Results 1 to 10 of about 335,632 (328)
PREADD: Prefix-Adaptive Decoding for Controlled Text Generation [PDF]
Annual Meeting of the Association for Computational Linguistics, 2023 We propose Prefix-Adaptive Decoding (PREADD), a flexible method for controlled text generation. Unlike existing methods that use auxiliary expert models to control for attributes, PREADD does not require an external model, instead relying on linearly ...
Jonathan Pei, Kevin Yang, Dan Klein
openalex +3 more sources
Defense-Prefix for Preventing Typographic Attacks on CLIP [PDF]
2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2023 Vision-language pre-training models (VLPs) have exhibited revolutionary improvements in various vision-language tasks. In VLP, some adversarial attacks fool a model into false or absurd classifications.
Hiroki Azuma, Yusuke Matsui
openalex +3 more sources
AMPERE: AMR-Aware Prefix for Generation-Based Event Argument Extraction Model [PDF]
Annual Meeting of the Association for Computational Linguistics, 2023 Event argument extraction (EAE) identifies event arguments and their specific roles for a given event. Recent advancement in generation-based EAE models has shown great performance and generalizability over classification-based models.
I-Hung Hsu +4 more
openalex +3 more sources
Between the Post and the Com-Post: Examining the Postdigital ‘Work’ of a Prefix
Postdigital Science and Education, 2018 In examining the work of the prefix ‘post’, we aim to contribute to the current postdigital dialogue. Our paper does not provide a rationale for the use of ‘postdigital’ in the title of this journal: that has been thoroughly explored elsewhere.
Christine Sinclair, Sarah L Hayes
exaly +2 more sources
A Survey among Network Operators on BGP Prefix Hijacking [PDF]
Computer Communication Review, 2018 BGP prefix hijacking is a threat to Internet operators and users. Several mechanisms or modifications to BGP that protect the Internet against it have been proposed.
Pavlos Sermpezis +2 more
exaly +2 more sources
Online conformance checking: relating event streams to process models using prefix-alignments
International Journal of Data Science and Analytics, 2017 Companies often specify the intended behaviour of their business processes in a process model. Conformance checking techniques allow us to assess to what degree such process models and corresponding process execution data correspond to one another.
Sebastiaan van Zelst +2 more
exaly +2 more sources
Prefix-Tuning: Optimizing Continuous Prompts for Generation [PDF]
Annual Meeting of the Association for Computational Linguistics, 2021 Fine-tuning is the de facto way of leveraging large pretrained language models for downstream tasks. However, fine-tuning modifies all the language model parameters and therefore necessitates storing a full copy for each task.
Xiang Lisa Li, Percy Liang
semanticscholar +1 more source
Investigating the Polysemy of the Prefix /hæm-/ in Persian Based on Cognitive Semantic Approach [PDF]
نشریه پژوهشهای زبانشناسی, 2022 One of the issues discussed in the framework of cognitive semantics is the issue of polysemy. One of the fundamental concepts in polysemy is radial categories. In cognitive semantics, a polysemous word forms a category, and the different meanings of that
Maryam Azimi +2 more
doaj +1 more source
Towards Adaptive Prefix Tuning for Parameter-Efficient Language Model Fine-tuning [PDF]
Annual Meeting of the Association for Computational Linguistics, 2023 Fine-tuning large pre-trained language models on various downstream tasks with whole parameters is prohibitively expensive. Hence, Parameter-efficient fine-tuning has attracted attention that only optimizes a few task-specific parameters with the frozen ...
Zhen-Ru Zhang +5 more
semanticscholar +1 more source
Dynamic Prefix-Tuning for Generative Template-based Event Extraction [PDF]
Annual Meeting of the Association for Computational Linguistics, 2022 We consider event extraction in a generative manner with template-based conditional generation.Although there is a rising trend of casting the task of event extraction as a sequence generation problem with prompts, these generation-based methods have two
Xiao Liu, Heyan Huang, Ge Shi, Bo Wang
semanticscholar +1 more source