Semantic Role Labeling with Pretrained Language Models for Known and Unknown Predicates

Daniil Larionov, Artem Shelmanov, Elena Chistova, Ivan Smirnov


Abstract
We build the first full pipeline for semantic role labelling of Russian texts. The pipeline implements predicate identification, argument extraction, argument classification (labeling), and global scoring via integer linear programming. We train supervised neural network models for argument classification using Russian semantically annotated corpus – FrameBank. However, we note that this resource provides annotations only to a very limited set of predicates. We combat the problem of annotation scarcity by introducing two models that rely on different sets of features: one for “known” predicates that are present in the training set and one for “unknown” predicates that are not. We show that the model for “unknown” predicates can alleviate the lack of annotation by using pretrained embeddings. We perform experiments with various types of embeddings including the ones generated by deep pretrained language models: word2vec, FastText, ELMo, BERT, and show that embeddings generated by deep pretrained language models are superior to classical shallow embeddings for argument classification of both “known” and “unknown” predicates.
Anthology ID:
R19-1073
Volume:
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)
Month:
September
Year:
2019
Address:
Varna, Bulgaria
Editors:
Ruslan Mitkov, Galia Angelova
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
619–628
Language:
URL:
https://aclanthology.org/R19-1073
DOI:
10.26615/978-954-452-056-4_073
Bibkey:
Cite (ACL):
Daniil Larionov, Artem Shelmanov, Elena Chistova, and Ivan Smirnov. 2019. Semantic Role Labeling with Pretrained Language Models for Known and Unknown Predicates. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), pages 619–628, Varna, Bulgaria. INCOMA Ltd..
Cite (Informal):
Semantic Role Labeling with Pretrained Language Models for Known and Unknown Predicates (Larionov et al., RANLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/R19-1073.pdf