NNHetSeq is a Bi-LSTM CRF based package for heterogeneous sequence labelling tasks. The system can be used for POS tagging, Named Entity Recognition, and other sequence labelling tasks.
POS-tagging accuracies of CTB5 boosts from 94.24 to 95.53 aided by PD corpus.
- Download LibN3L library and compile it.
- Open CMakeLists.txt and change "../LibN3L/" into the directory of your LibN3L package.
- run stacking model a. run base model and preserve the parameters using corpus A as command in
run_base.sh. b. then, run stacking model as command in
run_stack.shusing corpus B, and initialize the stacking model with the base model parameters.
- run multi-view coupling model as command in
run_couple.shdirectly set two resources of corpora (corpus A and corpus B) and run it
- run integrated stacking and multi-view coupling model a. run base model and preserve the parameters using corpus A as command in
run_base.sh.. b. run integrated model using corpus A and corpus B as command in
run_couplestack.sh, and initialize the integrated model with the base model parameters.
- NN stacking model (and the integrated model) convergent faster than multi-view coupling model based on our observations.