Difference between revisions of "N-Stage transfer"
Jump to navigation
Jump to search
Line 1: | Line 1: | ||
− | The idea of ''n-Stage transfer'' is to extend the <code>apertium-interchunk</code> so that it can output the same format as it inputs which would allow it to be called more than once, it would also be good to be able to "merge" chunks, for example <code>NP CC NP → NP</code> |
+ | The idea of '''n-Stage transfer''' is to extend the <code>apertium-interchunk</code> so that it can output the same format as it inputs which would allow it to be called more than once, it would also be good to be able to "merge" chunks, for example <code>NP CC NP → NP</code> |
This is something like the idea of cascaded finite-state chunking, as described by Abney (1995). |
This is something like the idea of cascaded finite-state chunking, as described by Abney (1995). |
Revision as of 06:47, 23 March 2009
The idea of n-Stage transfer is to extend the apertium-interchunk
so that it can output the same format as it inputs which would allow it to be called more than once, it would also be good to be able to "merge" chunks, for example NP CC NP → NP
This is something like the idea of cascaded finite-state chunking, as described by Abney (1995).
References
- Steven Abney. (1996) "Partial Parsing via Finite-State Cascades". J. of Natural Language Engineering, 2(4): 337-344.