eResponder: Electronic Question Responder

Carmel, David; Shtalhaim, Menachem; Soffer, Aya

doi:10.1007/10722620_16

Cited by 14 publications

(12 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Operating in a helpdesk environment, eResponder stores Q/A pairs that have previously been asked and answered; these pairs can be used to respond to user questions, or to assist customer service representatives in drafting new responses [6]. See [16] for a similar system and [15] for a variation that uses cluster-based retrieval.…”

Section: Question Answeringmentioning

confidence: 99%

Retrieving answers from frequently asked questions pages on the web

Jijkoun

Rijke

2005

Proceedings of the 14th ACM International Conference on Information and Knowledge Management

View full text Add to dashboard Cite

We address the task of answering natural language questions by using the large number of Frequently Asked Questions (FAQ) pages available on the web. The task involves three steps: (1) fetching FAQ pages from the web; (2) automatic extraction of question/answer (Q/A) pairs from the collected pages; and (3) answering users' questions by retrieving appropriate Q/A pairs. We discuss our solutions for each of the three tasks, and give detailed evaluation results on a collected corpus of about 3.6Gb of text data (293K pages, 2.8M Q/A pairs), with real users' questions sampled from a web search engine log. Specifically, we propose simple but effective methods for Q/A extraction and investigate task-specific retrieval models for answering questions. Our best model finds answers for 36% of the test questions in the top 20 results. Our overall conclusion is that FAQ pages on the web provide an excellent resource for addressing real users' information needs in a highly focused manner.

show abstract

Section: Question Answeringmentioning

confidence: 99%

Retrieving answers from frequently asked questions pages on the web

Jijkoun

Rijke

2005

Proceedings of the 14th ACM International Conference on Information and Knowledge Management

View full text Add to dashboard Cite

show abstract

“…The retrieval system eResponder [2] retrieves a list of request-response pairs and presents a ranked list of responses to the user. In contrast, our system can re-use a single representative response, or collate sentences from multiple responses to generate a single (possibly partial) response.…”

Section: Related Workmentioning

confidence: 99%

“…2 Our previous experiments show that a standard document retrieval approach, where a new request is matched in its entirety with previous requests or responses, is only successful in very few cases [4]. We posit that this is because (1) many requests raise multiple issues, and hence do not match well any one document; (2) the language variability in the requests is very high; and (3) as seen in Figure 1, the replies to many technical requests are largely non-technical, and hence do not match technical terms in the requests.…”

Section: Introductionmentioning

confidence: 97%

A corpus-based approach to help-desk response generation

Zukerman

Marom

2006

2006 International Conference on Computational Inteligence for Modelling Control and Automation and International Conference On

View full text Add to dashboard Cite

We are developing a corpus-based approach for the prediction of help-desk responses from features in customers' emails, where responses are represented at two levels of granularity: document and sentence. We present an automatic evaluation of the responses generated by our system, as well as a manual one involving human judges. The automatic evaluation involves textual comparisons between generated responses and responses composed by the help-desk operators. The results show that both levels of granularity produce good responses, addressing inquiries of different kinds. The human-based evaluation measures response informativeness, and confirms our conclusion that both levels of granularity produce useful responses.

show abstract

“…The retrieval system eResponder [8] retrieves a list of request-response pairs and presents a ranked list of responses to the user. In contrast, our system can re-use a single representative response, or collate sentences from multiple responses to generate a single (possibly partial) response.…”

Section: Related Researchmentioning

confidence: 99%

A Comparative Study of Information-Gathering Approaches for Answering Help-Desk Email Inquiries

Zukerman

Marom

2006

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. We present a comparative study of corpus-based methods for the automatic synthesis of email responses to help-desk requests. Our methods were developed by considering two operational dimensions: (1) information-gathering technique, and (2) granularity of the information. In particular, we investigate two techniques -retrieval and prediction -applied to information represented at two levels of granularity -sentence level and document level. We also developed a hybrid method that combines prediction with retrieval. Our results show that the different approaches are applicable in different situations, addressing a combined 72% of the requests with either complete or partial responses.

show abstract

eResponder: Electronic Question Responder

Cited by 14 publications

References 3 publications

Retrieving answers from frequently asked questions pages on the web

Retrieving answers from frequently asked questions pages on the web

A corpus-based approach to help-desk response generation

A Comparative Study of Information-Gathering Approaches for Answering Help-Desk Email Inquiries

Contact Info

Product

Resources

About