Context-Aware Representations for Knowledge Base Relation Extraction
We demonstrate that for sentence-level relation extraction it is beneficial to consider other relations in the sentential context while predicting the target relation. Our architecture uses an LSTM-based encoder to jointly learn representations for all relations in a single sentence. We combine the context representations with an attention mechanism to make the final prediction. We use the Wikidata knowledge base to construct a dataset of multiple relations per sentence and to evaluate our approach. Compared to a baseline system, our method results in an average error reduction of 24 on a held-out set of relations. The code and the dataset to replicate the experiments are made available at \url{https://github.com/ukplab/}.
PDF AbstractCode
Datasets
Results from the Paper
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Relation Extraction | Wikipedia-Wikidata relations | ContextAtt | Error rate | 0.1590 | # 1 |
