York University at TREC 2006: Enterprise Email Discussion Search

نویسندگان

  • Yu Fan
  • Xiangji Huang
  • Aijun An
چکیده

We use the Okapi retrieval system to conduct the email discussion search. The following issues are investigated. First, we make use of the thread structure in the emails to re-rank the documents retrieved by Okapi. We would like to see whether such post-processing of the retrieval result can boost the retrieval performance. Second, in terms of query formulation, we investigate whether the use of only title in a topic achieves better or worse results than the inclusion of other fields such as description and narrative. Third, we investigate whether stemming and stop word removal play an important role in the email search. Our conclusion includes that (1) re-ranking documents using a straightforward method that considers the thread structure can make a small improvement to the retrieval performance, (2) formulating the query using all the fields in a topic achieves the best result, and (3) the use of stemming and stop word removal can improve the performance, but the degree of improvement depends on the stemming method and the stop word list used.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

UMass at TREC 2006: Enterprise Track

This paper gives an overview of the work done at the University of Massachusetts, Amherst for the TREC 2006 Enterprise track. For the discussion search task, we compare two methods for incorporating thread evidence into the language models of email messages. For the expert finding task, we create implicit expert representations as mixtures of language models from associated documents.

متن کامل

The University of Amsterdam at the TREC 2006 Enterprise Track

We describe our participation in the TREC 2006 Enterprise track. We provide a detailed account of the ideas underlying our language modeling approaches to both the discussion search and expert search tasks. For discussion search, our focus was on query expansion techniques, using additional information from the topic statement and from message threads; while the former was generally helpful, th...

متن کامل

York University at TREC 2007: Enterprise Document Search

York University evaluated a prepcessing approach for this year’s enterprise document search task. With different parsing tools, we create two data sets. Based on each data set, we generate two official runs. Their results demonstrate that the removal of raw data in preprocessing stage has a negative impact on the retrieval performance.

متن کامل

Overview of the TREC 2006 Enterprise Track

The goal of the enterprise track is to conduct experiments with enterprise data — intranet pages, email archives, document repositories — that reflect the experiences of users in real organizations, such that for example, an email ranking technique that is effective here would be a good choice for deployment in a real multi-user email search application. This involves both understanding user ne...

متن کامل

In Enterprise Search: Methods to Identify Argumentative Discussions and to Find Topical Experts

Our intention in taking part in this year’s Enterprise Track is to experiment with various re-ranking approaches in solving two problems: email search and expert search. In email discussion search, we propose methods to retrieve email messages that contain pro/con argument about the topic in discussion. We compute the likelihood of an email having a pro/con argument about the topic and re-rank ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2006