Part-Of-Speech Tagging

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

15 leaderboard tables shown for this task, 15 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 15 until expanded.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

26 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 228 papers with code (990 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Towards Deep Learning Models Resistant to Adversarial Attacks
  19 Jun 2017 59 repositories listed Syntology ran 9 of 17 samples · 8 unverified · 13 pointer-only (licence)
  Its principled nature also enables us to identify methods for both training and attacking neural networks that are reliable and, in a certain sense, universal.
• End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF
  4 Mar 2016 25 repositories listed Syntology ran 4 of 24 samples · 20 unverified · 3 pointer-only (licence)
  State-of-the-art sequence labeling systems traditionally require large amounts of task-specific knowledge in the form of hand-crafted features and data pre-processing.
• Ask Me Anything: Dynamic Memory Networks for Natural Language Processing
  24 Jun 2015 10 repositories listed Syntology ran 2 of 5 samples · 3 unverified
  Most tasks in natural language processing can be cast into question answering (QA) problems over language input.
• CamemBERT: a Tasty French Language Model
  10 Nov 2019 8 repositories listed
  We show that the use of web crawled data is preferable to the use of Wikipedia data.
• ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations
  2 Nov 2019 7 repositories listed Syntology ran 7 of 35 samples · 28 unverified
  Moreover, it is shown that reasonable performance can be obtained when ZEN is trained on a small corpus, which is important for applying pre-training techniques to scenarios with limited data.
• Does Manipulating Tokenization Aid Cross-Lingual Transfer? A Study on POS Tagging for Non-Standardized Languages
  20 Apr 2023 6 repositories listed
  This can for instance be observed when finetuning PLMs on one language and evaluating them on data in a closely related language variety with no standardized orthography.
• Dice Loss for Data-imbalanced NLP Tasks
  7 Nov 2019 4 repositories listed Syntology ran 0 of 3 samples · 3 unverified
  Many NLP tasks such as tagging and machine reading comprehension are faced with the severe data imbalance issue: negative examples significantly outnumber positive examples, and the huge number of background examples…
• Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks
  18 Mar 2017 4 repositories listed Syntology ran 0 of 8 samples · 8 unverified
  Recent papers have shown that neural networks obtain state-of-the-art performance on several different sequence tagging tasks.
• Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Recurrent Neural Network
  21 Oct 2015 4 repositories listed
  Bidirectional Long Short-Term Memory Recurrent Neural Network (BLSTM-RNN) has been shown to be very effective for tagging sequential data, e.
• BERTweet: A pre-trained language model for English Tweets
  20 May 2020 3 repositories listed
  We present BERTweet, the first public large-scale pre-trained language model for English Tweets.
• Beheshti-NER: Persian Named Entity Recognition Using BERT
  19 Mar 2020 3 repositories listed
  In this paper, we use the pre-trained deep bidirectional network, BERT, to make a model for named entity recognition in Persian.
• Generalizing Natural Language Analysis through Span-relation Representations
  10 Nov 2019 3 repositories listed
  Natural language processing covers a wide variety of tasks predicting syntax, semantics, and information content, and usually each type of output is generated with specially designed architectures.
• NCRF++: An Open-source Neural Sequence Labeling Toolkit
  14 Jun 2018 3 repositories listed Syntology ran 1 of 9 samples · 8 unverified
  This paper describes NCRF++, a toolkit for neural sequence labeling.
• Learning Approximate Inference Networks for Structured Prediction
  9 Mar 2018 3 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 1 pointer-only (licence)
  Prior work used gradient descent for inference, relaxing the structured output to a set of continuous variables and then optimizing the energy with respect to them.
• Empower Sequence Labeling with Task-Aware Neural Language Model
  13 Sep 2017 3 repositories listed
  In this study, we develop a novel neural framework to extract abundant knowledge hidden in raw texts to empower the sequence labeling task.
• Semi-supervised Multitask Learning for Sequence Labeling
  24 Apr 2017 3 repositories listed
  We propose a sequence labeling framework with a secondary training objective, learning to predict surrounding words for every word in the dataset.
• Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss
  19 Apr 2016 3 repositories listed Syntology ran 1 of 4 samples · 3 unverified · 1 pointer-only (licence)
  Bidirectional long short-term memory (bi-LSTM) networks have recently proven successful for various NLP sequence modeling tasks, but little is known about their reliance to input representations, target languages, data…
• POS-tagging to highlight the skeletal structure of sentences
  21 Nov 2024 2 repositories listed
  This study presents the development of a part-of-speech (POS) tagging model to extract the skeletal structure of sentences using transfer learning with the BERT architecture for token classification.
• Lexically Grounded Subword Segmentation
  19 Jun 2024 2 repositories listed Syntology ran 3 of 3 samples · 0 unverified
  Third, we introduce an efficient segmentation algorithm based on a subword bigram model that can be initialized with the lexically aware segmentation method to avoid using Morfessor and large embedding tables at…
• Def2Vec: Extensible Word Embeddings from Dictionary Definitions
  16 Dec 2023 2 repositories listed
  Def2Vec introduces a novel paradigm for word embeddings, leveraging dictionary definitions to learn semantic representations.
• PuoBERTa: Training and evaluation of a curated language model for Setswana
  13 Oct 2023 2 repositories listed
  Natural language processing (NLP) has made significant progress for well-resourced languages such as English but lagged behind for low-resource languages like Setswana.
• Advancing Hungarian Text Processing with HuSpaCy: Efficient and Accurate NLP Pipelines
  24 Aug 2023 2 repositories listed
  This paper presents a set of industrial-grade text processing models for Hungarian that achieve near state-of-the-art performance while balancing resource efficiency and accuracy.
• Sentence Embedding Models for Ancient Greek Using Multilingual Knowledge Distillation
  24 Aug 2023 2 repositories listed
  In this work, we use a multilingual knowledge distillation approach to train BERT models to produce sentence embeddings for Ancient Greek text.
• Technical Report: Impact of Position Bias on Language Models in Token Classification
  26 Apr 2023 2 repositories listed
  Therefore, we conduct an in-depth evaluation of the impact of position bias on the performance of LMs when fine-tuned on token classification benchmarks.
• Unsupervised Boundary-Aware Language Model Pretraining for Chinese Sequence Labeling
  27 Oct 2022 2 repositories listed
  We apply BABERT for feature induction of Chinese sequence labeling tasks.
• reproducing "ner and pos when nothing is capitalized"
  17 Sep 2021 2 repositories listed
  Capitalization is an important feature in many NLP tasks such as Named Entity Recognition (NER) or Part of Speech Tagging (POS).
• Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction
  14 Sep 2021 2 repositories listed Syntology ran 1 of 7 samples · 6 unverified
  Zero-shot cross-lingual information extraction (IE) describes the construction of an IE model for some target language, given existing annotations exclusively in some other language, typically English.
• How Low is Too Low? A Computational Perspective on Extremely Low-Resource Languages
  30 May 2021 2 repositories listed
  Despite the recent advancements of attention-based deep learning architectures across a majority of Natural Language Processing tasks, their application remains limited in a low-resource setting because of a lack of…
• Potential Idiomatic Expression (PIE)-English: Corpus for Classes of Idioms
  25 Apr 2021 2 repositories listed
  The challenges with NLP systems with regards to tasks such as Machine Translation (MT), word sense disambiguation (WSD) and information retrieval make it imperative to have a labelled idioms dataset with classes such as…
• AlephBERT:A Hebrew Large Pre-Trained Language Model to Start-off your Hebrew NLP Application With
  8 Apr 2021 2 repositories listed Syntology ran 2 of 2 samples · 0 unverified
  Second, there are no accepted tasks and benchmarks to evaluate the progress of Hebrew PLMs on.

Syntology lines on 12 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.