50 papers with code • 4 benchmarks • 3 datasets
Chunking, also known as shallow parsing, identifies continuous spans of tokens that form syntactic units such as noun phrases or verb phrases.
Selecting optimal parameters for a neural network architecture can often make the difference between mediocre and state-of-the-art performance.
We propose a sequence labeling framework with a secondary training objective, learning to predict surrounding words for every word in the dataset.
Transfer and multi-task learning have traditionally focused on either a single source-target pair or very few, similar tasks.
Pre-trained word embeddings learned from unlabeled text have become a standard component of neural network architectures for NLP tasks.
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).
Open-domain KeyPhrase Extraction (KPE) aims to extract keyphrases from documents without domain or quality restrictions, e. g., web pages with variant domains and qualities.