基本信息
浏览量:18
职业迁徙
个人简介
My research interests lie in machine learning applications in the field of Natural Language Processing (NLP), with a core expertise in the area of user modeling and stylistic variation. I have been investigating how various individuals and sociodemographic groups differ in their language usage, and how this variation can be in return used in machine learning tasks to predict in-group behavior of interest. This also led me to a broader interest in the bias that the NLP field is subject to, in stereotype exaggeration, ethics issues, performance of machine learning models on underrepresented groups, and subsequently domain adaptation of the machine learning models.
My PhD was focused on lexical semantics - examining to which extent word ambiguity and context plays a role in document classification tasks. When is the provided context sufficient for the task at hand, following distributional hypothesis, and when does explicit word sense disambiguation, concept graphs or semantic ontologies become beneficial? Do these findings hold with the rise of deep learning architectures? Does explicitly supplied lexical semantic information still improve classification tasks in scenarios with limited training data?
I have been further pursuing the limited training data paradigm in industry, leading projects related to multilingual and multitask learning, as well as various other bootstrapping efforts for limited in-domain labeled data. I am a big fan of cross-disciplinary collaborations, publishing together with educational researchers, psychologists, sociologists, physicists, and visual analysts, among others.
My PhD was focused on lexical semantics - examining to which extent word ambiguity and context plays a role in document classification tasks. When is the provided context sufficient for the task at hand, following distributional hypothesis, and when does explicit word sense disambiguation, concept graphs or semantic ontologies become beneficial? Do these findings hold with the rise of deep learning architectures? Does explicitly supplied lexical semantic information still improve classification tasks in scenarios with limited training data?
I have been further pursuing the limited training data paradigm in industry, leading projects related to multilingual and multitask learning, as well as various other bootstrapping efforts for limited in-domain labeled data. I am a big fan of cross-disciplinary collaborations, publishing together with educational researchers, psychologists, sociologists, physicists, and visual analysts, among others.
研究兴趣
论文共 63 篇作者统计合作学者相似作者
按年份排序按引用量排序主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
NAACL-HLTpp.1029-1040, (2024)
International Conference on Computational Linguisticspp.1393-1407, (2024)
引用0浏览0EI引用
0
0
Shangrui Nie,Michael Fromm,Charles Welch, Rebekka Görge,Akbar Karimi,Joan Plepi, Nazia Afsan Mowmita, Nicolas Flores-Herr,Mehdi Ali,Lucie Flek
Proceedings of the 2nd Workshop on Cross-Cultural Considerations in NLPpp.65-83, (2024)
International Conference on Computational Linguisticspp.10237-10248, (2024)
引用0浏览0EI引用
0
0
PROCEEDINGS OF THE 6TH CONFERENCE ON ACM CONVERSATIONAL USER INTERFACES, CUI 2024 (2024)
CoRR (2024)
引用0浏览0EI引用
0
0
WASSA@ACLpp.553-557, (2023)
引用0浏览0EI引用
0
0
CoRR (2023)
加载更多
作者统计
#Papers: 67
#Citation: 841
H-Index: 18
G-Index: 28
Sociability: 5
Diversity: 2
Activity: 31
合作学者
合作机构
D-Core
- 合作者
- 学生
- 导师
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn