(2005) used a Question Answer Database (known as QUAB) to support interactive question answering .

Question answering (e.g., Pasca and Harabagiu, 2001; Echihabi and Marcu, 2003; Voorhees, 2004; Metzler and Croft, 2005) relates to question search.

Question answering automatically extracts short answers for a relatively limited class of question types from document collections.

For classifying according to type, as discussed above, most automated query classification for web logs have been based on the topic of the query rather than on the intended result type, but the question answering literature has intensively investigated how to predict appropriate answer types.

The candidate answer types are often drawn from the types of questions that have appeared in the TREC Question Answering track (Voorhees, 2003).

These categories include answer types used in question answering research as well as (to better capture the diverse nature of web queries) several more general response types such as Advice and General Information.

Since our focus is on exploring the usability of the answer content, we do not perform retrieval by finding similar questions already answered (Jeon et al., 2005), i.e., our answer collection C contains only the site’s answers without the corresponding questions answered .

We compute th< Pointwise Mutual Information (PMI) and Chi squar< (X2) association measures between each question answer word pair in the query-log corpus.

The problem of Question Answering (QA) has received considerable attention in the past few years.