Adversarial Defense without Adversarial Defense: Enhancing Language Model Robustness via Instance-level Principal Component Removal [0.03%]
无需对抗防御的对抗防御：通过实例级主成分移除增强语言模型的鲁棒性
Yang Wang,Chenghao Xiao,Yizhi Li et al.
Yang Wang et al.
Pre-trained language models (PLMs) have driven substantial progress in natural language processing but remain vulnerable to adversarial attacks, raising concerns about their robustness in real-world applications. Previous studies have sough...
Jay DeYoung,Stephanie C Martinez,Iain J Marshall et al.
Jay DeYoung et al.
Multi-document summarization entails producing concise synopses of collections of inputs. For some applications, the synopsis should accurately synthesize inputs with respect to a key aspect, e.g., a synopsis of film reviews written about a...
Adapting to the Long Tail: A Meta-Analysis of Transfer Learning Research for Language Understanding Tasks [0.03%]
适应长尾：语言理解任务的迁移学习研究元分析
Aakanksha Naik,Jill Lehman,Carolyn Rosé
Aakanksha Naik
Natural language understanding (NLU) has made massive progress driven by large benchmarks, but benchmarks often leave a long tail of infrequent phenomena underrepresented. We reflect on the question: Have transfer learning methods sufficien...
From Characters to Time Intervals: New Paradigms for Evaluation and Neural Parsing of Time Normalizations [0.03%]
从字符到时间间隔：时长规范评估和神经解析的新范式
Egoitz Laparra,Dongfang Xu,Steven Bethard
Egoitz Laparra
This paper presents the first model for time normalization trained on the SCATE corpus. In the SCATE schema, time expressions are annotated as a semantic composition of time entities. This novel schema favors machine learning approaches, as...
William F Styler th,Steven Bethard,Sean Finan et al.
William F Styler th et al.
This article discusses the requirements of a formal specification for the annotation of temporal information in clinical narratives. We discuss the implementation and extension of ISO-TimeML for annotating a corpus of clinical notes, known ...
Large-scale Analysis of Counseling Conversations: An Application of Natural Language Processing to Mental Health [0.03%]
基于自然语言处理的大型咨询对话分析及其在心理健康的运用研究
Tim Althoff,Kevin Clark,Jure Leskovec
Tim Althoff
Mental illness is one of the most pressing public health issues of our time. While counseling and psychotherapy can be effective treatments, our knowledge about how to conduct successful counseling conversations has been limited due to lack...