A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Filters
CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailment
[article]
2022
arXiv
pre-print
Preserved Fulltext
Then we propose a parameter-efficient fine-tuning strategy to boost the few-shot performance on the vqa task. ...
In this work, we empirically show that CLIP can be a strong vision-language few-shot learner by leveraging the power of language. ...
(No.62076081, No.61772153, and No.61936010), and Natural Science Foundation of Heilongjiang (No.YQ2021F006). ...
arXiv:2203.07190v1
fatcat:whf2ljh2mjfa5l4wsbr5dpvktq
FewCLUE: A Chinese Few-shot Learning Evaluation Benchmark
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2107.07498v1 fatcat:mmjgfft4ajeazopbgq2q3m6fqe
Pretrained Language Models (PLMs) have achieved tremendous success in natural language understanding tasks. ...
Experimental results reveal that: 1) The effect of different few-shot learning methods is sensitive to the pre-trained model to which the methods are applied; 2) PET and P-tuning achieve the best overall ...
., 2021) The above methods all restrict the generated templates to be natural language. ...
arXiv:2107.07498v2
fatcat:ljx2nma3b5aa3ix2pzyadnkgnu
Towards Zero-Label Language Learning
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Specifically, inspired by the recent success of few-shot inference on GPT-3, we present a training data creation procedure named Unsupervised Data Generation (UDG), which leverages few-shot prompts to ...
This paper explores zero-label learning in Natural Language Processing (NLP), whereby no human-annotated data is used anywhere during training and models are trained purely on synthetic data. ...
To this end, we propose to utilize language models to perform few-shot generation. ...
arXiv:2109.09193v1
fatcat:35ijbawdhbalxpqk32qcscbdky
ZmBART: An Unsupervised Cross-lingual Transfer Framework for Language Generation
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
This simple modeling approach gave us promising results.We experimented with few-shot training (with 1000 supervised data points) which boosted the model performance further. ...
In this work, we transfer supervision from high resource language (HRL) to multiple low-resource languages (LRLs) for natural language generation (NLG). ...
Moreover, although freezing the decoder layer and word embeddings helps in zero-shot setting, it is natural and useful to unfreeze them during few shot training. • Few-shot performance with Supervised ...
arXiv:2106.01597v1
fatcat:ajkygelpyfb4jjse7q4tg7w3fe
Label Semantics for Few Shot Named Entity Recognition
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
We propose a neural architecture that consists of two BERT encoders, one to encode the document and its tokens and another one to encode each of the labels in natural language format. ...
We study the problem of few shot learning for named entity recognition. ...
For the unique set of labels L D associated with dataset D, we apply three steps to get the representations: First, we manually convert the label names to their natural language forms, e.g. ...
arXiv:2203.08985v1
fatcat:qrim46gny5csjlv5uhj2lregsq
Vector Projection Network for Few-shot Slot Tagging in Natural Language Understanding
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Essentially, this approach is equivalent to a normalized linear model with an adaptive bias. ...
Specifically, in the five-shot setting on benchmarks SNIPS and NER, our method outperforms the strongest few-shot learning baseline by 6.30 and 13.79 points on F_1 score, respectively. ...
The weights are normalized as ||w k || = 1 to improve the generalization capability of the few-shot model. ...
arXiv:2009.09568v2
fatcat:mvglcehisfhwbegzuiwgxt6ts4
Detecting Hate Speech with GPT-3
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2103.12407v2 fatcat:mwh624ljzbcc5byqf57n66724eOther Versions
We use GPT-3 to identify sexist and racist text passages with zero-, one-, and few-shot learning. ...
Sophisticated language models such as OpenAI's GPT-3 can generate hateful text that targets marginalized groups. ...
We ask GPT-3 to classify these based on zero-, one-, and few-shot learning, with and without instruction. We find that the model performs best with few-shot learning when an instruction is included. ...
arXiv:2103.12407v4
fatcat:uzxo7rlbr5fd3esoxkgdwodequ
AdaDurIAN: Few-shot Adaptation for Neural Text-to-Speech with DurIAN
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
To cope with this issue, we introduce AdaDurIAN by training an improved DurIAN-based average model and leverage it to few-shot learning with the shared speaker-independent content encoder across different ...
Several few-shot learning tasks in our experiments show AdaDurIAN can outperform the baseline end-to-end system by a large margin. ...
Finally, we perform the few-shot emotion transfer tasks on two unseen speakers with limited neutral speech data. We highly recommend readers to go listen to the generated audios 1 . ...
arXiv:2005.05642v1
fatcat:v4q5yhqlkbh5dmu64576xdgc4i
Analyzing Commonsense Emergence in Few-shot Knowledge Models
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
To investigate this question, we train commonsense knowledge models in few-shot settings to study the emergence of their commonsense representation abilities. ...
of large language models. ...
Acknowledgements The authors would like to thank the anonymous reviewers for their feedback, and the Amazon Mechanical Turk community for help with annotation. ...
arXiv:2101.00297v3
fatcat:tn7gycypufej7jxsuvthgrgu5a
When does MAML Work the Best? An Empirical Study on Model-Agnostic Meta-Learning in NLP Applications
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Model-Agnostic Meta-Learning (MAML), a model-agnostic meta-learning method, is successfully employed in NLP applications including few-shot text classification and multi-domain low-resource language generation ...
Many impacting factors, including data quantity, similarity among tasks, and the balance between general language model and task-specific adaptation, can affect the performance of MAML in NLP, but few ...
) to evaluate the general language model. ...
arXiv:2005.11700v1
fatcat:gammq2ryjref7gr3cioore3pm4
PromptMaker: Prompt-based Prototyping with Large Language Models
2022
CHI Conference on Human Factors in Computing Systems Extended Abstracts
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Prototyping is notoriously difficult to do with machine learning (ML), but recent advances in large language models may lower the barriers to people prototyping with ML, through the use of natural language ...
Through interviews with eleven practitioners during a three-week sprint and a workshop, we find that prompt-based prototyping reduced barriers of access by substantially broadening who can prototype with ...
Mike Terry proposed the initial study design, conducted user studies, gave high-level scientific advice, and contributed to paper writing. ...
doi:10.1145/3491101.3503564
fatcat:mjxonbjkvnhi5b3lxq26uc2wsi
Reinforcement Learning for Few-Shot Text Generation Adaptation
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Controlling the generative model to adapt a new domain with limited samples is a difficult challenge and it is receiving increasing attention. ...
To address this shortcoming, we frame the adaptation of text generation systems as a reinforcement learning problem and provide a new approach to make text generation models easily adaptable to target ...
Related Work Few-shot-learning-based approaches are increasingly able to train powerful neural networks on small datasets in many nature language processing(NLP) problems [1] . ...
arXiv:2111.11030v1
fatcat:a66p54623bgyhaogegvfhu64zm
Open Aspect Target Sentiment Classification with Natural Language Prompts
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
To address this, we propose simple approaches that better solve ATSC with natural language prompts, enabling the task under zero-shot cases and enhancing supervised settings, especially for few-shot cases ...
For many business applications, we often seek to analyze sentiments associated with any arbitrary aspects of commercial products, despite having a very limited amount of labels or even without any labels ...
Natural Language Prompts There has been a number of recent papers on using prompts -additional sentences appended to the original input text -to direct language models to perform different tasks, exploiting ...
arXiv:2109.03685v1
fatcat:j3e27vm4ufd63az3oifkbkvfu4
FEWS: Large-Scale, Low-Shot Word Sense Disambiguation with the Dictionary
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
We establish baselines on FEWS with knowledge-based and neural WSD approaches and present transfer learning experiments demonstrating that models additionally trained with FEWS better capture rare senses ...
FEWS has high sense coverage across different natural language domains and provides: (1) a large training set that covers many more senses than previous datasets and (2) a comprehensive evaluation set ...
Finally, we see that even without exposure to the natural sense distribution in natural language texts, the zero-shot model still performs significantly better on the MFS of words than the LFS, with a ...
arXiv:2102.07983v1
fatcat:yigk5rru7nettojaqpixshmfpe
Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2011.01403v2 fatcat:v4fcpg6vv5da5avczfrc4skcweOther Versions
State-of-the-art natural language understanding classification models follow two-stages: pre-training a large language model on an auxiliary task, and then fine-tuning the model on a task-specific labeled ...
Our proposed fine-tuning objective leads to models that are more robust to different levels of noise in the fine-tuning training data, and can generalize better to related tasks with limited labeled data ...
GENERALIZATION ABILITY OF TASK MODELS In this experiment, we first fine-tune RoBERTa-Large on SST-2 using its full training set and get a task model with and without SCL term. ...
arXiv:2011.01403v3
fatcat:iv26tbgzxjf67o26tq2l5rlfpi
« Previous
Showing results 1 — 15 out of 56,553 results