download and extract val_avg_bleu=68.1000-step_count=5.ckpt to src/verbalizer/graph2text/outputs/t5-base_13881/
cd src
python3 run_matcher.py
get error message
It uses the default dataset, I didn't include my own. This time it is not related to (missing or faulty) python packages I guess, but rather to problems in the code base itself. Do you have any ideas how to fix it? It would be great if you keep the issue open until it's fixed, I am interested in running it also after OAEI has finished.
Verbalizing: 0%| | 0/71 [00:00<?, ?item/s]
['translate Graph to English: <H> event <R> is parent of <T> scientificevent <H> scientificevent <R> is parent of <T> individualpresentation <H> individualpresentation <R> is parent of <T> contributedtalk <H> event <R> is parent of <T> socialevent <H> socialevent <R> is parent of <T> conferencetrip ']
ERROR VERBALISING translate Graph to English: <H> event <R> is parent of <T> scientificevent <H> scientificevent <R> is parent of <T> individualpresentation <H> individualpresentation <R> is parent of <T> contributedtalk <H> event <R> is parent of <T> socialevent <H> socialevent <R> is parent of <T> conferencetrip
Traceback (most recent call last):
File "...OntoMatch/src/run_matcher.py", line 362, in <module>
main()
File "...OntoMatch/src/run_matcher.py", line 223, in main
tripleVerbalizer.verbaliseFile(tripleFilePath, tripleVerbalizedFilePath)
File "...OntoMatch/src/verbalizer/tripleVerbalizer.py", line 33, in verbaliseFile
verbalised_text = verbalise(triples, verb_module)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "...OntoMatch/src/verbalizer/tripleVerbalizer.py", line 16, in verbalise
return verbModule.verbalise(ans)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "...OntoMatch/src/verbalizer/verbalisation_module.py", line 143, in verbalise
return self.verbalise_sentence(input)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "...OntoMatch/src/verbalizer/verbalisation_module.py", line 103, in verbalise_sentence
gen_output = self.__generate_verbalisations_from_inputs(inputs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "...OntoMatch/src/verbalizer/verbalisation_module.py", line 46, in __generate_verbalisations_from_inputs
gen_output = self.g2t_module.model.generate(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/username/.virtualenvs/ontomatch/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/Users/username/.virtualenvs/ontomatch/lib/python3.12/site-packages/transformers/generation/utils.py", line 1713, in generate
self._prepare_special_tokens(generation_config, kwargs_has_attention_mask, device=device)
File "/Users/username/.virtualenvs/ontomatch/lib/python3.12/site-packages/transformers/generation/utils.py", line 1556, in _prepare_special_tokens
raise ValueError(
ValueError: `decoder_start_token_id` or `bos_token_id` has to be defined for encoder-decoder generation.
I'm trying to execute ontomatch, but i fail.
Steps to reproduce:
It uses the default dataset, I didn't include my own. This time it is not related to (missing or faulty) python packages I guess, but rather to problems in the code base itself. Do you have any ideas how to fix it? It would be great if you keep the issue open until it's fixed, I am interested in running it also after OAEI has finished.