Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings

Malte Ostendorff, Nils Rethmeier, Isabelle Augenstein, Bela Gipp, Georg Rehm


Abstract
Learning scientific document representations can be substantially improved through contrastive learning objectives, where the challenge lies in creating positive and negative training samples that encode the desired similarity semantics. Prior work relies on discrete citation relations to generate contrast samples. However, discrete citations enforce a hard cut-off to similarity. This is counter-intuitive to similarity-based learning and ignores that scientific papers can be very similar despite lacking a direct citation - a core problem of finding related research. Instead, we use controlled nearest neighbor sampling over citation graph embeddings for contrastive learning. This control allows us to learn continuous similarity, to sample hard-to-learn negatives and positives, and also to avoid collisions between negative and positive samples by controlling the sampling margin between them. The resulting method SciNCL outperforms the state-of-the-art on the SciDocs benchmark. Furthermore, we demonstrate that it can train (or tune) language models sample-efficiently and that it can be combined with recent training-efficient methods. Perhaps surprisingly, even training a general-domain language model this way outperforms baselines pretrained in-domain.
Anthology ID:
2022.emnlp-main.802
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11670–11688
Language:
URL:
https://aclanthology.org/2022.emnlp-main.802
DOI:
10.18653/v1/2022.emnlp-main.802
Bibkey:
Cite (ACL):
Malte Ostendorff, Nils Rethmeier, Isabelle Augenstein, Bela Gipp, and Georg Rehm. 2022. Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 11670–11688, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings (Ostendorff et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.802.pdf
Software:
 2022.emnlp-main.802.software.zip