Partially-supervised Mention Detection
This work addresses entity mention detection for NLP tasks, but it is incremental as it builds on existing methods for handling partial annotations.
The paper tackled the problem of entity mention detection with partially annotated data by proposing weighted loss and soft-target classification approaches, along with neural sequence tagging and exhaustive search methods, and showed that all methods improved recall and F1 scores when evaluated with coreference resolution using multitask learning.
Learning to detect entity mentions without using syntactic information can be useful for integration and joint optimization with other tasks. However, it is common to have partially annotated data for this problem. Here, we investigate two approaches to deal with partial annotation of mentions: weighted loss and soft-target classification. We also propose two neural mention detection approaches: a sequence tagging, and an exhaustive search. We evaluate our methods with coreference resolution as a downstream task, using multitask learning. The results show that the recall and F1 score improve for all methods.