Zhiping Zheng's research while affiliated with University of Michigan and other places
What is this page?
This page lists the scientific contributions of an author, who either does not have a ResearchGate profile, or has not yet added these contributions to their profile.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
Publications (5)
The web is now becoming one of the largest information and knowledge repositories. Many large scale search engines (Google,
Fast, Northern Light, etc.) have emerged to help users find information. In this paper, we study how we can effectively use
these existing search engines to mine the Web and discover the “correct” answers to factual natural la...
AnswerBus is an open-domain question answering system based on sentence level Web information retrieval. It accepts users' natural-language questions in English, German, French, Spanish, Italian and Portuguese and provides answers in English. Five search engines and directories are used to retrieve Web pages that are relevant to user questions. Fro...
Using formal information retrieval methods, International News Connection provides a centralized location on the Web that allows users to access constantly updated international news, through dynamic links to news stories from 14 different news sources. The links are updated every 15-20 minutes. The news stories are classified into seven regional c...
The web is now becoming one of the largest information and knowledge repositories. Many large scale search engines (Google, Fast, Northern Light, etc.) have emerged to help users find information. In this paper, we study how we can effectively use these existing search engines to mine the Web and discover the "correct" answers to factual natural la...
Citations
... Mining content from the Web to support human-computer interaction applications (e.g., question answering (Radev et al., 2001;Clarke et al., 2001;Yao et al., 2012), interactive question answering (Wong et al., 2011), conversational systems (Huang et al., 2007;Wu et al., 2008;Shibata et al., 2009)) has been investigated since the advent of the read-write Web. In particular, the practice of mining the Web to alleviate the bottleneck of conversational content acquisition is increasing in popularity. ...
![[object Object]](https://i1.rgstatic.net/ii/profile.image/272453729517594-1441969439814_Q64/John-Prager.jpg)
... On the other hand, the results lie behind than those systems using ranked retrieval. Radev et al. [2006] presents a method to learn building queries for Web search engines in order to retrieve relevant passages for QA. They define a set of query rewrite operations like REMOVE, DUPLICATE, etc. ...
... [17] Kwok, C.C.T has discussed about transformational grammar to perform syntactic modification. [9] Radev, be trained the most excellent query reformulations for their QA system. [10] Molla QA system translates question and answer sentence in to graph based logical form representation. [11] Stevenson et al used vector space model to learn the answer pattern and rank candidate answer. ...
... To develop collaborative Arabic QAS, the authors emphasized the significance of harnessing social media data and blogs and creating testbeds for QAS development. Zheng (2002) conducted a study in which analyzed and contrasted eleven quality assurance procedures. They compared Arabic QASs according to criteria such as domain, programming language, WordNet usage, ontology usage, linguistic resource usage, methodology, dataset source usage, answer form, question type, features, and experimental outcomes (Kurdi, Alkhaider & Alfaifi, 2014). ...
... The classification and retrieval of the large amount of news on the web has been a task that has attracted much research effort. There are some papers that worked on news classification such as [7], [8] and [9], and some others attempted to distribute the classification process. Few papers addressed non-English languages like [10] that is for Amharic language and there is no news classifier specialized for the Persian language. ...
