道读者朋友还能想到些什么？

注：转载请注明出处“我爱自然语言处理”：www.52nlp.cn

本文链接地址：http://www.52nlp.cn/自然语言处理与世界杯

COLING 2010: List of Accepted Papers (Oral)

52nlp — Fri, 04 Jun 2010 12:31:58 +0000

　　这是Coling 2010的List of Accepted Papers(Oral)，先是从水木自然语言处理社区看到，才在Coling的官方主页上找到。关于Coling本次的录用情况，水木自然语言处理版已经有过一波大讨论了，有兴趣的读者可以关注一下。 Coling是ACL之外另一个自然语言处理与计算语言学界的顶级会议，全称国际计算语言学大会(International Conference on Computational Linguistics)，每两年举办一次，第23届COLING会议将于2010年8月23日~27日在中国北京举行，由中文信息学会承办。
　　以下仅列出Oral的录用情况，关于Poster的录用情况，可以在Coling 2010官方网站的全部录用结果中找到：
　　http://www.coling-2010.org/accepted%20papers.htm

Oral
1. Adrian Bickerstaffe and Ingrid Zukerman. A Hierarchical Classifier Applied to Multi-way Sentiment Detection
2. Yiping Zhou, Lan Nie and Scott Gaffney. Surface Form Resolution Based on Wikipedia
3. Zhongwu Zhai, Bing Liu, Hua Xu and Peifa Jia. Grouping Product Features Using Semi-Supervised Learning with Soft-Constraints
4. Qin Gao, Francisco Guzman and Stephan Vogel. EMDC: A Semi-supervised Approach for Word Alignment
5. George Tsatsaronis, Iraklis Varlamis and Kjetil Nørvåg. SemanticRank: Ranking Keywords and Sentences Using Semantic Graphs
6. Jian Huang, Pucktada Treeratpituk, Sarah Taylor and C. Lee Giles. Enhancing Cross Document Coreference of Web Documents with Context Similarity and Very Large Scale Text Categorization
7. Verena Henrich and Erhard Hinrichs. Standardizing Wordnets in the ISO Standard Wordnet-LMF: The Case of GermaNet
8. Ekaterina Shutova, Lin Sun and Anna Korhonen. Metaphor Identification Using Verb and Noun Clustering
9. Xiaoyan Cai, Wenjie Li and You Ouyang. Simultaneous Ranking and Clustering of Sentences: An Reinforcement Approach to Multi-Document Summarization
10. Peter Nilsson and Pierre Nugues. Automatic Discovery of Feature Sets for Dependency Parsing
11. Kavita Ganesan and ChengXiang Zhai. Opinosis: A Graph Based Approach to Abstractive Summarization of Highly Redundant Opinions
12. Doo Soon Kim, Ken Barker and Bruce Porter. Improving the Quality of Text Understanding by Delaying Ambiguity Resolution
13. Gumwon Hong, Chi-Ho Li, Ming Zhou and Hae-Chang Rim. An Empirical Study on Web Mining of Parallel Data
14. Nigel Collier, Reiko Matsuda Goodwin, John McCrae, Son Doan, Ai Kawazoe, Mike Conway, Asanee Kawtrakul, Koichi Takeuchi and Dinh Dien. An ontology-driven system for detecting global health events
15. Changqin Quan and Fuji Ren. An Exploration of Features for Recognizing Word Emotion
16. Jun Sun, Min Zhang and Chew Lim Tan. Discriminative Induction of Sub-Tree Alignment using Limited Labeled Data
17. Wanxiang Che and Ting Liu. Jointly Modeling WSD and SRL with Markov Logic
18. Su Nam Kim, Timothy Baldwin and Min-Yen Kan. Evaluating N-gram based Evaluation Metrics for Automatic Keyphrase Extraction
19. Yang Liu and Qun Liu. Joint Parsing and Translation
20. Shiqi Zhao, Haifeng Wang and Ting Liu. Paraphrasing with Search Engine Query Logs
21. Daniel Tse and James R. Curran. Chinese CCGbank: extracting CCG derivations from the Penn Chinese Treebank
22. Liang-Chih Yu, Hsiu-Min Shih, Yu-Ling Lai, Jui-Feng Yeh and Chung-Hsien Wu. Discriminative Training for Near-Synonym Substitution
23. Shiqi Zhao, Haifeng Wang, Xiang Lan and Ting Liu. Leveraging Multiple MT Engines for Paraphrase Generation
24. Audrey Laroche and Philippe Langlais. Revisiting Context-based Projection Methods for Term-Translation Spotting in Comparable Corpora
25. Bernd Bohnet. Top Accuracy and Fast Dependency Parsing is not a Contradiction
26. Sebastian Spiegler and Andrew van der Spuy. Ukwabelana – An open-source morphological Zulu corpus
27. Fang KONG, Guodong ZHOU, Longhua QIAN and Qiaoming ZHU. Dependency-driven Anaphoricity Determination for Coreference Resolution
28. Veronika Vincze and János Csirik. Hungarian Corpus of Light Verb Constructions
29. ding liu and daniel gildea. Semantic Role Features for Machine Translation
30. Fan Bu, Xiaoyan Zhu and Ming Li. Measuring the Non-compositionality of Multiword Expressions
31. Kai Wang and Tat-Seng Chua. Exploiting Salient Patterns for Question Detection and Question Retrieval in Community-based Question Answering
32. Matthias Hartung and Anette Frank. A Structured Vector Space Model for Hidden Attribute Meaning in Adjective-Noun Phrases
33. Guintaré Grigonyté, João Paulo Cordeiro, Rumen Moraliyski, Gaël Dias and Pavel Brazdil. Paraphrase Alignment for Synonym Evidence Discovery
34. Yaakov HaCohen-Kerner, Aharon Tayeb and Natan Ben-Dror. Plagiarism Detection in Computer Science Papers
35. Shane Bergsma and Colin Cherry. Fast and Accurate Arc Filtering for Dependency Parsing
36. Fei Huang and Bing Xiang. Feature-Rich Discriminative Phrase Rescoring for SMT
37. Katja Filippova. Multi-Sentence Compression: Finding Shortest Paths in Word Graphs
38. Roland Kuhn, Boxing Chen, George Foster and Evan Stratford. Phrase Clustering for Smoothing TM Probabilities – or, How to Extract Paraphrases from Phrase Tables
39. Josep Maria Crego, Aurélien Max and Fran?ois Yvon. Local lexical adaptation in Machine Translation through triangulation: SMT helping SMT
40. Young-Suk Lee, Bing Zhao and Xiaoqian Luo. Constituent Reordering and Syntax Models for English-to-Japanese Statistical Machine Translation
41. Mu Li, Ying-Gong Zhao, Dongdong Zhang and Ming Zhou. Adaptive Log-linear Model Parameter Selection for Statistical Machine Translation
42. Mengqiu Wang and Christopher Manning. Probabilistic Tree-Edit Models with Structured Latent Variables for Textual Entailment and Question Answering
43. Sara Salem and Samir AbdelRahman. A Multiple-Domain Ontology Builder
44. Ge Xu, Xinfan Meng and Houfeng Wang. Build Chinese Emotion Lexicons Using A Graph-based Algorithm and Multiple Resources
45. Yunfang Wu and Miaomiao Wen. Disambiguating Dynamic Sentiment Ambiguous Adjectives
46. Shasha Liao and Ralph Grishman. Filtered Ranking for Bootstrapping in Event Extraction
47. Shoushan Li, Sophia Y. M. Lee, Ying Chen, Chu-Ren Huang and Guodong Zhou. Sentiment Classification and Polarity Shifting
48. Bernard Brosseau-Villeneuve, Jian-Yun Nie and Noriko Kando. Towards an optimal weighting of context words based on distance
49. Makoto Miwa, Rune Sætre, Yusuke Miyao and Jun’ichi Tsujii. Entity-Focused Sentence Simplification for Relation Extraction
50. Chien Chin Chen and Chen-Yuan Wu. Bipolar Person Name Identification of Topic Documents Using Principal Component Analysis
51. Fangtao Li, Chao Han, Minlie Huang, Xiaoyan Zhu, Ying-Ju Xia, Shu Zhang and Hao Yu. Structure-Aware Review Mining and Summarization
52. Hassan Al-Haj and Shuly Wintner. Identifying Multi-word Expressions by Leveraging Morphological and Syntactic Idiosyncrasy
53. Nan Duan, Mu Li, Dongdong Zhang and Ming Zhou. Mixture Model-based Minimum Bayes Risk Decoding using Multiple Machine Translation Systems
54. Xinyan Xiao, Yang Liu, YoungSook Hwang, Qun Liu and Shouxun Lin. Joint Tokenization and Translation
55. Nan Duan. Translation Model Generalization using Probability Averaging for Machine Translation
56. Anders S?gaard and Christian Rish?j. Robust semi-supervised dependency parsing of German and Swedish using generalized tri-training
57. Laura Kallmeyer and Wolfgang Maier. Data-Driven Parsing with Probabilistic Linear Context-Free Rewriting Systems
58. Xian Qian, Qi Zhang, Xuangjing Huang and Lide Wu. 2D Trie for fast parsing
59. Stergos Afantenos and Nicholas Asher. Testing SDRT’s Right Frontier: Implications for Machine Learning Discourse Graphs
60. Naoaki Okazaki and Jun’ichi Tsujii. Simple and Efficient Algorithm for Approximate Dictionary Matching
61. Zarrieß Sina, Cahill Aoife, Kuhn Jonas and Rohrer Christian. Cross-Lingual Induction for Deep Broad-Coverage Syntax: A Case Study on German Participles
62. Jinhua Du and Andy Way. A Discriminative Latent Variable-Based “DE” Classifier for Chinese–English SMT
63. Makoto Miwa, Sampo Pyysalo, Tadayoshi Hara and Jun’ichi Tsujii. Evaluating Dependency Representations for Event Extraction
64. Zhemin Zhu, Delphine Bernhard and Iryna Gurevych. A Monolingual Syntactic Translation Model for Sentence Simplification
65. Ksenia Shalonova and Bruno Golenia. Weakly Supervised Morphology Learning for Agglutinating Languages Using Small Training Sets.
66. Xiaojun Wan. Towards a Unified Approach to Simultaneous Single-Document and Multi-Document Summarizations
67. Seokhwan Kim, Minwoo Jeong, Jonghoon Lee and Gary Geunbae Lee. A Cross-lingual Annotation Projection Approach for Relation Detection
68. Erwin Marsi and Emiel Krahmer. Automatic analysis of semantic similarity in comparable text through syntactic tree matching
69. Chao Shen and Tao Li. Multi-Document Summarization via the Minimum Dominating Set
70. Kun Wang, Chengqing Zong and Keh-Yih Su. A Character-Based Joint Model for Chinese Word Segmentation
71. Sung-Pil Choi and Sung-Hyon Myaeng. Simplicity is Better: Revisiting Single Kernel PPI Extraction
72. Tao Zhuang and Chengqing Zong. A Minimum Error Weighting Combination Strategy for Chinese Semantic Role Labeling
73. Hui Yang, Anne De Roeck, Alistair Willis and Bashar Nuseibeh. A Methodology for Automatic Identification of Nocuous Ambiguity
74. Toyomi Meguro, Ryuichiro Higashinaka, Yasuhiro Minami and Kohji Dohsaka. Controlling Listening-oriented Dialogue using Partially Observable Markov Decision Processes
75. Makbule Ozsoy, Ilyas Cicekli and Ferda Alpaslan. Text Summarization of Turkish Texts using Latent Semantic Analysis
76. Alena Neviarouskaya, Helmut Prendinger and Mitsuru Ishizuka. Recognition of Affect, Judgment, and Appreciation in Text
77. Mark Dredze, Paul McNamee, Delip Rao, Adam Gerber and Tim Finin. Entity Disambiguation for Knowledge Base Population
78. Minh-Thang Luong and Min-Yen Kan. Enhancing Morphological Alignment for Translating Highly Inflected Languages
79. Junhui Li, Guodong Zhou and Qiaoming Zhu. Learning the Scope of Negation via Shallow Semantic Parsing
80. Graeme Blackwood, Adrià de Gispert and William Byrne. Fluency Constraints for Minimum Bayes-Risk Decoding of Statistical Machine Translation Lattices
81. Muhua Zhu, Jingbo Zhu and Tong Xiao. Heterogeneous Parsing via Collaborative Decoding
82. Yue Lu, Huizhong Duan, Hongning Wang and ChengXiang Zhai. Exploiting Structured Ontology to Organize Scattered Online Opinions
83. Richard Johansson and Alessandro Moschitti. Reranking Models in Fine-grained Opinion Analysis
84. Ying Chen, Sophia Yat Mei Lee, Shoushan Li and Chu-Ren Huang. Emotion Cause Detection with Linguistic Constructions
85. Karthik Visweswariah, Jiri Navratil, Jeffrey Sorensen, Vijil Chenthamarakshan and Nandakishore Kambhatla. Syntax Based Reordering with Automatically Derived Rules for Improved Statistical Machine Translation
86. Bo Li and Eric Gaussier. Improving Corpus Comparability for Bilingual Lexicon Extraction from Comparable Corpora
87. Zhaopeng Tu, Yang Liu, Young-Sook Hwang, Qun Liu and Shouxun Lin. Dependency Forest for Statistical Machine Translation
88. Tomek Strzalkowski, George Aaron Broadwell, Jennifer Stromer-Galley, Samira Shaikh, Sarah Taylor and Nick Webb. Modeling Socio-Cultural Phenomena in Discourse
89. Henning Wachsmuth, Peter Prettenhofer and Benno Stein. Ef?cient Statement Identi?cation for Automatic Market Forecasting
90. Spence Green and Christopher D. Manning. Better Arabic Parsing: Baselines, Evaluations, and Analysis
91. Jian Zhang and Pascale Fung. A Rhetorical Syntax-Driven Model for Speech Summarization
92. Nuria Bel, Maria Coll and Gabriela Resnik. Automatic Detection of Non-deverbal Event Nouns for Quick Lexicon Production
93. Joakim Nivre, Laura Rimell, Ryan McDonald and Carlos Gómez Rodríguez. Evaluation of Dependency Parsers on Unbounded Dependencies
94. Lin Sun, Thierry Poibeau, Anna Korhonen and Cedric Messiant. Investigating the cross-linguistic potential of VerbNet -style classification
95. Sebastian Spiegler and Christian Monson. EMMA: A novel Evaluation Metric for Morphological Analysis
96. Naoki Yoshinaga and Masaru Kitsuregawa. Kernel Slicing: Scalable Online Training with Conjunctive Features
97. Xiaohua LIU, Kuan LI, Bo HAN, Ming ZHOU and Long JIANG. Semantic Role Labeling for News Tweets
98. Hector Llorens, Estela Saquete and Borja Navarro. TimeML Events Recognition and Classification: Learning CRF Models with Semantic Roles
99. Dmitry Davidov and Ari Rappoport. Automated Translation of Semantic Relationships
100. Bernd Bohnet, Leo Wanner, Simon Mill and Alicia Burga. Broad Coverage Multilingual Deep Sentence Generation with a Stochastic Multi-Level Realizer
101. Smruthi Mukund, Debanjan Ghosh and Rohini Srihari. Using Cross-Lingual Projections to Generate Semantic Role Labeled Annotated Corpus for Urdu – A Resource Poor Language
102. Michael Roth and Anette Frank. EM-based Alignment of Routes and Route Directions for Natural Language Generation
103. Lilja Øvrelid, Erik Velldal and Stephan Oepen. Syntactic Scope Resolution in Uncertainty Analysis
104. Vahed Qazvinian and Dragomir R. Radev. Citation Summarization Through Keyphrase Extraction
105. Jianfeng Gao, Xiaolong Li, Daniel Micol and Chris Quirk. A Large Scale Ranker-Based System A large scale ranker-bsaed system for search query spelling correction
106. Fabio Massimo Zanzotto, Ioannis Korkontzelos, Francesca Fallucchi and Suresh Manandhar. Estimating Linear Models for Compositional Distributional Semantics
107. Daniel Andrade, Tetsuya Nasukawa and Junichi Tsujii. Robust Measurement and Comparison of Context Similarity for Finding Translation Pairs
108. Markus Dickinson. Generating Learner-Like Morphological Errors in Russian
109. Alberto Barrón-Cede?o, Paolo Rosso, Eneko Agirre and Gorka Labaka. Plagiarism Detection across Distant Language Pairs
110. ThuyLinh Nguyen, Stephan Vogel and Noah A. Smith. Nonparametric Word Segmentation for Machine Translation
111. Claire Gardent and Laura Perez-Beltrachini. Efficient RTG based surface realisation for TAG
112. Rohit Kate, Xiaoqiang Luo, Siddharth Patwardhan, Martin Franz, Radu Florian, Raymond Mooney, Salim Roukos and Chris Welty. Learning to Predict Readability using Diverse Linguistic Features
113. Tong Wang and Graeme Hirst. Near-synonym Lexical Choice in Latent Semantic Space
114. Xiaowen Ding and Bing Liu. Resolving Object and Attribute Coreference in Opinion Mining
115. Ines Rehbein, Josef Ruppenhofer and Alexis Palmer. Bringing Active Learning to Life
116. Shachar Mirkin, Jonathan Berant, Ido Dagan and Eyal Shnarch. Recognising Entailment within Discourse
117. Alpa Jain and Patrick Pantel. FactRank: Random Walks on a Web of Facts
118. Petr Knoth, Jakub Novotny and Zdenek Zdrahal. Automatic generation of inter-passage links based on textual analysis of content
119. Andre Blessing and Hinrich Schütze. Self-Annotation for fine-grained geospatial relation extraction
120. Bart Cramer and Yi Zhang. Constraining robust constructions for broad-coverage parsing with precision grammars
121. Alpa Jain and Marco Pennacchiotti. Open Entity Extraction fromWeb Search Query Logs
122. Simon Zwarts, Mark Johnson and Robert Dale. Detecting Speech Repairs Incrementally Using a Noisy Channel Approach
123. Shuming Shi, Huibin Zhang, Xiaojie Yuan and Ji-Rong Wen. Corpus-based Semantic Class Mining: Distributional vs. Pattern-Based Approaches
124. Mark Johnson and Katherine Demuth. Unsupervised phonemic Chinese word segmentation using Adaptor Grammars
125. Sujith Ravi, Ashish Vaswani, Kevin Knight and David Chiang. Fast, Greedy Model Minimization for Unsupervised Tagging
126. Sanae Fujita and Masaaki Nagata. Enriching Dictionaries with Images from the Internet – Targeting Wikipedia and a Japanese Semantic Lexicon: Lexeed -
127. Dmitriy Genzel. Automatically Learning Source-side Reordering Rules for Large Scale Machine Translation
128. Bin Chen, Jian Su and Chew Lim Tan. A Twin-Candidate Based Approach for Event Pronoun Resolution using Composite Kernel
129. Yao Yao and Feng-hsi Liu. A Working Report on Statistically Modeling Dative Variation in Mandarin Chinese
130. Emily Pitler, Shane Bergsma, Dekang Lin and Kenneth Church. Using Web-scale N-grams to Improve Base NP Parsing Performance
131. Derya Ozkan, Kenji Sagae and Louis-Philippe Morency. Latent Mixture of Discriminative Experts for Multimodal Prediction Modeling
132. Carmen Banea, Rada Mihalcea and Janyce Wiebe. Multilingual Subjectivity: Are More Languages Better?
133. Tom Lippincott, Diarmuid ó Séaghdha, Lin Sun and Anna Korhonen. Exploring variation across biomedical subdomains
134. Jie Cai and Michael Strube. End-to-End Coreference Resolution via Hypergraph Partitioning
135. Pascal Denis and Philippe Muller. Comparison of different algebras for inducing the temporal structure of texts
136. Yang Wang and Kathleen McKeown. “Got You!”: Automatic Vandalism Detection in Wikipedia with Web-based Syntactic-Semantic Modeling
137. Katsuhiko Hayashi, Hajime Tsukada, Katsuhito Sudoh, Kevin Duh and Seiichi Yamamoto. Hierarchical Phrase-based Machine Translation with Word-based Reordering Model
138. Razvan Bunescu and Yunfeng Huang. A Utility-Driven Approach to Question Ranking
139. Jakob Uszkoreit, Jay Ponte, Ashok Popat and Moshe Dubiner. Large Scale Parallel Document Mining for Machine Translation
140. Xiance Si and Maosong Sun. Explore the Structure of Social Tags by Subsumption Relations
141. Mitesh Khapra, Saurabh Sohoney, Anup Kulkarni and Pushpak Bhattacharyya. Value for Money: Balancing Annotation Effort, Lexicon Building and Accuracy for Multilingual WSD
142. Mei Yang and Katrin Kirchhoff. Contextual Modeling for Meeting Translation Using Unsupervised Word Sense Disambiguation
143. Yee Seng Chan and Dan Roth. Exploiting Background Knowledge for Relation Extraction
144. Jong-Hoon Oh, Ichiro Yamada, Kentaro Torisawa and De Saeger Stijn. Co-STAR: A Co-training Style Algorithm for Hyponymy Relation Acquisition from Structured and Unstructured Text
145. Yuncong Chen and Pascale Fung. Unsupervised Synthesis of Multilingual Wikipedia Articles
146. Xiaofeng YU and Wai LAM. Jointly Identifying Entities and Extracting Relations in Encyclopedia Text via A Graphical Model Approach
147. Ryan Georgi, Fei Xia and Will Lewis. Comparing Language Similarity Across Genetic and Typologically-Based Groupings
148. Julia Hockenmaier and Yonatan Bisk. Normal-form parsing for Combinatory Categorial Grammars with generalized composition and type-raising
149. Lizhen Qu, Georgiana Ifrim and Gerhard Weikum. The Bag-of-Opinions Method for Review Rating Prediction from Sparse Text Patterns
150. Yanqing He and Yu Zhou. A Novel Reordering Model Based on Multi-layer Phrase for Statistical Machine Translation
151. Jeff Pasternack and Dan Roth. Knowing what to Believe (when you already know something)
152. Wei Zhang, Jian Su and Chew Lim Tan. Entity Linking Leveraging Automatically Generated Annotation
153. Yajuan Duan, Long Jiang, Tao Qin, Ming Zhou and Harry Shum. An Empirical Study on Learning to Rank of Tweets
154. Shanheng Zhao and Hwee Tou Ng. Maximum Metric Score Training for Coreference Resolution
155. Sheng Guo and Naren Ramakrishnan. Finding the Storyteller: Automatic Spoiler Tagging using Linguistic Cues
156. Altaf Rahman and Vincent Ng. Fine-Grained Semantic Class Induction via Hierarchical and Collective Classification
157. Yao-zhong Zhang, Takuya Matsuzaki and Jun’ichi Tsujii. Forest-guided Supertagger Training

注：转载请注明出处“我爱自然语言处理”：www.52nlp.cn

本文链接地址：http://www.52nlp.cn/coling-2010-list-of-accepted-papers-oral

条件随机场文献阅读指南

52nlp — Mon, 24 May 2010 15:49:02 +0000

　　与最大熵模型相似，条件随机场（Conditional random fields，CRFs）是一种机器学习模型，在自然语言处理的许多领域（如词性标注、中文分词、命名实体识别等）都有比较好的应用效果。条件随机场最早由John D. Lafferty提出，其也是Brown90的作者之一，和贾里尼克相似，在离开IBM后他去了卡耐基梅隆大学继续搞学术研究，2001年以第一作者的身份发表了CRF的经典论文 “Conditional random fields: Probabilistic models for segmenting and labeling sequence data”。
　　关于条件随机场的参考文献及其他资料，Hanna Wallach在05年整理和维护的这个页面“conditional random fields”非常不错，其中涵盖了自01年CRF提出以来的很多经典论文（不过似乎只到05年，之后并未更新）以及几个相关的工具包(不过也没有包括CRF++），但是仍然非常值得入门条件随机场的读者参考，以下摘选自该网页。

introduction

Conditional random fields (CRFs) are a probabilistic framework for labeling and segmenting structured data, such as sequences, trees and lattices. The underlying idea is that of defining a conditional probability distribution over label sequences given a particular observation sequence, rather than a joint distribution over both label and observation sequences. The primary advantage of CRFs over hidden Markov models is their conditional nature, resulting in the relaxation of the independence assumptions required by HMMs in order to ensure tractable inference. Additionally, CRFs avoid the label bias problem, a weakness exhibited by maximum entropy Markov models (MEMMs) and other conditional Markov models based on directed graphical models. CRFs outperform both MEMMs and HMMs on a number of real-world tasks in many fields, including bioinformatics, computational linguistics and speech recognition.

tutorial

Hanna M. Wallach. Conditional Random Fields: An Introduction. Technical Report MS-CIS-04-21. Department of Computer and Information Science, University of Pennsylvania, 2004.

papers by year

2001

John Lafferty, Andrew McCallum, Fernando Pereira. Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data. In Proceedings of the Eighteenth International Conference on Machine Learning (ICML-2001), 2001.

2002

Hanna Wallach. Efficient Training of Conditional Random Fields. M.Sc. thesis, Division of Informatics, University of Edinburgh, 2002.

Thomas G. Dietterich. Machine Learning for Sequential Data: A Review. In Structural, Syntactic, and Statistical Pattern Recognition; Lecture Notes in Computer Science, Vol. 2396, T. Caelli (Ed.), pp. 15–30, Springer-Verlag, 2002.

2003

Fei Sha and Fernando Pereira. Shallow Parsing with Conditional Random Fields. In Proceedings of the 2003 Human Language Technology Conference and North American Chapter of the Association for Computational Linguistics (HLT/NAACL-03), 2003.

Andrew McCallum. Efficiently Inducing Features of Conditional Random Fields. In Proceedings of the 19th Conference in Uncertainty in Articifical Intelligence (UAI-2003), 2003.

David Pinto, Andrew McCallum, Xing Wei and W. Bruce Croft. Table Extraction Using Conditional Random Fields. In Proceedings of the 26th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2003), 2003.

Andrew McCallum and Wei Li. Early Results for Named Entity Recognition with Conditional Random Fields, Feature Induction and Web-Enhanced Lexicons. In Proceedings of the Seventh Conference on Natural Language Learning (CoNLL), 2003.

Wei Li and Andrew McCallum. Rapid Development of Hindi Named Entity Recognition Using Conditional Random Fields and Feature Induction. In ACM Transactions on Asian Language Information Processing (TALIP), 2003.

Yasemin Altun and Thomas Hofmann. Large Margin Methods for Label Sequence Learning. In Proceedings of 8th European Conference on Speech Communication and Technology (EuroSpeech), 2003.

Simon Lacoste-Julien. Combining SVM with graphical models for supervised classification: an introduction to Max-Margin Markov Networks. CS281A Project Report, UC Berkeley, 2003.

2004

Andrew McCallum, Khashayar Rohanimanesh and Charles Sutton. Dynamic Conditional Random Fields for Jointly Labeling Multiple Sequences. Workshop on Syntax, Semantics, Statistics; 16th Annual Conference on Neural Information Processing Systems (NIPS 2003), 2004.

Kevin Murphy, Antonio Torralba and William T.F. Freeman. Using the forest to see the trees: a graphical model relating features, objects and scenes. In Advances in Neural Information Processing Systems 16 (NIPS 2003), 2004.

Sanjiv Kumar and Martial Hebert. Discriminative Fields for Modeling Spatial Dependencies in Natural Images. In Advances in Neural Information Processing Systems 16 (NIPS 2003), 2004.

Ben Taskar, Carlos Guestrin and Daphne Koller. Max-Margin Markov Networks. In Advances in Neural Information Processing Systems 16 (NIPS 2003), 2004.

Burr Settles. Biomedical Named Entity Recognition Using Conditional Random Fields and Rich Feature Sets. To appear in Proceedings of the International Joint Workshop on Natural Language Processing in Biomedicine and its Applications (NLPBA), 2004.

A demo of the system can be downloaded here.

Charles Sutton, Khashayar Rohanimanesh and Andrew McCallum. Dynamic Conditional Random Fields: Factorized Probabilistic Models for Labeling and Segmenting Sequence Data. In Proceedings of the Twenty-First International Conference on Machine Learning (ICML 2004), 2004.

John Lafferty, Xiaojin Zhu and Yan Liu. Kernel conditional random fields: representation and clique selection. In Proceedings of the Twenty-First International Conference on Machine Learning (ICML 2004), 2004.

Xuming He, Richard Zemel, and Miguel Á. Carreira-Perpiñán. Multiscale conditional random fields for image labelling. In Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2004), 2004.

Yasemin Altun, Alex J. Smola, Thomas Hofmann. Exponential Families for Conditional Random Fields. In Proceedings of the 20th Conference on Uncertainty in Artificial Intelligence (UAI-2004), 2004.

Michelle L. Gregory and Yasemin Altun. Using Conditional Random Fields to Predict Pitch Accents in Conversational Speech. In Proceedings of the 42^nd Annual Meeting of the Association for Computational Linguistics (ACL 2004), 2004.

Brian Roark, Murat Saraclar, Michael Collins and Mark Johnson. Discriminative Language Modeling with Conditional Random Fields and the Perceptron Algorithm. In Proceedings of the 42^nd Annual Meeting of the Association for Computational Linguistics (ACL 2004), 2004.

Ryan McDonald and Fernando Pereira. Identifying Gene and Protein Mentions in Text Using Conditional Random Fields. BioCreative, 2004.

Trausti T. Kristjansson, Aron Culotta, Paul Viola and Andrew McCallum. Interactive Information Extraction with Constrained Conditional Random Fields. In Proceedings of the Nineteenth National Conference on Artificial Intelligence (AAAI 2004), 2004.

Thomas G. Dietterich, Adam Ashenfelter and Yaroslav Bulatov. Training Conditional Random Fields via Gradient Tree Boosting. In Proceedings of the Twenty-First International Conference on Machine Learning (ICML 2004), 2004.

John Lafferty, Yan Liu and Xiaojin Zhu. Kernel Conditional Random Fields: Representation, Clique Selection, and Semi-Supervised Learning. Technical Report CMU-CS-04-115, Carnegie Mellon University, 2004.

Fuchun Peng and Andrew McCallum (2004). Accurate Information Extraction from Research Papers using Conditional Random Fields. In Proceedings of Human Language Technology Conference and North American Chapter of the Association for Computational Linguistics (HLT/NAACL-04), 2004.

Yasemin Altun, Thomas Hofmann and Alexander J. Smola. Gaussian process classification for segmenting and annotating sequences. In Proceedings of the Twenty-First International Conference on Machine Learning (ICML 2004), 2004.

Yasemin Altun and Thomas Hofmann. Gaussian Process Classification for Segmenting and Annotating Sequences. Technical Report CS-04-12, Department of Computer Science, Brown University, 2004.

2005

Cristian Smimchisescu, Atul Kanaujia, Zhiguo Li and Dimitris Metaxus. Conditional Models for Contextual Human Motion Recognition. In Proceedings of the International Conference on Computer Vision, (ICCV 2005), Beijing, China, 2005.

Ariadna Quattoni, Michael Collins and Trevor Darrel. Conditional Random Fields for Object Recognition. In Advances in Neural Information Processing Systems 17 (NIPS 2004), 2005.

Jospeh Bockhorst and Mark Craven. Markov Networks for Detecting Overlapping Elements in Sequence Data. In Advances in Neural Information Processing Systems 17 (NIPS 2004), 2005.

Antonio Torralba, Kevin P. Murphy, William T. Freeman. Contextual models for object detection using boosted random fields. In Advances in Neural Information Processing Systems 17 (NIPS 2004), 2005.

Sunita Sarawagi and William W. Cohen. Semi-Markov Conditional Random Fields for Information Extraction. In Advances in Neural Information Processing Systems 17 (NIPS 2004), 2005.

Yuan Qi, Martin Szummer and Thomas P. Minka. Bayesian Conditional Random Fields. To appear in Proceedings of the Tenth International Workshop on Artificial Intelligence and Statistics (AISTATS 2005), 2005.

Aron Culotta, David Kulp and Andrew McCallum. Gene Prediction with Conditional Random Fields. Technical Report UM-CS-2005-028. University of Massachusetts, Amherst, 2005.

Yang Wang and Qiang Ji. A Dynamic Conditional Random Field Model for Object Segmentation in Image Sequences. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), Volume 1, 2005.

software

MALLET: A Machine Learning for Language Toolkit.

MALLET is an integrated collection of Java code useful for statistical natural language processing, document classification, clustering, information extraction, and other machine learning applications to text.

ABNER: A Biomedical Named Entity Recognizer.

ABNER is a text analysis tool for molecular biology. It is essentially an interactive, user-friendly interface to a system designed as part of the NLPBA/BioNLP 2004 Shared Task challenge.

MinorThird.

MinorThird is a collection of Java classes for storing text, annotating text, and learning to extract entities and categorize text.

Kevin Murphy’s MATLAB CRF code.

Conditional random fields (chains, trees and general graphs; includes BP code).

Sunita Sarawagi’s CRF package.

The CRF package is a Java implementation of conditional random fields for sequential labeling.

　　最后推荐CRF++:Yet Another CRF toolkit，如果读者对于基于字标注的中文分词感兴趣，可以很快的利用该工具包构造一个基于条件随机场的中文分词工具，而且性能也不赖。

注：转载请注明出处“我爱自然语言处理”：www.52nlp.cn

本文链接地址：http://www.52nlp.cn/条件随机场文献阅读指南

足球依然是圆的！

52nlp — Sat, 22 May 2010 20:43:18 +0000

　　作为国米的死忠和穆里尼奥的追随者，这一刻，很幸福！相关文章:胡正，StarDict，TheSourceCodeOfMyWorld Google’s Python Class – SOS 祝福大家虎年吉祥如意单词也疯狂——漂亮的“单词云” 52nlp博客恢复 “大教堂与市集”摘要关于计算语言学的一首词机器翻译与微软对联赞一下host2ez 天佑安康，天佑父老乡亲！相关文章:

微软：Web N-gram Services

52nlp — Wed, 12 May 2010 18:07:12 +0000

　　微软研究院的官方网站上近期发布了一篇文章：“Microsoft Web N-gram Services“，大意是邀请整个社区使用其提供的”Web N-gram services”,这个服务旨在通过基于云的存储平台，推动网络搜索，自然语言处理，语音技术等相关领域，在研究现实世界的大规模网络数据时，利用该服务所提供动态数据对项目中的常规数据进行补充更新，进而有所发现和创新。
　　有意思的是它的副标题：“Access petabytes of data via the Web N-gram services (Public Beta)”，注意微软这个服务提供的是PB(petabytes)级别的数据:
　　1PB = 1PeraByte = 1024 TB = 1024 * 1024 * 1024 MB
　　如果说Google的1T n-gram语言模型还可以压缩到大硬盘里使用的话，那么PB级别的n-gram语言模型目前来说最好的存储平台就是“云端”了。
　　微软的这项”Web N-gram Services”包括如下服务内容：
　　* Content types: Document Body, Document Title, Anchor Texts
　　* Model types: Smoothed models
　　* N-gram availability: unigram, bigram, trigram, N-gram with N=4, 5.（最大也是5元）
　　* Training size (Body): All documents indexed by Bing
　　* Access: Hosted Services by Microsoft
　　* Updates: Periodical updates
　　查了一下微软的这个“Web N-gram Services”，大致是在4月下旬WWW2010会议上公开的，之前一年属于”private beta”，目前是“public beta”，不过这篇文章最后说得是：“We are now expanding access in the Public Beta Web N-gram Services to include professors and students at accredited colleges and universities worldwide.” 似乎只针对授权的大学教授和学生开放。
　　不过网上目前可以查到如何使用该服务的文章：How to use Microsoft Web N-gram service，微软自己也有一个“Quick Start”，需要你”read the terms of use”并点击“I agree”之后就能看到，或者，可以试一下下面这个网页：

http://web-ngram.research.microsoft.com/info/quickstart.htm

　　这两份文档都比较详细，有兴趣和条件的读者可以试一下。

注：转载请注明出处“我爱自然语言处理”：www.52nlp.cn

本文链接地址：http://www.52nlp.cn/微软-web-n-gram-services