Neural Models for Sequence Chunking

2017/01/15 by Feifei Zhai, Zhai, Feifei, Saloni Potdar +5 · 2 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1701.04027

openalex publication_date 2017/01/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Dependency-based Convolutional Neural Networks for Sentence Embedding
• Multi-Task Cross-Lingual Sequence Tagging from Scratch
• Encoder-decoder with Focus-mechanism for Sequence Labelling Based Spoken Language Understanding
• Convolutional Neural Networks for Sentence Classification
• Transition-Based Dependency Parsing with Stack Long Short-Term Memory
• Classifying Relations by Ranking with Convolutional Neural Networks
• Recurrent Neural Networks with External Memory for Language Understanding

Cited by

• GCDT: A Global Context Enhanced Deep Transition Architecture for Sequence Labeling
• Deep Cascade Multi-task Learning for Slot Filling in Online Shopping Assistant

Related

• Improving Neural Sequence Labelling Using Additional Linguistic Information
• Combining Discrete and Neural Features for Sequence Labeling
• The Emergence of Chunking Structures with Hierarchical RNN
• The Emergence of Chunking Structures with Hierarchical RNN
• Learning Better Internal Structure of Words for Sequence Labeling