Hammond, K., Burke, R., Martin, C., and Lytinen, S., "FAQ Finder: A case-based approach to knowledge navigation," Proceedings of the 11th Conference on Artificial Intelligence for Applications, Los Angeles, CA, pp. 80-86, 1995.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....for input using keypads and styluses (Section 4) and speech (Section 5) Section 6 discusses opportunities for better models of questions. 2 The corpus of questions We collected around 450,000 questions from various online sources logs of the Ask Jeeves and Excite search engines, FAQFinder [2], AnswerBus [3] and test questions from the TREC question answering track [4] from 1998 to 2001 and wrote scripts to correct common typos and spelling mistakes and to filter the corpus in the various ways in Table 1. After this massaging the corpus had 279,456 unique questions. Table 2 shows a ....

K. Hammond, R. Burke, C. Martin, and S. Lytinen. FAQ finder: A case-based approach to knowledge navigation. In Proceedings of the Eleventh Conference on Artificial Intelligence for Applications, pages 80-- 86, Los Alamitos, February 1995. IEEE Computer Society Press.

....information from unfamiliar resources. Some of the intelligent web agents have been developed to search for relevant information using characteristics of a particular domain (and possibly a user profile) to organize and interpret the discovered information. Agents such as Harvest [12] FAQ Finder [13], Information Manifold [14] OCCAM [15] and Parasite [16] rely either on prespecified domain specific information about particular types of documents, or on hard coded models of the information sources to retrieve and interpret documents. The Harvest system [12] relies on semistructured documents ....

....to improve its ability to extract information. For example, it knows how to find author and title information in Latex documents and how to strip position information from postscript files. Harvest neither discovers new documents nor learns new models of document structure. Similarly, FAQ Finder [13] extracts answers to frequently asked questions (FAQs) from FAQ files available on the web. ShopBot [17] and Internet Learning Agent (ILA) 18] attempt to interact with and learn the structure of unfamiliar information sources. ShopBot retrieves product information from a variety of vendor sites ....

K. Hammond, R. Burke, C. Martin, and S. Lytinen, "Faq-finder: A case based approach to knowledge navigation," presented at the Working Notes of AAAI Spring Symposium on Information Gathering From Heterogeneous Distributed Environments, Stanford, CA, 1995.

....information from unfamiliar resources. Some of the intelligent web agents have been developed to search for relevant information using characteristics of a particular domain (and possibly a user profile) to organize and interpret the discovered information. Agents such as Harvest [12] FAQ Finder [13], Information Manifold [14] OCCAM [15] and Parasite [16] rely either on pre specified domain specific information about particular types of documents, or on hard coded models of the information sources to retrieve and interpret documents. The Harvest system [12] relies on semi structured ....

....to improve its ability to extract information. For example, it knows how to find author and title information in Latex documents and how to strip position information from postscript files. Harvest neither discovers new documents nor learns new models of document structure. Similarly, FAQ Finder [13] extracts answers to frequently asked questions (FAQ s) from FAQ files available on the web. ShopBot [17] and ILA (Internet Learning Agent) 18] attempt to interact with and learn the structure of unfamiliar information sources. ShopBot retrieves product information from a variety of vendor sites ....

K. Hammond, R. Burke, C. Martin, and S. Lytinen, "Faq-finder: a case based approach to knowledge navigation," in Working Notes of AAAI Spring Symposium on Information Gathering from Heterogeneous Distributed Environments, 1995.

....harvest demobrokers.html) Harvest neither discovers new documents nor learns new models of document structure. However, Harvest easily handles new documents of a familiar type. FAQ Finder extracts answers to frequently asked questions (FAQ) from FAQ files available on the Web [6, 11]. Like Harvest, FAQ Finder relies on a model of document structure. A user poses a question in natural language and the text of the question is used to search the FAQ files for a matching question. FAQFinder then returns the answer associated with the matching question. Because of the ....

Hammond, K., Burke, R., Martin, C., and Lytinen, S. FAQ finder: A case-based approach to knowledge navigation. In Working Notes of the AAAI Spring Symposium: Information gathering from Heterogeneous, Distributed Enviornments, 1995, AAAI Press, Stanford University, pp. 69--73, To order a copy, contact sss@aaai.org.

....categories: Intelligent Search Agents Several intelligent Web agents have been developed that search for relevant information using characteristics of a particular domain (and possibly a user profile) to organize and interpret the discovered information. For example, agents such as FAQ Finder [14], Information Manifold [18] and OCCAM [19] rely either on pre specified and domain specific information about particular types of documents, or on hard coded models of the information sources to retrieve and interpret documents. Other agents, User option Clustering Modules Query Generator ....

K. Hammond, R. Burke, C. Martin, and S. Lytinen. FAQ-Finder: A case-based approach to knowledge navigation. In Working Notes of the AAAI Spring Symposium: Information Gathering from Heterogeneous, Distributed Environments. AAAI Press, 1995.

....subject. The documents vary significantly in both content and format. An e#cient and e#ective way to extract answers from FAQ documents will be a time saving tool for many computer users. There have been research projects for building tools to retrieve FAQ information, most notably the FAQ Finder (Hammond et al. 1995; Burke, Hammond, Kozlovsky 1996) and Auto FAQ (Whitehead 1994) Without manual preprocessing, each FAQ document is treated as a single piece of text indexed by keywords. Our experiments were designed to extract title and Q A information from HTML documents automatically so that each question ....

Hammond, K.; Burke, R.; Martin, C.; and Lytinen, S. 1995. Faq finder: A case-based approach to knowledge navigation. In AAAI Spring Symposium on Information Gathering in Heterogeneous, Distributed Environments, 69--73. AAAI.

....categories: Intelligent Search Agents Several intelligent Web agents have been developed that search for relevant information using characteristics of a particular domain (and possibly a user profile) to organize and interpret the discovered information. For example, agents such as FAQ Finder [HBML95] Information Manifold [KLSS95] and OCCAM [KW96] rely either on pre specified and domain specific information about particular types of documents, or on hard coded models of the information sources to retrieve and interpret documents. Other agents, such as ShopBot [DEW96] and ILA [PE95] attempt ....

K. Hammond, R. Burke, C. Martin, and S. Lytinen. FAQ-Finder: A case-based approach to knowledge navigation. In Working Notes of the AAAI Spring Symposium: Information Gathering from Heterogeneous, Distributed Environments. AAAI Press, 1995.

....The documents vary significantly in both content and format. An efficient and effective way to extract answers from FAQ documents will be a time saving tool for many computer users. There have been research projects for building tools to retrieve FAQ information, most notably the FAQ Finder (Hammond et al. 1995; Burke, Hammond, Kozlovsky 1996) and Auto FAQ (Whitehead 1994) Without manual preprocessing, each FAQ document is treated as a single piece of text indexed by keywords. Our experiments were designed to extract title and Q A information from HTML documents automatically so that each question ....

Hammond, K.; Burke, R.; Martin, C.; and Lytinen, S. 1995. Faq finder: A case-based approach to knowledge navigation. In AAAI Spring Symposium on Information Gathering in Heterogeneous, Distributed Environments, 69--73. AAAI.

.... Gathering included a large number of papers on diverse agents [10] Some of the agents focused on the Web as an information source; agents have been designed for filtering, browsing [2,13] and traversing the Web [1] as well as searching specific information on it (e.g. FAQ files for newsgroups [9]) and heterogeneous sources [17] Agents often reference domain dependent databases and utilize a complex logical or semantic domain model [17,11,6] For example, 6] describes a distributed purchasing agent that aids in location and pricing of products. An internal predicate logic repre1 ....

Kristian Hammond, Robin Burke, Charles Martin, and Steve Lytinen. FAQFinder: A case-based approach to knowledge navigation. In Craig Knoblock and Alon Levy, editors, Working Notes of the AAAI Spring Symposium Series on Information Gathering from Distributed, Heterogeneous Environments, Palo Alto, CA, 1995.

....it becomes greater. There are already a number of applications that aid the user. These include the WebWatcher at CMU[4] the LIRA system at Stanford[1] and the Webhunter and Letizia projects at the MIT Media Lab[6] The Softbot project at UW[2] and the FAQ Finder at the University of Chicago[3] both make use of Internet resources to answer natural language user queries. The large amounts of new data that appear daily on the Internet bring a number of challenges. This data cannot be easily processed by humans. Hence, relevance judgments, such as those provided in the Tipster ....

Burke R. Martin C. Hammond, K. and S. Lytinen. Faq finder: A case-based approach to knowledge navigation. In Proc. 1995 AAAI Spring Symp. on Information Gathering from Heterogeneous, Distributed Environments, Stanford, March 1995.

....categories: Intelligent Search Agents Several intelligent Web agents have been developed that search for relevant information using characteristics of a particular domain (and possibly a user profile) to organize and interpret the discovered information. For example, agents such as FAQ Finder [HBML95] Information Manifold [KLSS95] and OCCAM [KW96] rely either on pre specified and domain specific information about particular types of documents, or on hard coded models of the information sources to retrieve and interpret documents. Other agents, such as ShopBot [DEW96] and ILA [PE95] ....

K. Hammond, R. Burke, C. Martin, and S. Lytinen. FAQ-Finder: A case-based approach to knowledge navigation. In Working Notes of the AAAI Spring Symposium: Information Gathering from Heterogeneous, Distributed Environments. AAAI Press, 1995.

....Harvest neither discovers new documents nor learns new models of document structure. However, Harvest easily handles new documents of a familiar type. FAQ Finders extract answers to frequently asked questions (FAQs) from FAQ files available on the Web [6, 11]. Like Harvest, they rely on a model of document structure. People pose their question in natural language and the text of their question is used to search the FAQ files for a matching question; FAQ Finder then returns the answer associated with the matching question. Because of the ....

Kristen Hammond, Robin Burke, Charles Martin, and Steven Lytinen. FAQ finder: A case-based approach to knowledge navigation. In Working Notes of the AAAI Spring Symposium: Information Gathering from Heterogeneous, Distributed Environments, pages 69--73, Stanford University, 1995. AAAI Press. To order a copy, contact sss@aaai.org.

....context of the assisted browsing task [4] 19] in which the agent attempts to identify promising links by inferring the user s interests from her past browsing behavior. Attempts to process semi structured information have been in a very different context than ShopBot. For example, FAQ Finder [9] relies on the special format of FAQ files to map natural language queries to the appropriate answers. In terms of its task, BargainFinder [14] is the closest agent to ShopBot. But BargainFinder is hand coded for one product domain, whereas ShopBot is productindependent: it takes a description of ....

Kristen Hammond, Robin Burke, Charles Martin, and Steven Lytinen. FAQ finder: A casebased approach to knowledge navigation. In Working Notes of the AAAI Spring Symposium: Information Gathering from Heterogeneous, Distributed Environments, pp. 69--73, Stanford University, 1995. AAAI Press. To order a copy, contact sss@aaai.org.

....browsing task [4, 13] in which the agent attempts to identify promising links by inferring the user s interests from her past browsing behavior. Finally, there have been attempts to process semi structured information, but again in a very different context than ShopBot. For example, FAQ Finder [8] relies on the special format of FAQ files to map natural language queries to the appropriate answers. In contrast with ShopBot, virtually all learning agents (e.g. 15, 14, 6, 10] learn about their user s interests, instead of learning about the external resources they access. The key exception ....

Kristen Hammond, Robin Burke, Charles Martin, and Steven Lytinen. Faq finder: A casebased approach to knowledge navigation. In Working Notes of the AAAI Spring Symposium: Information Gathering from Heterogeneous, Distributed Environments, pages 69--73, Stanford University, 1995. AAAI Press. To order a copy, contact sss@aaai.org.

....The documents vary significantly in both content and format. An efficient and effective way to extract answers from FAQ documents will be a time saving tool for many computer users. There have been research projects for building tools to retrieve FAQ information, most notably the FAQ Finder [14, 3] and Auto FAQ [22] Without manual preprocessing, each FAQ document is treated as a single piece of text indexed by keywords. Our experiments were designed to extract title and Q A information from HTML documents automatically so that each question can be indexed and processed with a higher ....

K. Hammond, R. Burke, C. Martin, and S. Lytinen. Faq finder: A case-based approach to knowledge navigation. In AAAI Spring Symposium on Information Gathering in Heterogeneous, Distributed Environments, pages 69--73, Stanford University, 1995. AAAI, AAAI Press. file://cs.uchicago.edu/pub/users/burke/

....it becomes greater. There are already a number of applications that aid the user. These include the WebWatcher at CMU[1] the LIRA system at Stanford[2] and the Webhunter and Letizia projects at the MIT Media Lab[8] The Softbot project at UW[3] and the FAQ Finder at the University of Chicago[5] both make use of Internet resources to answer natural language user queries. The large amounts of new data that appear daily on the Internet bring a number of challenges. This data cannot be easily processed by humans. Hence, relevance judgments, such as those provided in the Tipster ....

K. Hammond, R. Burke, C. Martin, and S Lytinen. Faq finder: A case-based approach to knowledge navigation. In Proc. 1995 AAAI Spring Symp. on Information Gathering from Heterogeneous, Distributed Environments, Stanford, March 1995.

....placed into the following three categories: Intelligent Search Agents: Several intelligent Web agents have been developed that search for relevant information using domain characteristics and user profiles to organize and interpret the discovered information. Agents such as Harvest [6] FAQFinder [19], Information Manifold [27] OCCAM [30] and ParaSite [51] rely either on pre specified domain information about particular types of documents, or on hard coded models of the information sources to retrieve and interpret documents. Agents such as ShopBot [14] and ILA (Internet Learning Agent) 42] ....

K. Hammond, R. Burke, C. Martin, and S. Lytinen. Faq-finder: A case-based approach to knowledge navigation. In Working Notes of the AAAI Spring Symposium: Information Gathering from Heterogeneous, Distributed Environments. AAAI Press, 1995.

....et al. 1997) In order to facilitate the representation of textual cases in a way suitable for a case based reasoning system, another possible solution could be to help the user to identify the section of the text in which the information related to the indexing term is given. The FAQ Finder (Hammond et al. 1995) locates information within usenet FAQ files for answering their (natural language) questions. IR techniques are used to locate the appropriate file. Within that file, a parse of the user s question is matched semantically against the text sections, to find the information most closely related to ....

Hammond, K.; Burke, R.; Martin, C.; and Lytinen, S. 1995. FAQ-Finder - A Case-Based Approach to Knowledge Navigation. In Proceedings of the AAAI Spring Symposium on Machine Learning in Information Access.

....these services just manually categorize the resources, thus, the collected resources underlying these tools are very limited compared to the panoply of internet resources. ffl Special purpose agents were designed to help users find a specific type of information. An example is the FAQfinder [7] agent at the InfoLab of the University of Chicago, which is designed to match user questions to questions in the FAQ files. Another is DejaNews, it searches Usenet newsgroups, finding the topic you re interested in by a weighted search criteria that sorts the information based on the number of ....

....in information gathering and data mining. We want to continue the work in the following direction: ffl The possibility of a better document representation. The word association measurement is a promising way to improve the precision of measurement of document similarity. Our previous on FAQfinder[7] has exploited the possible use of WordNet in query expansion which proved to be a good direction. ffl The possibility of application of guided machine learning techniques. Data clustering is an unguided machine learning technique, we will exploit the possible application of other methods. We ....

Kristian Hammond et al. Faqfinder: A case-based approach to knowledge navigation. In Craig Knoblock and Alon Levy, editors, Working note of the AAAI Spring Symposium Series on Information Gathering from Distributed, Heterogenous Environment, 1995.

....of a document and the structural organization of information in a document interchangeably. Our approach to document processing emerged from the ongoing research on FAQ Finder [1] a question answering system whose main source of knowledge is the files of Frequently Asked Questions (FAQs) [2]. Given a question, FAQ Finder narrows the search down to a small set of FAQs and then matches the question against the Q A pairs in the top ranked FAQ or in the FAQ selected by the user. A small list of Q A pairs is returned to the user as a result. When we started working on the ....

....FAQ Minder has four types of constraints. Each constraint is defined with respect to one of the three types of marker sequences. For lack of space, we give one example per constraint type: Recursion Constraints: Alphanumeric sequences do not recurse. e.g. seq1 [1] text . seq1 [2] . text . seq1 [3] text . text . seq2 [1] text . 2 We use the terms markers and marker sequences to refer to orthographic markers and orthographic marker sequences. The recursion constraint forces the second [1] marker to start a new ....

[Article contains additional citation context not shown here]

Hammond, K.J.; Burke, R., Martin, C., and Lytinen, S. (1995). FAQ Finder: A Case-Based Approach to Knowledge Navigation. In AAAI Symposium on Information 4 Two strings are similar if they satisfy the subset relation after being stoplisted. Gathering in Heterogeneous, Distributed Environments. AAAI. March 1995. Stanford University.

No context found.

Hammond, K., Burke, R., Martin, C., and Lytinen, S., "FAQ Finder: A case-based approach to knowledge navigation," Proceedings of the 11th Conference on Artificial Intelligence for Applications, Los Angeles, CA, pp. 80-86, 1995.

No context found.

Hammond, K.J.; Burke, R., Martin, C., and Lytinen, Stephen (1995). FAQ Finder: A Case-Based Approach to Knowledge Navigation. In AAAI Symposium on Information Gathering in Heterogeneous, Distributed Environments. AAAI. March 1995. Stanford University.

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