Moderated by Stephen Muggleton.

Claude Sammut

Managing Context in a Conversational Agent

The article mentioned above has been submitted to the Electronic Transactions on Artificial Intelligence, and the present page contains the review discussion. Click here for more explanations and for the webpage of theauthor, Claude Sammut.

Overview of interactions

N:o Question Answer(s) Continued discussion
1 15.10  Anonymous Referee 1
2 15.10  Anonymous Referee 2

Q1. Anonymous Referee 1 (15.10):

Recommendation: The paper can eventually be accepted for ETAI. Another refereeing round is needed.

The paper is interesting in that it proposes a practical method for realizing conversation by providing context switching mechanism. However, since the mechanism is rather simple, there might be the case that it would not work in a realistic situation. Further experimental studies should be conducted and evaluation on that experiments should be added.

Q2. Anonymous Referee 2 (15.10):

This is an interesting paper that addresses managing information about the context of a conversation. It describes a system working in a real world setting which is of course inspiring.

However, I have two serious concerns:

1. How should a conversational agent be evaluated? This is important yet non-trivial and warrants at least a discussion, yet is not discussed. For instance, how can one have confidence on the spreading activation strategy when there is no explicit method of evaluation?

2. The paper states that there are a variety of mechanisms for representing and managing context. However, the paper doesn't mention any of these. Grounding in the literature would be helpful to understand the paper's contribution.

Also, the abstract should clearly state the contribution of the paper.


Background: Review Protocol Pages and the ETAI

This Review Protocol Page (RPP) is a part of the webpage structure for the Electronic Transactions on Artificial Intelligence, or ETAI. The ETAI is an electronic journal that uses the Internet medium not merely for distributing the articles, but also for a novel, two-stage review procedure. The first review phase is open and allows the peer community to ask questions to the author and to create a discussion about the contribution. The second phase - called refereeing in the ETAI - is like conventional journal refereeing except that the major part of the required feedback is supposed to have occurred already in the first, review phase.

The referees make a recommendation whether the article is to be accepted or declined, as usual. The article and the discussion remain on-line regardless of whether the article was accepted or not. Additional questions and discussion after the acceptance decision are welcomed.

The Review Protocol Page is used as a working structure for the entire reviewing process. During the first (review) phase it accumulates the successive debate contributions. If the referees make specific comments about the article in the refereeing phase, then those comments are posted on the RPP as well, but without indicating the identity of the referee. (In many cases the referees may return simply an " accept" or " decline" recommendation, namely if sufficient feedback has been obtained already in the review phase).