Recognizing Semantic Relations by Combining Transformers and Fully Connected Models

Dmitri Roussinov, Serge Sharoff, Nadezhda Puchnina


Abstract
Automatically recognizing an existing semantic relation (e.g. “is a”, “part of”, “property of”, “opposite of” etc.) between two words (phrases, concepts, etc.) is an important task affecting many NLP applications and has been subject of extensive experimentation and modeling. Current approaches to automatically telling if a relation exists between two given concepts X and Y can be grouped into two types: 1) those modeling word-paths connecting X and Y in text and 2) those modeling distributional properties of X and Y separately, not necessary in the proximity to each other. Here, we investigate how both types can be improved and combined. We suggest a distributional approach that is based on an attention-based transformer. We have also developed a novel word path model that combines useful properties of a convolutional network with a fully connected language model. While our transformer-based approach works better, both our models significantly outperform the state-of-the-art within their classes of approaches. We also demonstrate that combining the two approaches results in additional gains since they use somewhat different data sources.
Anthology ID:
2020.lrec-1.715
Volume:
Proceedings of the Twelfth Language Resources and Evaluation Conference
Month:
May
Year:
2020
Address:
Marseille, France
Editors:
Nicoletta Calzolari, Frédéric Béchet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Hélène Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
5838–5845
Language:
English
URL:
https://aclanthology.org/2020.lrec-1.715
DOI:
Bibkey:
Cite (ACL):
Dmitri Roussinov, Serge Sharoff, and Nadezhda Puchnina. 2020. Recognizing Semantic Relations by Combining Transformers and Fully Connected Models. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 5838–5845, Marseille, France. European Language Resources Association.
Cite (Informal):
Recognizing Semantic Relations by Combining Transformers and Fully Connected Models (Roussinov et al., LREC 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.lrec-1.715.pdf