Relation Mention Extraction from Noisy Data with Hierarchical Reinforcement Learning
This addresses a problem for natural language processing applications by improving relation extraction from noisy data, though it is incremental as it builds on existing methods for handling noise.
The paper tackles relation mention extraction from noisy, distantly supervised sentences by proposing a hierarchical reinforcement learning model that denoises data and extracts mentions without explicit annotations, achieving effective results as shown in experiments.
In this paper we address a task of relation mention extraction from noisy data: extracting representative phrases for a particular relation from noisy sentences that are collected via distant supervision. Despite its significance and value in many downstream applications, this task is less studied on noisy data. The major challenges exists in 1) the lack of annotation on mention phrases, and more severely, 2) handling noisy sentences which do not express a relation at all. To address the two challenges, we formulate the task as a semi-Markov decision process and propose a novel hierarchical reinforcement learning model. Our model consists of a top-level sentence selector to remove noisy sentences, a low-level mention extractor to extract relation mentions, and a reward estimator to provide signals to guide data denoising and mention extraction without explicit annotations. Experimental results show that our model is effective to extract relation mentions from noisy data.