Chunking, also known as shallow parsing, identifies continuous spans of tokens that form syntactic units such as noun phrases or verb phrases.
|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
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)
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
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.
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).
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.
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
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.
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