Anastasios Tombros and Mark Sanderson. 1998. Advantages of query biased summaries in information retrieval. In Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 2--10.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....assessment, a subject is presented with a document and a topic, and asked to determine the relevance of the document to the topic. The influence of summarization on accuracy and time in the task is then studied. There have been numerous extrinsic evaluations involving this task paradigm [37], 12] 4] 16] 17] of which the TIPSTER SUMMAC evaluation [17] was the most large scale, developerindependent evaluation. Although the SUMMAC evaluation included the intrinsic Q A evaluation component described above, its main focus was on an extrinsic evaluation, based on tasks which ....

Tombros, A., and Sanderson, M. 1998. Advantages of query biased summaries in information retrieval. In Proceedings of the 21st ACM SIGIR Conference (SIGIR'98), pp. 2-10.

....information retrieval (IR) In the context of IR, summarization has at least two possibilities: it can be used in preprocessing or in postprocessing. Many researchers have dealt with the latter, by providing the user with query focused summaries of retrieved documents for ecient relevance preview [1, 5, 12, 22, 24]. In contrast, little work has been reported regarding the former, which involves the use of generic summaries instead of fulltexts as the source of document index terms to improve retrieval e ectiveness and or eciency. For convenience, we treat full text as a single word in this paper. While ....

Tombros, A. and Sanderson, M.: Advantages of Query Biased Summaries in Information Retrieval, ACM SIGIR '98 Proceedings, pp. 2-10 (1998).

....how characteristic a word is for its text. Considering domain specific summarization, words that are characteristic for a given topic, not for a text as a whole, must be found. In the context of Information Retrieval, words from the user query indicate the topic for specific summarization [13, 1], but only coarsely as queries tend to be rather short. Sentence compression has only recently been explored. In most approaches, syntactical clues were used to find phrases within a sentence that can be cancelled [7, 9] However, as will be argued in section 4.2, important information can show ....

A. Tombros and M. Sanderson. Advantages of query biased summaries in information retrieval. In Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 2--10, 1998.

.... based (TH based) sentence extraction algorithm[6] My main interest during this workshop was to measure the effect of topic identification based on the thematic hierarchy. I was particularly interested in measuring smaller differences of summaries with task based evaluation than Tombros et al.[9] measured in comparing a query biased summary with one comprising the first few sentences of a source text. For this purpose, I tailored a TH based summarization algorithm and a baseline algorithm that did not use the thematic hierarchy of the text for either of the tasks performed (i.e. tasks A ....

A. Tombros and M. Sanderson. Advantages of query biased summaries in information retrieval. In Proc. of SIGIR'98, pages 2 10. the Association for Computing Machinery, 1998.

....do not master many foreign languages. A rough translation probably suits the case better but of what quality High quality is not always possible, and translation speed is also a concern. Therefore, shallow translation of browsing quality seems a more practical alternative. Tombros Sanderson [6] have reported that user biased summaries can improve monolingual retrieval performance. We believe translated summaries can also help users in a similar way. Therefore, summarization is designed as an integral part of MuST. In this demonstration, we show MuST in the context of retrieving, ....

Tombros, A. and Sanderson M. Advantages of Query Biased Summaries in Information Retrieval. In Proceedings of the 21 st ACM/SIGIR Conference, pp. 2-10, 1998.

....roughly what the returned pages are about by reading their summaries, but the summaries often do not explain why these pages are returned. The reason for this deficiency is that these summaries are constructed at indexing time and do not take users queries into account. Tombros and Sanderson [22] have shown that the use of query biased summaries significantly improves both the accuracy and speed of user relevance judgements. MuST includes a multilingual text summarization engine, SUMMARIST [11,14] The goal of SUMMARIST is to create summaries of arbitrary text in English and other ....

Tombros, A. and Sanderson M. Advantages of Query Biased Summaries in Information Retrieval. In Proc. of the 21st ACM/SIGIR Conf., pp. 2-10, 1998.

....further: clearly if they never look at an item it will not be one of those ending up as a product of the session. This selection is based on surrogates: the short (often one line) descriptions of each item shown on the lists. Such lists can be tested alone with users using focused experiments (37) Future directions Future work will be characterised by attempts to explore basic tensions in direction. One is the tension between highly standardised workbench tests using precision and recall and no human users (fast and highly comparable with the work of others thus good for competitions, ....

TOMBROS, A., SANDERSON, M., AND GRAY, P. The advantages of querybiased summaries in Information Retrieval, Proceedings of AAAI98 Spring Symposium on Intelligent Text Summarization, to appear 1998. New IR - New Evaluation 14

....in order to improve the quality of summaries, we have to consider not only such information, but also other types of information available in the process of summarization of retrieved documents. The mainstream of methodology, which adopts a part of such information, is the querybiased summarization[10]. The method of summarization uses user s query to give weight to the words or phrases in the query. Although the method which lays emphasis on queries is very intuitive and works well, there are a drawback that it does not use the information derived from the set of retrieved documents, which is ....

....to be retrieved according to the relevance to the query. Both of those types of information are expected to be good clues in summarization. In this section, we consider incorporating those types of information into the process of term weighting. First choice is the query biased summarization[10]. This methodology is based on the intuition that the words or phrases in the query express users information needs directly, and summaries should include those expressions. Although it is very intuitive and works well, there are the following drawbacks: # Since the expressions in the query are ....

[Article contains additional citation context not shown here]

A. Tombros and M. Sanderson. Advantages of Query Biased Summaries in Information Retrieval. In Proceedings of the 21st Annual International ACM-SIGIR Conference on Research and Development in Information Retrieval, pages 2--10, 1998.

....paper , home page , discussion forum , news . These user defined categories do not necessary exist in existing search engines. Preliminary results also showed that annotations can be used to summarize the documents. Recent research in automatic document summarization (Lopez, 1999 ; Tombros, 1998) demonstrated the benefits of using query terms to produce personalized document summaries. Similarly, highlighted texts could be used to build user directed document summaries. Document summaries are important for information access and the simple concatenation of highlighted texts has proved to ....

A. Tombros, M. Sanderson. (1998). The advantages of query-biased summaries in Information Retrieval. In Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2-10, Melbourne, Australia

....summaries that are produced automatically and by hand. However, this evaluation method has been criticized because it assumes that there is only one correct summary. A taskbased evaluation scheme has been recently adopted as new way of evaluating summaries(Jing et al. 1998; Mani et al. 1998; Tombros and Sanderson, 1998). It evaluates the performance of a summarization system in a given task, such as information retrieval and text categorization. This paper compares ten different summarization methods based on information retrieval tasks. To evaluate the system performance, subjects speed and accuracy are ....

.... tf i log N df i for query terms, 4) where is a constant set to 3, based on the results of preliminary experiments, to produce summaries that are different from the ones produced by the generic term frequency method. This method is an earlier method for producing querybiased summaries(Tombros and Sanderson, 1998). 7) produce a generic summary by extracting sentences based on lexical chains (cf.idf) In this method, the importance of a sentence is calculated based on the importance of lexical chains in the sentence. Lexical chains(Morris and Hirst, 1991) are sequences of words that are in a lexical ....

Tombros, A. and M. Sanderson, 1998. Advantages of Query Biased Summaries in Information Retrieval. In Proc. of 21st Annual International ACM Special Interest Group on Information Retrieval Conference on Research and Development in Information Retrieval. pages 2--10.

....problem have been in the form of improved tools for search and retrieval [5] but it has also been shown to be bene cial to provide mechanisms through which users are supported in assessing for themselves the potential relevance of an interesting resource. Techniques such as sentence selection [7] and natural language generation [4] are being used to generate summaries of documents for information retrieval. However, they cannot present multimedia content nor information about the resource. An alternative is the use of rich metadata to describe a resource, i.e. separate information such as ....

....two stages. First, the user poses a query to a search engine. A long list of resources may be returned, perhaps with a title and some other summary information, and then the user must (somehow) choose a few of those resources to download. Summaries may usefully be tailored to the user s query [7], but the query is not the whole story. To help with selection we need to distinguish between the user s search criteria, which are expressed in the initial query, and the user s selection criteria, which are the means by which the user decides which of the resources to download. Users typically ....

[Article contains additional citation context not shown here]

Tombros, A. and Sanderson, M.: The Advantages of Query Biased Summaries in Information Retrieval. Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Melbourne, Australia, (1998) 2-10.

....of indication as to the content of an image. The second trend is the sentence based abstraction technique. This technique relies on repetitions of terms and phrases in the text and tries to extract the most salient sentences or key phrases and assemble them together ( 23] 27] 6] 18] 28] 8] [26]) This technique assumes that a summary does not have to be cohesive, but that it should represent as much information from the text as possible. There are many researchers studying this field, and some of them use heuristics such as preferring terms which appear in titles or headers, preferring ....

Tombros A., Sanderson M., & Gray P. (1998). Advantages of query biased summaries in information retrieval. In AAAI 98 Spring Symposium on Intelligent Text Summarization, pages 44-52.

....implementation of IVIRS is still in progress [4] A divide and conquer approach has been followed, consisting of dividing the implementation and experimentation of IVIRS in the parallel implementation and experimentation of different components. I have implemented and experimented with the DSS [29], the Text to Speech and Speech to Text modules of the VDM [28] and the DDS and I am currently developing a PIRS able to cope with the different forms of uncertainty involved in the retrieval task. 4 Issues Related to the Use of Spoken Queries in Information Retrieval One of the underlying ....

A. Tombros and M. Sanderson. Advantages of query biased summaries in Information Retrieval. In Proceedings of ACM SIGIR, pages 2--10, Melbourne, Australia, August 1998.

....3:79 87, 1991. Context Bib Related Track Check 67 [44] 1) Michael I. Jordan. Attractor dynamics and parallelism in a connectionist sequential machine. In Proceedings of the 1986 Cognitive Science Conference, pages 531 546. Lawrence Erlbaum, 1986. Context Bib Related Track Check 48 [28] (4) M.I. Jordan and D.E. Rumelhart. Forward models: Supervised learning with a distal teacher. Cognitive Science, 16:307 354, 1992. Details Context Bib Related Track Check [ section deleted. Self citations are not included in the graph or the main number of citations. michael w 2 ....

....Applications. New York: Springer Verlag. section deleted. Figure 2: Sample detail information for an article in the CiteSeer database. The document header, abstract, and citations can be seen, along with an active bibliography of related documents. shown to improve search efficiency [28, 29]. Tombros performed a user study that showed that users working with the query sensitive summaries had a higher success rate. The query sensitive summaries allowed the users to more accurately and rapidly determine the relevance of documents, and greatly reduced the need to refer to the full text ....

A. Tombros and M. Sanderson. Advantages of query biased summaries in information retrieval. In Proceedings of SIGIR 98, Melbourne, Australia, 1998.

....of three summarization systems. They found that different systems achieved their best performance at different lengths (compression ratios) They also found the same results for determining document relevance to a topic (one of the TIPSTER tasks) for query relevant summaries. Tombros and Sanderson [41] found that query relevant summaries significantly improved both the accuracy and speed of user relevance judgements over a static predefined summary composed of the title and first few sentences of retrieved relevant documents, whereas TIPSTER found a significant difference in relevance judgment ....

....for multiple languages, the above items are the principal foci of my proposed work. 4.1. 1 Passage Unit Choice Using the sentence as a unit may be suitable for single document summarization as demonstrated by my evaluation results as well as the results of TIPSTER and other evaluations [13,17,23,28,41], however, it is not clear what is the most appropriate unit for multi document summarization. Incorrect referents can quickly mislead readers when sentences with pronouns are strung together from multiple documents. Thus I will investigate whether multiple sentences that include the referent need ....

A. Tombros and M. Sanderson. Advantages of query biased summaries in information retrieval. In Proceedings of SIGIR-98, Melbourne, Australia, Aug. 1998.

....for interactive and automatic query expansion. 1. Introduction The main focus of Glasgow s Interactive Track study was to investigate the use of summaries in interactive searching. Our experiments used a form of the query biasing summarisation technique proposed by Tombros and Sanderson [TS98], to create short document summaries that are tailored to the user s query. These summaries highlight the main points of the document that pertain to the query. The summaries are based on highly matching sentences, allowing users to view the context in which query terms are used within the ....

....full text of documents [RSZ71] Query biased text summarisation is an emerging area of summarisation research that had not been addressed until recently. Tombros and Sanderson looked into the application of such methods in information retrieval, evaluating the indicative function of the summaries [TS98]. Their study showed that users were better able to identify relevant documents when using the summaries than when using the first few sentences of a document. Recently the TIPSTER funded SUMMAC project [MHKHOFCS98] provided a framework for the evaluation of different types of summarisation ....

[Article contains additional citation context not shown here]

A. Tombros and M. Sanderson. The advantages of query-biased summaries in Information Retrieval. Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. pp. 2 - 10. 1998.

....full text of documents (Rush et al. 1971) Query biased text summarisation is an emerging area of research that had not been addressed until recently. Tombros and Sanderson looked into the application of such methods in information retrieval, evaluating the indicative function of the summaries (Tombros Sanderson, 1998). Their study showed that users were better able to identify relevant documents when using the summaries than when using the first few sentences of a document. Recently, the TIPSTER funded SUMMAC project (Mani et al. 1998) provided a framework for the evaluation of different types of ....

....described in this paper has been developed by Tombros and Sanderson. The system is based on a number of sentence extraction methods (Paice, 1990) that utilise information both from the documents of the collection and from the queries used. A detailed description of the system can be found in (Tombros Sanderson, 1998); here we shall briefly describe the summary generation process. The document collection to be summarised comprised news articles of the Wall Street Journal taken from the TREC collection (Harman, 1996) Each individual document of the collection was passed through the summarisation system, and ....

[Article contains additional citation context not shown here]

Tombros, A., & Sanderson, M. (1998). Advantages of query biased summaries in information retrieval. In Proceedings of ACM SIGIR (pp. 2--10). Melbourne, Australia.

....to assess a set of documents and thus enter relevance feedback more quickly. In this paper we report on a set of experiments to investigate the use of summaries for interactive searching. Our experiments used a form of the query biasing summarisation technique proposed by Tombros and Sanderson [19], to create short document summaries that are tailored to the user s query. The summaries are based on highly matching sentences, allowing users to view the context in which query terms are used within the document. We hypothesised that this form of summarisation would allow users to filter out ....

....full text of documents [15] Query biased text summarisation is an emerging area of summarisation research that had not been addressed until recently. Tombros and Sanderson looked into the application of such methods in information retrieval, evaluating the indicative function of the summaries [19]. Their study showed that users were better able to identify relevant documents when using the summaries than when using the first few sentences of a document. The summaries generated by our system were indicative and query biased, aiming to provide users working on an interactive IR system with ....

[Article contains additional citation context not shown here]

A. Tombros and M. Sanderson. The advantages of query-biased summaries in Information Retrieval. Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. pp. 2 - 10. 1998.

....full text of documents (Rush et al. 1971) Query biased text summarisation is an emerging area of research that had not been addressed until recently. Tombros and Sanderson looked into the application of such methods in information retrieval, evaluating the indicative function of the summaries (Tombros Sanderson, 1998). Their study showed that users were better able to identify relevant documents when using the summaries than when using the first few sentences of a document. Recently the TIPSTER funded SUMMAC project (Mani et al. 1998) provided a framework for the evaluation of different types of summarisation ....

....described in this paper has been developed by Tombros and Sanderson. The system is based on a number of sentence extraction methods (Paice, 1990) that utilise information both from the documents of the collection and from the queries used. A detailed description of the system can be found in (Tombros Sanderson, 1998); here we shall briefly describe the summary generation process. The document collection to be summarised comprised news articles of the Wall Street Journal (WSJ) taken from the TREC collection (Harman, 1996) Each individual document of the collection was passed through the summarisation system, ....

[Article contains additional citation context not shown here]

Tombros, A. and Sanderson, M. (1998). Advantages of query biased summaries in information retrieval. In Proceedings of ACM SIGIR, pages 2-10, Melbourne, Australia.

....on the full text of documents [21] Query biased text summarisation is an emerging area of research that had not been addressed until recently. Tombros and Sanderson looked into the application of such methods in information retrieval, evaluating the indicative function of the summaries [24]. Their study showed that users were better able to identify relevant documents when using the summaries than when using the first few sentences of a document. Recently the TIPSTER funded SUMMAC project [15] provided a framework for the evaluation of different types of summarisation systems. As ....

....experiments described in this paper has been developed by Tombros and Sanderson. The system is based on a number of sentence extraction methods [19] that utilise information both from the documents of the collection and from the queries used. A detailed description of the system can be found in [24]; here we shall briefly describe the summary generation process. The document collection to be summarised comprised news articles of the Wall Street Journal (WSJ) taken from the TREC collection [11] Each individual document of the collection was passed through the summarisation system, and as a ....

[Article contains additional citation context not shown here]

A. Tombros and M. Sanderson. Advantages of query biased summaries in Information Retrieval. In Proceedings of ACM SIGIR, pages 2--10, Melbourne, Australia, August 1998.

No context found.

Anastasios Tombros and Mark Sanderson. 1998. Advantages of query biased summaries in information retrieval. In Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 2--10.

No context found.

Tombros, A., and Sanderson, M.: Advantages of query biased summaries in information retrieval. Proceedings of SIGIR'98, Melbourne, 3-10 (1998).

No context found.

A. Tombros and M. Sanderson. Advantages of query biased summaries in information retrieval. In Proc. SIGIR, pages 2--10. ACM Press, 1998.

No context found.

A. Tombros and M. Sanderson. The advantages of query-biased summaries in Information Retrieval Proceedings of the Twenty-First Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. pp. 2-10. Melbourne. 1998.

No context found.

Tombros, Anastasios, Mark Sanderson, 1998 Advantages of Query Biased Summaries in Information Retrieval, Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval , pp. 2.1.1-10.

No context found.

A. Tombros and M. Sanderson, "Advantages of query biased summaries in Information Retrieval ", in:Proceedings of ACM SIGIR, pp. 2--10, Melbourne, Australia, August 1998.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC