search

NJUNLP / GTS

Code and data for paper "Grid Tagging Scheme for Aspect-oriented Fine-grained Opinion Extraction". Aspect opinion pair datasets and aspect triplet datasets.
Apache License 2.0
85 stars 26 forks source link

predict.py #11

Closed issuesolver12 closed 3 years ago

issuesolver12 commented 3 years ago

If yes,How long will you take add predict.py for OPE and OTE tasks?

issuesolver12 commented 3 years ago

Do you plan to add predict.py file for existing implementation?

wuzhen247 commented 3 years ago

I am sorry temporarily not because of some ddls.

issuesolver12 commented 3 years ago

what about other contributors ,who can pitch in and complete the implementation?

wuzhen247 commented 3 years ago

There are no other code contributors.

issuesolver12 commented 3 years ago

can you guide me on how to predict pairs and triplets using this code implementation?

wuzhen247 commented 3 years ago

No problem. In fact, you can print line87, and the tuple "[al, ar, pl, pr]" denotes an aspect term-opinion term pair. In this pair, the "al", "ar" respectively represent the start and end positions of the aspect term in the original sentence, and "pl", "pr" respectively represent the start and end positions of a corresponding opinion term. So does line118.

wuzhen247 commented 3 years ago

The corresponding implementations in BiLSTM/CNN models are at line94 and line120. If you need further help, please feel free to contact me wuzhen247@gmail.com.

issuesolver12 commented 3 years ago

Sure, thnks for your inputs. Will sure work on it