# DAG-based Long Short-Term Memory for Neural Word Segmentation

arXiv: https://arxiv.org/abs/1707.00248 · HTML: https://mlsanity.com/paper/1707.00248/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2017.

## Built on by (most cited first, 2 of 2)

- [pLSTM: parallelizable Linear Source Transition Mark networks](https://mlsanity.com/paper/2506.11997/) (2025)
- [An Effective Incorporating Heterogeneous Knowledge Curriculum Learning for Sequence Labeling](https://mlsanity.com/paper/2402.13534/) (2024)

## Abstract (arXiv)

Neural word segmentation has attracted more and more research interests for its ability to alleviate the effort of feature engineering and utilize the external resource by the pre-trained character or word embeddings. In this paper, we propose a new neural model to incorporate the word-level information for Chinese word segmentation. Unlike the previous word-based models, our model still adopts the framework of character-based sequence labeling, which has advantages on both effectiveness and efficiency at the inference stage. To utilize the word-level information, we also propose a new long short-term memory (LSTM) architecture over directed acyclic graph (DAG). Experimental results demonstrate that our model leads to better performances than the baseline models.