COMBO: State-of-the-Art Morphosyntactic Analysis
Not on the map. Why?
Abstract (arXiv)
We introduce COMBO - a fully neural NLP system for accurate part-of-speech tagging, morphological analysis, lemmatisation, and (enhanced) dependency parsing. It predicts categorical morphosyntactic features whilst also exposes their vector representations, extracted from hidden layers. COMBO is an easy to install Python package with automatically downloadable pre-trained models for over 40 languages. It maintains a balance between efficiency and quality. As it is an end-to-end system and its modules are jointly trained, its training is competitively fast. As its models are optimised for accuracy, they achieve often better prediction quality than SOTA. The COMBO library is available at: https://gitlab.clarin-pl.eu/syntactic-tools/combo.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 20 of its 44 references that are in the map. First posted on arXiv 11 Sep 2021.
Builds on
20 of 44 references.
References · 20
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
- 2020Stanza: A Python Natural Language Processing Toolkit for Many Human Languagescited by 719
- 2019What do you learn from context? Probing for sentence structure in contextualized word representationscited by 436
- 2020AraBERT: Transformer-based Model for Arabic Language Understandingcited by 359
- 2018AllenNLP: A Deep Semantic Natural Language Processing Platformcited by 347
- 2018Learning Word Vectors for 157 Languagescited by 279
- 2015A Theoretically Grounded Application of Dropout in Recurrent Neural Networkscited by 161
- 2019Open Sesame: Getting Inside BERT's Linguistic Knowledgecited by 119
- 2019Multilingual is not enough: BERT for Finnishcited by 118
8 more
- 2019Investigating BERT's Knowledge of Language: Five Analysis Methods with NPIscited by 58
- 2021HerBERT: Efficiently Pretrained Transformer-based Language Model for Polishcited by 51
- 2018Simpler but More Accurate Semantic Dependency Parsingcited by 46
- 2017Fast and Accurate Entity Recognition with Iterated Dilated Convolutionscited by 40
- 2020Is Supervised Syntactic Parsing Beneficial for Language Understanding? An Empirical Investigationcited by 34
- 2020Give your Text Representation Models some Love: the Case for Basquecited by 28
- 2020Semi-Supervised Neural System for Tagging, Parsing and Lematizationcited by 5
- 2021COMBO: a new module for EUD parsingcited by 1
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.