NUIG at TIAD: Combining Unsupervised NLP and Graph Metrics for Translation Inference

John Philip McCrae; MIHAEL ARCAN

doi:10.13025/21327

NUIG at TIAD: Combining Unsupervised NLP and Graph Metrics for Translation Inference

John Philip McCrae
, MIHAEL ARCAN

Research output: Chapter in Book or Conference Publication/Proceeding › Conference Publication › peer-review

Abstract

In this paper, we present the NUIG system at the TIAD shard task. This system includes graph-based metrics calculated using novel algorithms, with an unsupervised document embedding tool called ONETA and an unsupervised multi-way neural machine translation method. The results are an improvement over our previous system and produce the highest precision among all systems in the task as well as very competitive F-Measure results. Incorporating features from other systems should be easy in the framework we describe in this paper, suggesting this could very easily be extended to an even stronger result.

Original language	English (Ireland)
Title of host publication	Proceedings of the 2020 Globalex Workshop on Linked Lexicography
Publisher	European Language Resources Association (ELRA)
DOIs	https://doi.org/10.13025/21327
Publication status	Published - 1 May 2020

Access to Document

10.13025/21327Licence: CC BY-NC-ND

2020Accepted author manuscript, 268 KBLicence: CC BY-NC-ND

Cite this

@inproceedings{d19cd8e2660e4a07a9bc0191daa0603d,

title = "NUIG at TIAD: Combining Unsupervised NLP and Graph Metrics for Translation Inference",

abstract = "In this paper, we present the NUIG system at the TIAD shard task. This system includes graph-based metrics calculated using novel algorithms, with an unsupervised document embedding tool called ONETA and an unsupervised multi-way neural machine translation method. The results are an improvement over our previous system and produce the highest precision among all systems in the task as well as very competitive F-Measure results. Incorporating features from other systems should be easy in the framework we describe in this paper, suggesting this could very easily be extended to an even stronger result.",

author = "McCrae, \{John Philip\} and MIHAEL ARCAN",

year = "2020",

month = may,

day = "1",

doi = "10.13025/21327",

language = "English (Ireland)",

booktitle = "Proceedings of the 2020 Globalex Workshop on Linked Lexicography",

publisher = "European Language Resources Association (ELRA)",

}

TY - GEN

T1 - NUIG at TIAD: Combining Unsupervised NLP and Graph Metrics for Translation Inference

AU - McCrae, John Philip

AU - ARCAN, MIHAEL

PY - 2020/5/1

Y1 - 2020/5/1

N2 - In this paper, we present the NUIG system at the TIAD shard task. This system includes graph-based metrics calculated using novel algorithms, with an unsupervised document embedding tool called ONETA and an unsupervised multi-way neural machine translation method. The results are an improvement over our previous system and produce the highest precision among all systems in the task as well as very competitive F-Measure results. Incorporating features from other systems should be easy in the framework we describe in this paper, suggesting this could very easily be extended to an even stronger result.

AB - In this paper, we present the NUIG system at the TIAD shard task. This system includes graph-based metrics calculated using novel algorithms, with an unsupervised document embedding tool called ONETA and an unsupervised multi-way neural machine translation method. The results are an improvement over our previous system and produce the highest precision among all systems in the task as well as very competitive F-Measure results. Incorporating features from other systems should be easy in the framework we describe in this paper, suggesting this could very easily be extended to an even stronger result.

UR - http://hdl.handle.net/10379/16057

U2 - 10.13025/21327

DO - 10.13025/21327

M3 - Conference Publication

BT - Proceedings of the 2020 Globalex Workshop on Linked Lexicography

PB - European Language Resources Association (ELRA)

ER -

NUIG at TIAD: Combining Unsupervised NLP and Graph Metrics for Translation Inference

Abstract

Access to Document

Other files and links

Fingerprint

Cite this