Experiment on Combining Sources of Evidence for Passage Retrieval
نویسندگان
چکیده
Passage retrieval consists in identifying short but informative runs of a long text, given a specific user query. We discuss the sources of evidence that help choosing likely high-quality passages, such as relevance to the user query and self-containedness. These measures are different from the traditional information retrieval procedure due to the use of the context of the passage.
منابع مشابه
Enhancing Relevance Models with Adaptive Passage Retrieval
Passage retrieval and pseudo relevance feedback/query expansion have been reported as two effective means for improving document retrieval in literature. Relevance models, while improving retrieval in most cases, hurts performance on some heterogeneous collections. Previous research has shown that combining passage-level evidence with pseudo relevance feedback brings added benefits. In this pap...
متن کاملBoosting Passage Retrieval through Reuse in Question Answering
Question Answering (QA) is an emerging important field in Information Retrieval. In a QA system the archive of previous questions asked from the system makes a collection full of useful factual nuggets. This paper makes an initial attempt to investigate the reuse of facts contained in the archive of previous questions to help and gain performance in answering future related factoid questions. I...
متن کاملImproving a Basic Retrieval Method by Linksand Passage Level
A conventional text retrieval method is improved by two additional sources of evidence of relevance: rst, by a passage retrieval method that is based on Hidden Markov Models and second, by a so-called link method which was originally developed for hypertext retrieval. The results show that the two additional sources of evidence improve a conventional vector space retrieval method both in a cons...
متن کاملCombining Evidence from Homologous Datasets
With Machine Translation and/or Automatic Speech Recognition, there can be different versions of the same data with distinct expressions. We argue that combining evidence from these “homologous” datasets can give us better representation of the original data, and our experiments show that a model combining all sources outperforms each individual dataset in retrieval.
متن کاملPassage-level Evidence for Cross-Language Information Retrieval
Machine translation (MT) techniques can be used to generate a query in a target language from a query in a source language for the cross-language information retrieval (CLIR). Recent MT systems have advanced enough to generate translations which are human-readable, However, translation error is still a serious impediment which hurts the effectiveness of a CLIR system. To compensate for defects ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2005