Neural Models for Sequence Chunking


  • Feifei Zhai IBM Watson
  • Saloni Potdar IBM Watson
  • Bing Xiang IBM Watson
  • Bowen Zhou IBM Watson



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.




How to Cite

Zhai, F., Potdar, S., Xiang, B., & Zhou, B. (2017). Neural Models for Sequence Chunking. Proceedings of the AAAI Conference on Artificial Intelligence, 31(1).