1 |
Utilising knowledge graph embeddings for data-to-text generation
|
|
|
|
BASE
|
|
Show details
|
|
2 |
NUIG-DSI’s submission to the GEM Benchmark 2021
|
|
|
|
Abstract:
This paper describes the submission by NUIG-DSI to the GEM benchmark 2021. We participate in the modeling shared task where we submit outputs on four datasets for data-to-text generation, namely, DART, WebNLG (en), E2E and CommonGen. We follow an approach similar to the one described in the GEM benchmark paper where we use the pre-trained T5-base model for our submission. We train this model on additional monolingual data where we experiment with different masking strategies specifically focused on masking entities, predicates and concepts as well as a random masking strategy for pre-training. In our results we find that random masking performs the best in terms of automatic evaluation metrics, though the results are not statistically significantly different compared to other masking strategies. ; This work was conducted with the financial support of the Science Foundation Ireland Centre for Research Training in Artificial Intelligence under Grant No. 18/CRT/6223 and co-supported by Science Foundation Ireland under grant number SFI/12/RC/2289 2 (Insight), co-funded by the European Regional Development Fund. ; peer-reviewed
|
|
Keyword:
GEM benchmark
|
|
URL: https://doi.org/10.18653/v1/2021.gem-1.13 http://hdl.handle.net/10379/16886
|
|
BASE
|
|
Hide details
|
|
3 |
Enhancing multiple-choice question answering with causal knowledge
|
|
|
|
BASE
|
|
Show details
|
|
4 |
NUIG-DSI at the WebNLG+ challenge: Leveraging transfer learning for RDF-to-text generation
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Bilingual lexicon induction across orthographically-distinct under-resourced Dravidian languages
|
|
|
|
In: Chakravarthi, Bharathi Raja orcid:0000-0002-4575-7934 , Rajasekaran, Navaneethan, Arcan, Mihael orcid:0000-0002-3116-621X , McGuinness, Kevin orcid:0000-0003-1336-6477 , O'Connor, Noel E. orcid:0000-0002-4033-9135 and McCrae, John P. orcid:0000-0002-7227-1331 (2020) Bilingual lexicon induction across orthographically-distinct under-resourced Dravidian languages. In: 7th Workshop on NLP for Similar Languages, Varieties and Dialects, 13 Dec 2020, Barcelona, Spain (Online). (2020)
|
|
BASE
|
|
Show details
|
|
6 |
Leveraging orthographic information to improve machine translation of under-resourced languages
|
|
|
|
BASE
|
|
Show details
|
|
7 |
NUIG at TIAD: Combining unsupervised NLP and graph metrics for translation inference
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Aspects of Terminological and Named Entity Knowledge within Rule-Based Machine Translation Models for Under-Resourced Neural Machine Translation Scenarios ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Bilingual Lexicon Induction across Orthographically-distinct Under-Resourced Dravidian Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Bilingual Lexicon Induction across Orthographically-distinct Under-Resourced Dravidian Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Comparison of Different Orthographies for Machine Translation of Under-Resourced Dravidian Languages
|
|
|
|
BASE
|
|
Show details
|
|
12 |
TIAD 2019 Shared Task: Leveraging knowledge graphs with neural machine translation for automatic multilingual dictionary generation
|
|
|
|
BASE
|
|
Show details
|
|
13 |
The ESSOT system goes wild: an easy way for translating ontologies
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Generating linked-data based domain-specific sentiment lexicons from legacy language and semantic resources
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Automatic enrichment of terminological resources: the IATE RDF example
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Avtomatsko pridobivanje besednih zvez iz korpusa z uporabo leksikona SSJ
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Inferring translation candidates for multilingual dictionary generation with multi-way neural machine translation
|
|
|
|
BASE
|
|
Show details
|
|
|
|