A large and growing number of web pages display contextual advertising based on keywords automatically extracted from the text of the page, and this is a substantial source of revenue supporting the web today. Despite the importance of this area, little formal, published research exists. We describe a system that learns how to extract keywords from web pages for advertisement targeting. The system uses a number of features, such as term frequency of each

In the sponsored search model, search engines are paid by businesses that are interested in displaying ads for their site alongside the search results. Businesses bid for keywords, and their ad is displayed when the keyword is queried to the search engine. An important problem in this process is keyword generation: given a business that is interested in launching a campaign, suggest keywords that are related to that campaign. We address this problem by making use of the query logs of the search engine. We identify queries related to a campaign by exploiting the associations between queries and URLs as they are captured by the user’s clicks. These queries form good keyword suggestions since they capture the “wisdom of the crowd ” as to what is related to a site. We formulate the problem as a semi-supervised learning problem, and propose algorithms within the Markov Random Field model. We perform experiments with real query logs, and we demonstrate that our algorithms scale to large query logs and produce meaningful results.

Wikipedia article names can be utilized as a controlled vocabulary for identifying the main topics in a document. Wikipedia’s 2M articles cover the terminology of nearly any document collection, which permits controlled indexing in the absence of manually created vocabularies. We combine state-of-the-art strategies for automatic controlled indexing with Wikipedia’s unique property—a richly hyperlinked encyclopedia. We evaluate the scheme by comparing automatically assigned topics with those chosen manually by human indexers. Analysis of indexing consistency shows that our algorithm outperforms some human subjects. 1.

The Rich News system, that can automatically annotate radio and television news with the aid of resources retrieved from the World Wide Web, is described. Automatic speech recognition gives a temporally precise but conceptually inaccurate annotation model. Information extraction from related web news sites gives the opposite: conceptual accuracy but no temporal data. Our approach combines the two for temporally accurate conceptual semantic annotation of broadcast news. First low quality transcripts of the broadcasts are produced using speech recognition, and these are then automatically divided into sections corresponding to individual news stories. A key phrases extraction component finds key phrases for each story and uses these to search for web pages reporting the same event. The text and meta-data of the web pages is then used to create index documents for the stories in the original broadcasts, which are semantically annotated using the KIM knowledge management platform. A web interface then allows conceptual search and browsing of news stories, and playing of the parts of the media files corresponding to each news story. The use of material from the World Wide Web allows much higher quality textual descriptions and semantic annotations to be produced than would have been possible using the ASR transcript directly. The semantic annotations can form a part of the Semantic Web, and an evaluation shows that the system operates with high precision, and with a moderate level of recall.

Abstract. We present a keyphrase extraction algorithm for scientific publications. Different from previous work, we introduce features that capture the positions of phrases in document with respect to logical sections found in scientific discourse. We also introduce features that capture salient morphological phenomena found in scientific keyphrases, such as whether a candidate keyphrase is an acronyms or uses specific terminologically productive suffixes. We have implemented these features on top of a baseline feature set used by Kea [1]. In our evaluation using a corpus of 120 scientific publications multiply annotated for keyphrases, our system significantly outperformed Kea at the p <.05 level. As we know of no other existing multiply annotated keyphrase document collections, we have also made our evaluation corpus publicly available. We hope that this contribution will spur future comparative research. 1

Automatic key phrase extraction is a useful tool in many text related applications such as clustering and summarization. State-of-the-art methods are aimed towards extracting key phrases from traditional text such as technical papers. Application of these methods on Web documents, which often contain diverse and heterogeneous contents, is of particular interest and challenge in the information age. In this work, we investigate the significance of narrative text classification in the task of automatic key phrase extraction in Web document corpora. We benchmark three methods, TFIDF, KEA, and Keyterm, used to extract key phrases from all the plain text and from only the narrative text of Web pages. ANOVA tests are used to analyze the ranking data collected in a user study using quantitative measures of acceptable percentage and quality value. The evaluation shows that key phrases extracted from the narrative text only are significantly better than those obtained from all plain text of Web pages. This demonstrates that narrative text classification is indispensable for effective key phrase extraction in Web document corpora.

Newly published data, when combined with existing public knowledge, allows for complex and sometimes unintended inferences. We propose semi-automated tools for detecting these inferences prior to releasing data. Our tools give data owners a fuller understanding of the implications of releasing data and help them adjust the amount of data they release to avoid unwanted inferences. Our tools first extract salient keywords from the private data intended for release. Then, they issue search queries for documents that match subsets of these keywords, within a reference corpus (such as the public Web) that encapsulates as much of relevant public knowledge as possible. Finally, our tools parse the documents returned by the search queries for keywords not present in the original private data. These additional keywords allow us to automatically estimate the likelihood of certain inferences. Potentially dangerous inferences are flagged for manual review. We call this new technology Web-based inference control. The paper reports on two experiments which demonstrate early successes of this technology. The first experiment shows the use of our tools to automatically estimate the risk that an anonymous document allows for re-identification of its author. The second experiment shows the use of our tools to detect the risk that a document is linked to a sensitive topic. These experiments, while simple, capture the full complexity of inference detection and illustrate the power of our approach.

Abstract. Effectively summarizing Web page collections becomes more and more critical as the amount of information continues to grow on the World Wide Web. A concise and meaningful summary of a Web page collection, which is generated automatically, can help Web users understand the essential topics and main contents covered in the collection quickly without spending much browsing time. However, automatically generating coherent summaries as good as human-authored summaries is a challenging task since Web page collections often contain diverse topics and contents. This research aims towards clustering of Web page collections using automatically extracted topical terms, and automatic summarization of the resulting clusters. We experiment with word- and term-based representations of Web documents and demonstrate that term-based clustering significantly outperforms word-based clustering with much lower dimensionality. The summaries of computed clusters are informative and meaningful, which indicates that clustering and summarization of large Web page collections is promising for alleviating the information overload problem. 1

This paper describes the development of practical automatic metadata assignment tools to support automatic record creation for virtual libraries, metadata repositories and digital libraries, with particular reference to library-standard metadata. The development process is incremental in nature, and depends upon an automatic metadata evaluation tool to objectively measure its progress. The evaluation tool is based on and informed by the metadata created and maintained by librarian experts at the INFOMINE Project, and uses different metrics to evaluate different metadata fields. In this paper, we describe the form and function of common metadata fields, and identify appropriate performance measures for these fields. The automatic metadata assignment tools in the iVia virtual library software are described, and their performance is measured. Finally, we discuss the limitations of automatic metadata evaluation, and cases where we choose to ignore its evidence in favor of human judgment.

Browsing through large volumes of spoken audio is known to be a challenging task for end users. One way to facilitate this task is to provide keyphrases extracted from the audio, thus allowing users to quickly get the gist of the