Scope resolution of predicted negation cues: A two-step neural network-based approach
This work addresses the challenge of handling imperfect cue information in negation resolution for natural language processing, but it is incremental as it builds on existing neural methods without achieving new SOTA results.
The study tackled the problem of negation scope resolution by testing a two-step neural network approach that uses a Bidirectional LSTM for cue detection, finding it unsuitable for detection but showing that models with only a recurrent layer are most robust to inaccurate cues.
Neural network-based methods are the state of the art in negation scope resolution. However, they often use the unrealistic assumption that cue information is completely accurate. Even if this assumption holds, there remains a dependency on engineered features from state-of-the-art machine learning methods. The current study adopted a two-step negation resolving apporach to assess whether a Bidirectional Long Short-Term Memory-based method can be used for cue detection as well, and how inaccurate cue predictions would affect the scope resolution performance. Results suggest that this method is not suitable for negation detection. Scope resolution performance is most robust against inaccurate information for models with a recurrent layer only, compared to extensions with a Conditional Random Fields layer or a post-processing algorithm. We advocate for more research into the application of deep learning on negation detection and the effect of imperfect information on scope resolution.