natural-language-processing-4

POS Tagging

3260 papers • 126 benchmarks • 313 datasets

Part of Speech Tagging

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in pos-tagging-4

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find pos-tagging-4 models and implementations

jiesutd/NCRFpp

2 papers 1,877

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF

E. Hovy, Xuezhe Ma•Thu Mar 03 2016

A novel neutral network architecture is introduced that benefits from both word- and character-level representations automatically, by using combination of bidirectional LSTM, CNN and CRF, thus making it applicable to a wide range of sequence labeling tasks.

2760

Content

jiesutd/PyTorchSeqLabel

2 papers 1,877

0

Paper Graph

Does Manipulating Tokenization Aid Cross-Lingual Transfer? A Study on POS Tagging for Non-Standardized Languages

Hinrich Schütze, Barbara Plank, Verena Blaschke•Wed Apr 19 2023

Overall, it is found that the similarity between the percentage of words that get split into subwords in the source and target data (the isplit word ratio difference/i) is the strongest predictor for model performance on target data.

21 0

Paper Graph

Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Recurrent Neural Network

Zhao Hai, Yao Qian, Peilu Wang, F. Soong, Lei He•Tue Oct 20 2015

This study proposes to use BLSTM-RNN with word embedding for part-of-speech (POS) tagging task and can also achieve a good performance comparable with the Stanford POS tagger.

114 0

Paper Graph

Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks

R. Salakhutdinov, Zhilin Yang, William W. Cohen•Thu Nov 03 2016

The effects of transfer learning for deep hierarchical recurrent networks across domains, applications, and languages are examined, and it is shown that significant improvement can often be obtained.

355 0

Paper Graph

PKUSEG: A Toolkit for Multi-Domain Chinese Word Segmentation

Xu Sun, Jingjing Xu, Y. Zhang, Ruixuan Luo, Zhiyuan Zhang, Xuancheng Ren•Wed Jun 26 2019

The new toolkit, named PKUSEG, targets at multi-domain word segmentation and provides separate models for different domains, such as web, medicine, and tourism, and supports POS tagging and model training to adapt to various application scenarios.

117 0

Paper Graph

Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss

Yoav Goldberg, Anders Søgaard, Barbara Plank•Mon Apr 18 2016

This work presents a novel bi-LSTM model, which combines the POS tagging loss function with an auxiliary loss function that accounts for rare words, which obtains state-of-the-art performance across 22 languages, and works especially well for morphologically complex languages.

417 0

Paper Graph

Semi-supervised Multitask Learning for Sequence Labeling

Marek Rei•Sun Apr 23 2017

A sequence labeling framework with a secondary training objective, learning to predict surrounding words for every word in the dataset, which incentivises the system to learn general-purpose patterns of semantic and syntactic composition, useful for improving accuracy on different sequence labeling tasks.

251 0

Paper Graph

Portuguese Word Embeddings: Evaluating on Word Analogies and Natural Language Tasks

C. Shulby, S. Aluísio, N. Hartmann, Erick Rocha Fonseca, Marcos Vinícius Treviso, Jéssica S. Rodrigues•Sat Aug 19 2017

Evaluating different word embedding models trained on a large Portuguese corpus, including both Brazilian and European variants, suggests that word analogies are not appropriate forword embedding evaluation; task-specific evaluations appear to be a better option.

212 0

Paper Graph

LINSPECTOR: Multilingual Probing Tasks for Word Representations

Iryna Gurevych, Clara Vania, Ilia Kuznetsov, Gözde Gül Şahin•Thu Mar 21 2019

It is found that a number of probing tests have significantly high positive correlation to the downstream tasks, especially for morphologically rich languages, and these tests can be used to explore word embeddings or black-box neural models for linguistic cues in a multilingual setting.

45 0

Paper Graph

Segmental Recurrent Neural Networks

Chris Dyer, Noah A. Smith, Lingpeng Kong•Tue Nov 17 2015

Experiments on handwriting recognition and joint Chinese word segmentation/POS tagging show that segmental recurrent neural networks obtain substantially higher accuracies compared to models that do not explicitly represent segments.

125 0

Paper Graph

Adding a benchmark result helps the community track progress.