Feature-Less End-to-End Nested Term Extraction
This work addresses domain-specific term extraction for researchers or practitioners, but it is incremental as it builds on existing ATE methods with a focus on nested structures and feature reduction.
The paper tackles the problem of automatic term extraction (ATE) by proposing a deep learning-based end-to-end method that supports nested term extraction without relying on extra features, achieving high recall and comparable precision on segmented raw text.
In this paper, we proposed a deep learning-based end-to-end method on the domain specified automatic term extraction (ATE), it considers possible term spans within a fixed length in the sentence and predicts them whether they can be conceptual terms. In comparison with current ATE methods, the model supports nested term extraction and does not crucially need extra (extracted) features. Results show that it can achieve high recall and a comparable precision on term extraction task with inputting segmented raw text.