diff --git a/INSTALL b/INSTALL index 1e3e13464dcabca832b39d74b66abe50e8227fc6..f42a9ee8d0b8809d3f1e256ad16e2142a243f351 100644 --- a/INSTALL +++ b/INSTALL @@ -20,5 +20,9 @@ To use the trained model, issue the following (for more details please consult R iobber kpwr.ini -d model-kpwr04/ my_xces_input.xml -i xces -O ccl_chunked_output.xml +If there is need to recognise chunk syntactic heads model-kpwr04-H can be used: + +iobber kpwr.ini -d model-kpwr04+H/ my_xces_input.xml -i xces -O ccl_chunked_output.xml + NOTE: the kpwr.ini configuration assumes that the input is morphosyntactically tagged. diff --git a/README b/README index 2811d9e241733b58ed7a9c0e8d1974d96aa1aee2..6e6aa4e09158a4130f6e84cb66a308b62d720c9f 100644 --- a/README +++ b/README @@ -38,10 +38,11 @@ The kpwr.ini config (and its trained model -- model-kpwr04) defines two layers: * layer2 with phrases based on pred-arg structure: chunk_np, chunk_adjp and chunk_vp. +It is also possible to recognise chunks' syntactic heads using model-kpwr04-H -NOTE: the current version of iobber does not recognise chunks' syntactic heads. -Also, it is unable to recognise discontinuous chunks. Both types of information -may be included in ccl format and this is likely to be supported in the future. +NOTE: the current version of iobber is unable to recognise discontinuous chunks. +Both types of information may be included in ccl format and this is likely to be +supported in the future. If the input file contains annotations in channels other than those defined