Augmenting Document-level Relation Extraction with Efficient Multi-Supervision
This work addresses the challenge of handling low-information-density data for researchers in document-level relation extraction, though it is incremental as it builds on existing supervision methods.
The paper tackles the problem of efficiently using noisy distantly supervised data for document-level relation extraction by selecting informative documents and integrating multiple supervision sources, resulting in improved model performance and higher time efficiency compared to existing baselines.
Despite its popularity in sentence-level relation extraction, distantly supervised data is rarely utilized by existing work in document-level relation extraction due to its noisy nature and low information density. Among its current applications, distantly supervised data is mostly used as a whole for pertaining, which is of low time efficiency. To fill in the gap of efficient and robust utilization of distantly supervised training data, we propose Efficient Multi-Supervision for document-level relation extraction, in which we first select a subset of informative documents from the massive dataset by combining distant supervision with expert supervision, then train the model with Multi-Supervision Ranking Loss that integrates the knowledge from multiple sources of supervision to alleviate the effects of noise. The experiments demonstrate the effectiveness of our method in improving the model performance with higher time efficiency than existing baselines.