Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Zhijing Jin"'
Publikováno v:
Computational Linguistics, Vol 48, Iss 1, Pp 155-205 (2022)
AbstractText style transfer is an important task in natural language generation, which aims to control certain attributes in the generated text, such as politeness, emotion, humor, and many others. It has a long history in the field of natural langua
Externí odkaz:
https://doaj.org/article/ed8d40b969e84a44b955c6cc3f24c581
Publikováno v:
Journal of palliative medicine. 26(1)
The Journal of Palliative Medicine (JPM) is globally recognized as a leading interdisciplinary peer-reviewed palliative care journal providing balanced information that informs and improves the practice of palliative care. JPM shapes the values, inte
Publikováno v:
AAAI
Machine learning algorithms are often vulnerable to adversarial examples that have imperceptible alterations from the original counterparts but can fool the state-of-the-art models. It is helpful to evaluate or even improve the robustness of these mo
Autor:
Zhijing Jin, Julius von Kügelgen, Jingwei Ni, Tejas Vaidhya, Ayush Kaushal, Mrinmaya Sachan, Bernhard Schoelkopf
Publikováno v:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
The principle of independent causal mechanisms (ICM) states that generative processes of real world data consist of independent modules which do not influence or inform each other. While this idea has led to fruitful developments in the field of caus
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c1eb38dca39530a46f5be9a8010fa343
http://arxiv.org/abs/2110.03618
http://arxiv.org/abs/2110.03618
Publikováno v:
Findings of ACL: ACL-IJCNLP 2021
Findings of ACL
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021
ACL/IJCNLP (Findings)
Findings of ACL
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021
ACL/IJCNLP (Findings)
Recent years have seen many breakthroughs in natural language processing (NLP), transitioning it from a mostly theoretical field to one with many real-world applications. Noting the rising number of applications of other machine learning and AI techn
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dcdfb863aa1466ef3d6e98f49f9c518b
Publikováno v:
Findings of the Association for Computational Linguistics: EMNLP 2021.
Publikováno v:
2020 Conference on Empirical Methods in Natural Language Processing-Proceedings of the Conference
EMNLP (1)
EMNLP (1)
Aspect-based sentiment analysis (ABSA) aims to predict the sentiment towards a specific aspect in the text. However, existing ABSA test sets cannot be used to probe whether a model can distinguish the sentiment of the target aspect from the non-targe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::587c528fcae6e282cad4769f2ce56e51
https://hdl.handle.net/21.11116/0000-000B-9A93-1
https://hdl.handle.net/21.11116/0000-000B-9A93-1
Publikováno v:
COLING
Data collection for the knowledge graph-to-text generation is expensive. As a result, research on unsupervised models has emerged as an active field recently. However, most unsupervised models have to use non-parallel versions of existing small super
Publikováno v:
ACL
Current summarization systems only produce plain, factual headlines, but do not meet the practical needs of creating memorable titles to increase exposure. We propose a new task, Stylistic Headline Generation (SHG), to enrich the headlines with three
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::53df8dae1aabe0f6bd0396e781bb2d09
Autor:
Richard Leiter, Enrico Santus, Zhijing Jin, Katherine Lee, Miryam Yusufov, Edward Moseley, Yujie Qian, Jiang Guo, Charlotta Lindvall
Publikováno v:
Journal of Pain and Symptom Management. 60:279-280