dinner with Noah Goodman
Jul. 23rd, 2007 11:41 pm![[personal profile]](https://www.dreamwidth.org/img/silk/identity/user.png){kind=small}
guslHad dinner with Noah Goodman (who happens to know ![[livejournal.com profile]](https://www.dreamwidth.org/img/external/lj-userinfo.gif)
mrwright), at Le Pain Quotidien. We talked about the work he's done with Josh and Chris on inferring intentions by doing inverse planning... and how we might be able to extend this to pragmatics. It was a chill conversation, and we drifted into gossip.
He told me that Clark Glymour used to be a pig farmer. I went on Google, and sure enough:
this confirms it.
I explained the ICA idea to him on a napkin... finally I told him about the argument-mapping idea, and he sketched out a generative model of the DAG being flattened into linear text. It was based on an analogy with springs. He also suggested using anaphoras as clues for the edges between the boxes.
It's a huge bummer we don't have argument-map data.
mrwright), at Le Pain Quotidien. We talked about the work he's done with Josh and Chris on inferring intentions by doing inverse planning... and how we might be able to extend this to pragmatics. It was a chill conversation, and we drifted into gossip.He told me that Clark Glymour used to be a pig farmer. I went on Google, and sure enough:
this confirms it.
I explained the ICA idea to him on a napkin... finally I told him about the argument-mapping idea, and he sketched out a generative model of the DAG being flattened into linear text. It was based on an analogy with springs. He also suggested using anaphoras as clues for the edges between the boxes.
It's a huge bummer we don't have argument-map data.
![[identity profile]](https://www.dreamwidth.org/img/silk/identity/openid.png){kind=small}
(no subject)
Date: 2007-07-24 04:12 pm (UTC)