Exploring Segment Representations for Neural Segmentation Models
Authors: Yijia Liu, Wanxiang Che, Jiang Guo, Bing Qin, Ting Liu
IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conduct extensive experiments on two typical segmentation tasks: named entity recognition (NER) and Chinese word segmentation (CWS). Experimental results show that our neural semi-CRF model benefits from representing the entire segment and achieves the stateof-the-art performance on CWS benchmark dataset and competitive results on the Co NLL03 dataset. |
| Researcher Affiliation | Academia | Yijia Liu, Wanxiang Che , Jiang Guo, Bing Qin, Ting Liu Research Center for Social Computing and Information Retrieval Harbin Institute of Technology, China {yjliu,car,jguo,qinb,tliu}@ir.hit.edu.cn |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | We release our code at https://github.com/Exp Results/segrep-for-nn-semicrf. |
| Open Datasets | Yes | For NER, we use the Co NLL03 dataset which is widely adopted for evaluating NER models performance. For CWS, we follow previous study and use three Simplified Chinese datasets: PKU and MSR from 2nd SIGHAN bakeoff and Chinese Treebank 6.0 (CTB6). |
| Dataset Splits | Yes | For the PKU and MSR datasets, last 10% of the training data are used as development data as [Pei et al., 2014] does. For CTB6 data, recommended data split is used. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., CPU/GPU models, memory, or cloud instance types) used for running the experiments. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers (e.g., Python 3.x, PyTorch 1.x) that would be needed for replication. |
| Experiment Setup | Yes | Throughout this paper, we use the same hyper-parameters for different experiments as listed in Table 1. Initial learning rate is set as 0 = 0.1 and updated as t = 0/(1 + 0.1t) on each epoch t. Best training iteration is determined by the evaluation score on development data. |