{"ID":2856057,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.10936","arxiv_id":"2510.10936","title":"End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF: A Reproducibility Study","abstract":"We present a reproducibility study of the state-of-the-art neural architecture for sequence labeling proposed by Ma and Hovy (2016)\\cite{ma2016end}. The original BiLSTM-CNN-CRF model combines character-level representations via Convolutional Neural Networks (CNNs), word-level context modeling through Bi-directional Long Short-Term Memory networks (BiLSTMs), and structured prediction using Conditional Random Fields (CRFs). This end-to-end approach eliminates the need for hand-crafted features while achieving excellent performance on named entity recognition (NER) and part-of-speech (POS) tagging tasks. Our implementation successfully reproduces the key results, achieving 91.18\\% F1-score on CoNLL-2003 NER and demonstrating the model's effectiveness across sequence labeling tasks. We provide a detailed analysis of the architecture components and release an open-source PyTorch implementation to facilitate further research.","short_abstract":"We present a reproducibility study of the state-of-the-art neural architecture for sequence labeling proposed by Ma and Hovy (2016)\\cite{ma2016end}. The original BiLSTM-CNN-CRF model combines character-level representations via Convolutional Neural Networks (CNNs), word-level context modeling through Bi-directional Lon...","url_abs":"https://arxiv.org/abs/2510.10936","url_pdf":"https://arxiv.org/pdf/2510.10936v1","authors":"[\"Anirudh Ganesh\",\"Jayavardhan Reddy\"]","published":"2025-10-13T02:49:21Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.LG\"]","methods":"[\"Convolutional Neural Network\"]","has_code":false}