Towards Web-based mass argumentation in natural language

Citation: Wyner, Adam, Engers, Tom Van (2010) Towards Web-based mass argumentation in natural language.
Internet Archive Scholar (search for fulltext): Towards Web-based mass argumentation in natural language
Download: http://wyner.info/research/Papers/WynerVanEngersEKAW2010.pdf
Tagged: Computer Science (RSS) ACE (RSS), ACEWiki (RSS), controlled natural language (RSS), WWAW (RSS), deliberation (RSS), e-government (RSS), e-participation (RSS), online argumentation (RSS), argumentation mining (RSS), argumentation frameworks (RSS), argumentation (RSS), IMPACT Project (RSS)

Summary

This is based an extended draft, rather than the EKAW 2010 published poster with a similar title ("Web-based Mass Argumentation in Natural Language").

This paper envisions using ACEWiki to construct a consistent knowledge base incrementally, based on users' input and using the Pellet inference engine to test for consistency.

Example

It shares a running example--a recycling debate--with A framework for enriched, controlled on-line discussion forums for e-government policy-making, which introduced the objectives and presented a requirements analysis, and with From policy-making statements to first-order logic, which analyzed the natural language example to create a controlled language version in Attempo Controlled English (ACE). It draws from and extends the work of these papers.

The example, below, is derived from a BBC Have Your Say discussion ``Should people be paid to recycle?". They have derived the statements as follows:

(1) Every householder should pay tax for the garbage which the householder throws away. 
(2) No householder should pay tax for the garbage which the householder throws away. 
(3) Paying tax for garbage increases recycling. 
(4) Recycling more is good. 
(5) Paying tax for garbage is unfair. 
(6) Every householder should be charged equally. 
(7) Every householder who takes benefits does not recycle. 
(8) Every householder who does not take benefits pays for every householder who does take benefits. 
(9) Professor Resicke says that recycling reduces the need for new garbage dumps. 
(10) A reduction of the need for new garbage dumps is good. 
(11) Professor Resicke is not objective. 
(12) Professor Resicke owns a recycling company. 
(13) A person who owns a recycling company earns money from recycling. 
(14) Supermarkets create garbage. 
(15) Supermarkets should pay tax. 
(16) Supermarkets pass the taxes for the garbage to the consumer.

Argumentation Frameworks

The main objective of the paper is to draw maximal sets of consistent propositions from information entered in controlled natural language.

One limitation of ACEWiki is that it cannot accept inconsistent information; this work overcomes that limitation.

It presents an argumentation framework for the example recycling debate--a graph showing the relationships between the 16 sentences of the running example--in order to find the maximal set of consistent propositions, i.e. a possible policy.

Theoretical and Practical Relevance

Related papers are described in the author's blog post.

This paper describes an approach for overcoming the knowledge acquisition bottleneck, using controlled natural language. Unlike previous approaches to ACEWiki, they are able to accept inconsistent information while also finding the maximal sets of consistent propositions.

The authors argue that for important, high impact discussions, users will be willing to use controlled natural language, which they argue is easy to learn.