A Unified Encoder-Decoder Framework with Entity Memory

Zhihan Zhang, Wenhao Yu, Chenguang Zhu, Meng Jiang


Abstract
Entities, as important carriers of real-world knowledge, play a key role in many NLP tasks.We focus on incorporating entity knowledge into an encoder-decoder framework for informative text generation. Existing approaches tried to index, retrieve, and read external documents as evidence, but they suffered from a large computational overhead. In this work, we propose an encoder-decoder framework with an entity memory, namely EDMem. The entity knowledge is stored in the memory as latent representations, and the memory is pre-trained on Wikipedia along with encoder-decoder parameters. To precisely generate entity names, we design three decoding methods to constrain entity generation by linking entities in the memory. EDMem is a unified framework that can be used on various entity-intensive question answering and generation tasks. Extensive experimental results show that EDMem outperforms both memory-based auto-encoder models and non-memory encoder-decoder models.
Anthology ID:
2022.emnlp-main.43
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
689–705
Language:
URL:
https://aclanthology.org/2022.emnlp-main.43
DOI:
Bibkey:
Cite (ACL):
Zhihan Zhang, Wenhao Yu, Chenguang Zhu, and Meng Jiang. 2022. A Unified Encoder-Decoder Framework with Entity Memory. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 689–705, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
A Unified Encoder-Decoder Framework with Entity Memory (Zhang et al., EMNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.emnlp-main.43.pdf