Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Ni'mah, Iftitahu"'
Representing documents into high dimensional embedding space while preserving the structural similarity between document sources has been an ultimate goal for many works on text representation learning. Current embedding models, however, mainly rely
Externí odkaz:
http://arxiv.org/abs/2310.19650
In this study, we analyze automatic evaluation metrics for Natural Language Generation (NLG), specifically task-agnostic metrics and human-aligned metrics. Task-agnostic metrics, such as Perplexity, BLEU, BERTScore, are cost-effective and highly adap
Externí odkaz:
http://arxiv.org/abs/2305.08566
ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain Detection
Publikováno v:
Findings of the Association for Computational Linguistics: EMNLP 2021
The ability to detect Out-of-Domain (OOD) inputs has been a critical requirement in many real-world NLP applications. For example, intent classification in dialogue systems. The reason is that the inclusion of unsupported OOD inputs may lead to catas
Externí odkaz:
http://arxiv.org/abs/2108.12229
This study mainly investigates two common decoding problems in neural keyphrase generation: sequence length bias and beam diversity. To tackle the problems, we introduce a beam search decoding strategy based on word-level and ngram-level reward funct
Externí odkaz:
http://arxiv.org/abs/1909.09485
Autor:
Xiong, Wenting, Ni'mah, Iftitahu, Huesca, Juan M. G., van Ipenburg, Werner, Veldsink, Jan, Pechenizkiy, Mykola
Layer-wise Relevance Propagation (LRP) and saliency maps have been recently used to explain the predictions of Deep Learning models, specifically in the domain of text classification. Given different attribution-based explanations to highlight releva
Externí odkaz:
http://arxiv.org/abs/1811.03970
Autor:
Liu, Shiwei1 (AUTHOR) s.liu3@tue.nl, Ni'mah, Iftitahu1 (AUTHOR), Menkovski, Vlado1 (AUTHOR), Mocanu, Decebal Constantin1,2 (AUTHOR), Pechenizkiy, Mykola1 (AUTHOR)
Publikováno v:
Neural Computing & Applications. Aug2021, Vol. 33 Issue 15, p9625-9636. 12p.
Publikováno v:
2015 9th International Conference on Telecommunication Systems Services & Applications (TSSA); 2015, p1-5, 5p