Text Summarization as Tree Transduction by Top-Down TreeLSTM
This work addresses the problem of extractive compression for natural language processing, offering a novel approach that improves performance on specific benchmarks.
The paper tackled extractive compression by formulating it as a parse tree transduction problem instead of sequence transduction, and introduced a deep neural model based on TreeLSTM that achieved state-of-the-art performance on sentence compression benchmarks in accuracy and compression rate.
Extractive compression is a challenging natural language processing problem. This work contributes by formulating neural extractive compression as a parse tree transduction problem, rather than a sequence transduction task. Motivated by this, we introduce a deep neural model for learning structure-to-substructure tree transductions by extending the standard Long Short-Term Memory, considering the parent-child relationships in the structural recursion. The proposed model can achieve state of the art performance on sentence compression benchmarks, both in terms of accuracy and compression rate.