Chunking
Chunking, also known as shallow parsing, identifies continuous spans of tokens that form syntactic units such as noun phrases or verb phrases.
Example:
| Vinken | , | 61 | years | old |
|---|---|---|---|---|
| B-NLP | I-NP | I-NP | I-NP | I-NP |
State-of-the-art leaderboards
| Trend | Dataset | Best Method | Paper title | Paper | Code | Compare |
|---|---|---|---|---|---|---|
|
Greatest papers with code
Semi-supervised sequence tagging with bidirectional language models
ACL 2017
• zalandoresearch/flair
• 
Pre-trained word embeddings learned from unlabeled text have become a standard component of neural network architectures for NLP tasks. However, in most cases, the recurrent network that operates on word-level representations to produce context sensitive representations is trained on relatively little labeled data.
#7 best model for
Named Entity Recognition on CoNLL 2003 (English)
NCRF++: An Open-source Neural Sequence Labeling Toolkit
This paper describes NCRF++, a toolkit for neural sequence labeling. NCRF++ is designed for quick implementation of different neural sequence labeling models with a CRF inference layer.
#5 best model for
Chunking on Penn Treebank
Design Challenges and Misconceptions in Neural Sequence Labeling
COLING 2018
• jiesutd/NCRFpp
•
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). Misconceptions and inconsistent conclusions in existing literature are examined and clarified under statistical experiments.
Optimal Hyperparameters for Deep LSTM-Networks for Sequence Labeling Tasks
• jiesutd/NCRFpp
•
Selecting optimal parameters for a neural network architecture can often make the difference between mediocre and state-of-the-art performance. However, little is published which parameters and design choices should be evaluated or selected making the correct hyperparameter optimization often a "black art that requires expert experiences" (Snoek et al., 2012).
Natural Language Processing (almost) from Scratch
We propose a unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including: part-of-speech tagging, chunking, named entity recognition, and semantic role labeling. This versatility is achieved by trying to avoid task-specific engineering and therefore disregarding a lot of prior knowledge.
CHUNKING NAMED ENTITY RECOGNITION PART-OF-SPEECH TAGGING SEMANTIC ROLE LABELING
Semi-supervised Multitask Learning for Sequence Labeling
ACL 2017
• marekrei/sequence-labeler
• 
We propose a sequence labeling framework with a secondary training objective, learning to predict surrounding words for every word in the dataset. This language modeling objective incentivises the system to learn general-purpose patterns of semantic and syntactic composition, which are also useful for improving accuracy on different sequence labeling tasks.
#3 best model for
Grammatical Error Detection on FCE
CHUNKING GRAMMATICAL ERROR DETECTION LANGUAGE MODELLING NAMED ENTITY RECOGNITION PART-OF-SPEECH TAGGING
Substitute Based SCODE Word Embeddings in Supervised NLP Tasks
The results show that the proposed method achieves as good as or better results compared to the other word embeddings in the tasks we investigate. It achieves state-of-the-art results in multilingual dependency parsing.
CHUNKING DEPENDENCY PARSING NAMED ENTITY RECOGNITION WORD EMBEDDINGS
Bidirectional LSTM-CRF Models for Sequence Tagging
In this paper, we propose a variety of Long Short-Term Memory (LSTM) based models for sequence tagging. It can also use sentence level tag information thanks to a CRF layer.
A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks
EMNLP 2017 • rubythonode/joint-many-task-model
Transfer and multi-task learning have traditionally focused on either a single source-target pair or very few, similar tasks. Ideally, the linguistic levels of morphology, syntax and semantics would benefit each other by being trained in a single model.
#2 best model for
Chunking on Penn Treebank