Neural Models for Sequence Chunking
This addresses the need for more accurate chunking in NLU tasks like shallow parsing and semantic slot filling, representing an incremental improvement over existing DNN-based methods.
The paper tackles the problem of sequence chunking in natural language understanding by proposing neural models that treat chunks as complete units for labeling, achieving state-of-the-art performance on text chunking and slot filling tasks.
Many natural language understanding (NLU) tasks, such as shallow parsing (i.e., text chunking) and semantic slot filling, require the assignment of representative labels to the meaningful chunks in a sentence. Most of the current deep neural network (DNN) based methods consider these tasks as a sequence labeling problem, in which a word, rather than a chunk, is treated as the basic unit for labeling. These chunks are then inferred by the standard IOB (Inside-Outside-Beginning) labels. In this paper, we propose an alternative approach by investigating the use of DNN for sequence chunking, and propose three neural models so that each chunk can be treated as a complete unit for labeling. Experimental results show that the proposed neural sequence chunking models can achieve start-of-the-art performance on both the text chunking and slot filling tasks.