paper-with-me

홈 › Papers

To Coerce or Not to Coerce: A Corpus-based Exploration of Some Complement Coercion Verbs in Chinese

2013-09-01 · WS 2013 9 · Chan-Chia Hsu, Shu-Kai Hsieh
📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Linguistic Productivity in Large Language Models: Models Coerce, but do not Preempt

2026-06-01 · Claire Bonial, Claire Benet Post, Laura Michaelis, Harish Tayyar Madabushi arxiv

Usage-based theories of grammars posit that creative productivity of the structures of language is both bolstered and constrained by two distinct frequency signals: entrenchment, stemming from high frequency usage, and p…

Modeling the US-China trade conflict: a utility theory approach

2020-10-23 · Yuhan Zhang, Cheng Chang

This paper models the US-China trade conflict and attempts to analyze the (optimal) strategic choices. In contrast to the existing literature on the topic, we employ the expected utility theory and examine the conflict m…

Coercing LLMs to do and reveal (almost) anything

2024-02-21 · Jonas Geiping, Alex Stein, Manli Shu, Khalid Saifullah 외

It has recently been shown that adversarial attacks on large language models (LLMs) can "jailbreak" the model into making harmful statements. In this work, we argue that the spectrum of adversarial attacks on LLMs is muc…

Learning Noise-Invariant Representations for Robust Speech Recognition

2018-07-17 · Davis Liang, Zhiheng Huang, Zachary C. Lipton

Despite rapid advances in speech recognition, current models remain brittle to superficial perturbations to their inputs. Small amounts of noise can destroy the performance of an otherwise state-of-the-art model. To hard…

Data AugmentationRepresentation LearningRobust Speech Recognitionspeech-recognition+1

Learning Noise-Invariant Representations for Robust Speech Recognition

2018-10-02 · Anonymous

Despite rapid advances in speech recognition, current models remain brittle to superficial perturbations to their inputs. Small amounts of noise can destroy the performance of an otherwise state-of-the-art model. To hard…

Data AugmentationRepresentation LearningRobust Speech Recognitionspeech-recognition+1