CERES: Pretraining of Graph-Conditioned Transformer for Semi-Structured Session Data

Rui Feng, Chen Luo, Qingyu Yin, Bing Yin, Tuo Zhao, Chao Zhang


Abstract
User sessions empower many search and recommendation tasks on a daily basis. Such session data are semi-structured, which encode heterogeneous relations between queries and products, and each item is described by the unstructured text. Despite recent advances in self-supervised learning for text or graphs, there lack of self-supervised learning models that can effectively capture both intra-item semantics and inter-item interactions for semi-structured sessions. To fill this gap, we propose CERES, a graph-based transformer model for semi-structured session data. CERES learns representations that capture both inter- and intra-item semantics with (1) a graph-conditioned masked language pretraining task that jointly learns from item text and item-item relations; and (2) a graph-conditioned transformer architecture that propagates inter-item contexts to item-level representations. We pretrained CERES using ~468 million Amazon sessions and find that CERES outperforms strong pretraining baselines by up to 9% in three session search and entity linking tasks.
Anthology ID:
2022.naacl-main.16
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
219–230
Language:
URL:
https://aclanthology.org/2022.naacl-main.16
DOI:
10.18653/v1/2022.naacl-main.16
Bibkey:
Cite (ACL):
Rui Feng, Chen Luo, Qingyu Yin, Bing Yin, Tuo Zhao, and Chao Zhang. 2022. CERES: Pretraining of Graph-Conditioned Transformer for Semi-Structured Session Data. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 219–230, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
CERES: Pretraining of Graph-Conditioned Transformer for Semi-Structured Session Data (Feng et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.16.pdf