Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Lizhen Qu"'
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 11, Pp 511-530 (2023)
AbstractIn this paper, we conduct the first study on spurious correlations for open-domain response generation models based on a corpus CGDialog curated by ourselves. The current models indeed suffer from spurious correlations and have a tendency to
Externí odkaz:
https://doaj.org/article/27d1fea302754b53b84a85cbf00802ca
Publikováno v:
IEEE Transactions on Dependable and Secure Computing. 19:438-451
A major cause of security incidents such as cyber attacks is rooted in software vulnerabilities. These vulnerabilities should ideally be found and fixed before the code gets deployed. Machine learning-based approaches achieve state-of-the-art perform
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a5410f302556c63df2bb92d2a5256038
https://doi.org/10.1109/tdsc.2020.2984505
https://doi.org/10.1109/tdsc.2020.2984505
Publikováno v:
IEEE Transactions on Software Engineering. 47:2296-2311
Application Programming Interfaces (APIs) have been widely discussed on social-technical platforms (e.g., Stack Overflow). Extracting API mentions from such informal software texts is the prerequisite for API-centric search and summarization of progr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0c14fb177ce1b18c4ea4041ae2f77946
https://doi.org/10.1109/tse.2019.2946830
https://doi.org/10.1109/tse.2019.2946830
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031200588
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fe38cf978f8e1acde47ee1072d3a3b2e
https://doi.org/10.1007/978-3-031-20059-5_22
https://doi.org/10.1007/978-3-031-20059-5_22
Publikováno v:
ACII
Emotions and Dialog Acts (DAs) are phenomena in interpersonal communication that are informative of a person’s underlying thoughts and feelings. Thus, affective computing and dialog system researchers are interested in understanding and detecting e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::355bdfb8446fbcc6bc36eca471b251a2
https://doi.org/10.1109/acii52823.2021.9597428
https://doi.org/10.1109/acii52823.2021.9597428
Publikováno v:
Scopus-Elsevier
ACL/IJCNLP (2)
ACL/IJCNLP (2)
Commonsense reasoning aims to incorporate sets of commonsense facts, retrieved from Commonsense Knowledge Graphs (CKG), to draw conclusion about ordinary situations. The dynamic nature of commonsense knowledge postulates models capable of performing
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1b38889932ebffdc56e3f17ade036512
http://arxiv.org/abs/2105.06717
http://arxiv.org/abs/2105.06717
Publikováno v:
Science progress. 104(2)
Ewing sarcoma (ES) is a malignant tumor that occurs mostly in children. However, the underlying mechanisms of ES are still unknown. Analyzing the results of two previous miRNA array reports, we found that miR-146b-5p might be an onco-miRNA in ES prog
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cafa02bcedf7534c08b804f7430a37f7
https://pubmed.ncbi.nlm.nih.gov/33844600
https://pubmed.ncbi.nlm.nih.gov/33844600
Publikováno v:
WSDM
Leakage of personal information in conversations raises serious privacy concerns. Malicious people or bots could pry into sensitive personal information of vulnerable people, such as juveniles, through conversations with them or their digital persona
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f19e6a35d8b08c211b7e5abfa9e1d5c9
https://doi.org/10.1145/3437963.3441706
https://doi.org/10.1145/3437963.3441706
The ability to generate natural-language questions with controlled complexity levels is highly desirable as it further expands the applicability of question generation. In this paper, we propose an end-to-end neural complexity-controllable question g
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::47b1aea3302d6faa04a253fb383951eb