Design Challenges and Misconceptions in Neural Sequence Labeling
This work addresses inconsistencies in the literature for researchers and practitioners in natural language processing, though it is incremental as it focuses on analysis and clarification rather than introducing new methods.
The authors tackled the problem of inconsistent conclusions and design challenges in neural sequence labeling by reproducing twelve state-of-the-art models and conducting systematic comparisons on three benchmarks (NER, Chunking, and POS tagging), resulting in clarified misconceptions and practical conclusions for practitioners.
We investigate the design challenges of constructing effective and efficient neural sequence labeling systems, by reproducing twelve neural sequence labeling models, which include most of the state-of-the-art structures, and conduct a systematic model comparison on three benchmarks (i.e. NER, Chunking, and POS tagging). Misconceptions and inconsistent conclusions in existing literature are examined and clarified under statistical experiments. In the comparison and analysis process, we reach several practical conclusions which can be useful to practitioners.