Moderated by Stephen Muggleton.

Ikuo Kobayashi, Koichi Furukawa, Tomonobu Ozaki, and Mutsumi Imai

A Computational Model for Children's Language Acquisition using Inductive Logic Programming

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 theauthors: Ikuo Kobayashi, Koichi Furukawa, Tomonobu Ozaki, and Mutsumi Imai.

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):

This is an extremely interesting paper, but gaps need to be filled. The most obvious is that it is not clear which elements of the proposed system have been implemented, and which have not. Also, I am not clear about the results of the virtual experiment. The constraints chosen look promising. But are they implemented and how successful are they in practice? i.e., should this paper be seen primarily as a proposal for work to be done in the future, rather than a reprt on completed work? This should be clarified before publication.

Additionally, there would be considerable interest in having a short overview at the beginning of the paper covering what is currently known about real children's early language development

There are various small points of criticism: this paper should have a wider readership than the AI community. Therefore AI terms (e.g. Cognitive bias) could usefully be explained.

The Category for this paper must be C (publication after major revisions). It must be stressed that it is potentially of great interest.

Q2. Anonymous Referee 2 (15.10):

The paper describes a method for concept acquisition that uses ILP and is based on some facts about concept acquisition in children. The method is exemplified with learning a fork/spoon distinction and a cat/dog distinction.

I have a concern about the use of festures that are crisp valued (no "fuzziness is admitted") and that are assumed as given by a previous perception phase. It would seem that distinctions such as those in the two examples must rely heavily on the direct matching on shapes and/or on the use of graded features.

I am also concerned about the small number of examples, the extreme simplicity of the examples and the lack of comparison with how other methods would handle the same examples.

All considered, I recommend that the article should be returned to the authors with a recommendation to re-submit a revised and extended article that may take these comments into account.


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).