From phm@xxx.xxx Tue Dec 1 05:16:21 1998 X-Digest-Num: 21 Message-ID: <44114.21.87.959273823@eGroups.com> Date: Tue, 1 Dec 1998 14:16:21 +0100 (CET) From: PILCH Hartmut >Could a Lojban parser output intelligible English some day? > > No doubt an approach similar to whjat you describe of converting parse to > Prolog to Lisp to English would be more effective than what Nora is > doing, but Nora's solution is easy (if she only had time to work on it) I would find time to work on a lojlisp2english program. Also, I suspect it's more easy to do than what Nora seems to be attempting, if only I have a Lisp representation of the parsing result available. > A good glosser is a useful learning tool. A good translator would also be > good. But the main thing needed to make either very useful is some kind > of AI based error correction - something that couild look at a bad parse and > figure out what was likely to be wrong (a missing "cu", two selbri in the > bridi, etc.) and perhaps even suggest the corrections. That again is a very difficult tenth step The first step is done (John Cowan's parser). I only need a commandline switch that will output the parsing result in Lisp (foo bar baz) notation. The second step is a lojlisp2english converter that will allow people to read existing correctly written lojban texts in [Logician's] English and, by comparing with the original and the lojlisp version, understand the original structure without having to look up every word. -- Hartmut Pilch http://www.a2e.de/phm/