Home > Research > Publications & Outputs > Leveraging Pre-Trained Embeddings for Welsh Tag...

Links

View graph of relations

Leveraging Pre-Trained Embeddings for Welsh Taggers

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Leveraging Pre-Trained Embeddings for Welsh Taggers. / Ezeani, Ignatius; Piao, Scott; Neale, Steven; Rayson, Paul; Knight, Dawn.

Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019): Held at the 57th Annual Meeting of the Association for Computational Linguistics. Florence, Italy : Association for Computational Linguistics, 2019. p. 270-280.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Ezeani, I, Piao, S, Neale, S, Rayson, P & Knight, D 2019, Leveraging Pre-Trained Embeddings for Welsh Taggers. in Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019): Held at the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Florence, Italy, pp. 270-280. <https://www.aclweb.org/anthology/W19-4332>

APA

Ezeani, I., Piao, S., Neale, S., Rayson, P., & Knight, D. (2019). Leveraging Pre-Trained Embeddings for Welsh Taggers. In Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019): Held at the 57th Annual Meeting of the Association for Computational Linguistics (pp. 270-280). Association for Computational Linguistics. https://www.aclweb.org/anthology/W19-4332

Vancouver

Ezeani I, Piao S, Neale S, Rayson P, Knight D. Leveraging Pre-Trained Embeddings for Welsh Taggers. In Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019): Held at the 57th Annual Meeting of the Association for Computational Linguistics. Florence, Italy: Association for Computational Linguistics. 2019. p. 270-280

Author

Ezeani, Ignatius ; Piao, Scott ; Neale, Steven ; Rayson, Paul ; Knight, Dawn. / Leveraging Pre-Trained Embeddings for Welsh Taggers. Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019): Held at the 57th Annual Meeting of the Association for Computational Linguistics. Florence, Italy : Association for Computational Linguistics, 2019. pp. 270-280

Bibtex

@inproceedings{277e926e9e014cbc8b71b00db5c0673e,
title = "Leveraging Pre-Trained Embeddings for Welsh Taggers",
abstract = "While the application of word embedding models to downstream Natural Language Processing (NLP) tasks has been shown to be successful, the benefits for low-resource languages is somewhat limited due to lack of adequate data for training the models. However, NLP research efforts for low-resource languages have focused on constantly seeking ways to harness pre-trained models to improve the performance of NLP systems built to process these languages without the need to re-invent the wheel. One such language is Welsh and therefore, in this paper, we present the results of our experiments on learning a simple multi-task neural network model for part-of-speech and semantic tagging for Welsh using a pre-trained embedding model from FastText. Our model{\textquoteright}s performance was compared with those of the existing rule-based stand-alone taggers for part-of-speech and semantic taggers. Despite its simplicity and capacity to perform both tasks simultaneously, our tagger compared very well with the existing taggers.",
author = "Ignatius Ezeani and Scott Piao and Steven Neale and Paul Rayson and Dawn Knight",
year = "2019",
month = aug,
day = "2",
language = "English",
pages = "270--280",
booktitle = "Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)",
publisher = "Association for Computational Linguistics",

}

RIS

TY - GEN

T1 - Leveraging Pre-Trained Embeddings for Welsh Taggers

AU - Ezeani, Ignatius

AU - Piao, Scott

AU - Neale, Steven

AU - Rayson, Paul

AU - Knight, Dawn

PY - 2019/8/2

Y1 - 2019/8/2

N2 - While the application of word embedding models to downstream Natural Language Processing (NLP) tasks has been shown to be successful, the benefits for low-resource languages is somewhat limited due to lack of adequate data for training the models. However, NLP research efforts for low-resource languages have focused on constantly seeking ways to harness pre-trained models to improve the performance of NLP systems built to process these languages without the need to re-invent the wheel. One such language is Welsh and therefore, in this paper, we present the results of our experiments on learning a simple multi-task neural network model for part-of-speech and semantic tagging for Welsh using a pre-trained embedding model from FastText. Our model’s performance was compared with those of the existing rule-based stand-alone taggers for part-of-speech and semantic taggers. Despite its simplicity and capacity to perform both tasks simultaneously, our tagger compared very well with the existing taggers.

AB - While the application of word embedding models to downstream Natural Language Processing (NLP) tasks has been shown to be successful, the benefits for low-resource languages is somewhat limited due to lack of adequate data for training the models. However, NLP research efforts for low-resource languages have focused on constantly seeking ways to harness pre-trained models to improve the performance of NLP systems built to process these languages without the need to re-invent the wheel. One such language is Welsh and therefore, in this paper, we present the results of our experiments on learning a simple multi-task neural network model for part-of-speech and semantic tagging for Welsh using a pre-trained embedding model from FastText. Our model’s performance was compared with those of the existing rule-based stand-alone taggers for part-of-speech and semantic taggers. Despite its simplicity and capacity to perform both tasks simultaneously, our tagger compared very well with the existing taggers.

M3 - Conference contribution/Paper

SP - 270

EP - 280

BT - Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)

PB - Association for Computational Linguistics

CY - Florence, Italy

ER -