Neural Open Information Extraction
This work addresses error propagation in Open IE for NLP applications, representing an incremental advancement.
The paper tackles error propagation in conventional Open Information Extraction systems by proposing a neural approach that learns from a state-of-the-art system, resulting in significant performance improvements on a benchmark dataset while maintaining computational efficiency.
Conventional Open Information Extraction (Open IE) systems are usually built on hand-crafted patterns from other NLP tools such as syntactic parsing, yet they face problems of error propagation. In this paper, we propose a neural Open IE approach with an encoder-decoder framework. Distinct from existing methods, the neural Open IE approach learns highly confident arguments and relation tuples bootstrapped from a state-of-the-art Open IE system. An empirical study on a large benchmark dataset shows that the neural Open IE system significantly outperforms several baselines, while maintaining comparable computational efficiency.