GRAPHCACHE: Message Passing as Caching for Sentence-Level Relation Extraction
Yiwei Wang, Muhao Chen, Wenxuan Zhou, Yujun Cai, Yuxuan Liang, Bryan, Hooi

TL;DR
GRAPHCACHE introduces a graph neural network module that propagates dataset-level features across sentences to enhance sentence-level relation extraction, improving performance by leveraging global prior knowledge.
Contribution
The paper proposes GRAPHCACHE, a novel dataset-level feature propagation method using message passing, to enrich sentence representations for relation extraction.
Findings
Significant performance improvements on RE tasks.
Effective global feature aggregation across datasets.
Efficient online updating of property representations.
Abstract
Entity types and textual context are essential properties for sentence-level relation extraction (RE). Existing work only encodes these properties within individual instances, which limits the performance of RE given the insufficient features in a single sentence. In contrast, we model these properties from the whole dataset and use the dataset-level information to enrich the semantics of every instance. We propose the GRAPHCACHE (Graph Neural Network as Caching) module, that propagates the features across sentences to learn better representations for RE. GRAPHCACHE aggregates the features from sentences in the whole dataset to learn global representations of properties, and use them to augment the local features within individual sentences. The global property features act as dataset-level prior knowledge for RE, and a complement to the sentence-level features. Inspired by the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Natural Language Processing Techniques · Text Readability and Simplification
