Sequence Labeling: A Practical Approach

August 12, 2018 · Entered Twilight · 🏛 arXiv.org

"Last commit was 7.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: LICENSE, README.md, annotate.py, convert, data, evaluate.py, logs, model, train.py, util

Authors Adnan Akhundov, Dietrich Trautmann, Georg Groh arXiv ID 1808.03926 Category cs.CL: Computation & Language Cross-listed cs.LG Citations 20 Venue arXiv.org Repository https://github.com/aakhundov/sequence-labeling ⭐ 6 Last Checked 1 month ago

Abstract

We take a practical approach to solving sequence labeling problem assuming unavailability of domain expertise and scarcity of informational and computational resources. To this end, we utilize a universal end-to-end Bi-LSTM-based neural sequence labeling model applicable to a wide range of NLP tasks and languages. The model combines morphological, semantic, and structural cues extracted from data to arrive at informed predictions. The model's performance is evaluated on eight benchmark datasets (covering three tasks: POS-tagging, NER, and Chunking, and four languages: English, German, Dutch, and Spanish). We observe state-of-the-art results on four of them: CoNLL-2012 (English NER), CoNLL-2002 (Dutch NER), GermEval 2014 (German NER), Tiger Corpus (German POS-tagging), and competitive performance on the rest.