mlsanityData to 7 Oct 2026

Towards Better UD Parsing: Deep Contextualized Word Embeddings, Ensemble, and Treebank Concatenation

arXiv 1807.03121 ↗First posted 9 Jul 2018cs.CLcited by 21

Not on the map. Why?

Abstract (arXiv)

This paper describes our system (HIT-SCIR) submitted to the CoNLL 2018 shared task on Multilingual Parsing from Raw Text to Universal Dependencies. We base our submission on Stanford's winning system for the CoNLL 2017 shared task and make two effective extensions: 1) incorporating deep contextualized word embeddings into both the part of speech tagger and parser; 2) ensembling parsers trained with different initialization. We also explore different ways of concatenating treebanks for further improvements. Experimental results on the development data show the effectiveness of our methods. In the final evaluation, our system was ranked first according to LAS (75.84%) and outperformed the other systems by a large margin.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 7; 2023: 0; 2024: 2; 2025: 2; 2026: 1.

21 papers.

Sort:

  1. 2021Large-Scale Contextualised Language Modelling for Norwegiancited by 21
  2. 2022DAMO-NLP at SemEval-2022 Task 11: A Knowledge-based System for Multilingual Named Entity Recognitioncited by 17
  3. 2021Article Reranking by Memory-Enhanced Key Sentence Matching for Detecting Previously Fact-Checked Claimscited by 16
  4. 2021Meta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsingcited by 10
  5. 2021!Qu'e maravilla! Multimodal Sarcasm Detection in Spanish: a Dataset and a Baselinecited by 8
  6. 2022Resources for Turkish Natural Language Processing: A critical surveycited by 6
  7. 2022Evaluation Benchmarks for Spanish Sentence Representationscited by 6
  8. 2021Evaluation of contextual embeddings on less-resourced languagescited by 4
  9. 2021Neural Supervised Domain Adaptation by Augmenting Pre-trained Models with Random Unitscited by 2
  10. 2024A Comprehensive Analysis of Static Word Embeddings for Turkishcited by 2
  11. 2021Revisiting Tri-training of Dependency Parserscited by 1
  12. 2022Bridging Pre-trained Language Models and Hand-crafted Features for Unsupervised POS Taggingcited by 1
9 more
  1. 2021Android Security using NLP Techniques: A Reviewcited by 0
  2. 2021Multimodal Approach for Metadata Extraction from German Scientific Publicationscited by 0
  3. 2022Exploring Descriptions of Movement Through Geovisual Analyticscited by 0
  4. 2022Zero-shot Cross-Linguistic Learning of Event Semanticscited by 0
  5. 2022The Fragility of Multi-Treebank Parsing Evaluationcited by 0
  6. 2024Empirical Analysis for Unsupervised Universal Dependency Parse Tree Aggregationcited by 0
  7. 2025Fake Advertisements Detection Using Automated Multimodal Learning: A Case Study for Vietnamese Real Estate Datacited by 0
  8. 2025Scraping the Shadows: Deep Learning Breakthroughs in Dark Web Intelligencecited by 0
  9. 2026Tokenization and Morphological Fidelity in Uralic NLP: A Cross-Lingual Evaluationcited by 0