Filters








820 Hits in 6.8 sec

Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference [article]

Jian-Guo Zhang, Kazuma Hashimoto, Wenhao Liu, Chien-Sheng Wu, Yao Wan, Philip S. Yu, Richard Socher, Caiming Xiong
2020 arXiv   pre-print
We propose to boost the discriminative ability by transferring a natural language inference (NLI) model.  ...  More notably, the NLI transfer enables our 10-shot model to perform competitively with 50-shot or even full-shot classifiers, while we can keep the inference time constant by leveraging a faster embedding  ...  Acknowledgments This work is supported in part by NSF under grants III-1763325, III-1909323, and SaTC-1930941.  ... 
arXiv:2010.13009v1 fatcat:s3uuyunrkreapnoyjn2pyfyuui

Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference

Jianguo Zhang, Kazuma Hashimoto, Wenhao Liu, Chien-Sheng Wu, Yao Wan, Philip Yu, Richard Socher, Caiming Xiong
2020 Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)   unpublished
We propose to boost the discriminative ability by transferring a natural language inference (NLI) model.  ...  More notably, the NLI transfer enables our 10-shot model to perform competitively with 50-shot or even full-shot classifiers, while we can keep the inference time constant by leveraging a faster embedding  ...  Acknowledgments This work is supported in part by NSF under grants III-1763325, III-1909323, and SaTC-1930941.  ... 
doi:10.18653/v1/2020.emnlp-main.411 fatcat:ijzws2bzqbb43if6jb56n2q3q4

Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning [article]

Jianguo Zhang, Trung Bui, Seunghyun Yoon, Xiang Chen, Zhiwei Liu, Congying Xia, Quan Hung Tran, Walter Chang, Philip Yu
2021 arXiv   pre-print
In this work, we focus on a more challenging few-shot intent detection scenario where many intents are fine-grained and semantically similar.  ...  We present a simple yet effective few-shot intent detection schema via contrastive pre-training and fine-tuning.  ...  Acknowledgements This work is supported in part by NSF under grants III-1763325, III-1909323, III-2106758, and SaTC-1930941. We thank the anonymous reviewers for their helpful and thoughtful comments.  ... 
arXiv:2109.06349v1 fatcat:pndv226l3zbxlfgt4bkgugehfa

CG-BERT: Conditional Text Generation with BERT for Generalized Few-shot Intent Detection [article]

Congying Xia, Chenwei Zhang, Hoang Nguyen, Jiawei Zhang, Philip Yu
2020 arXiv   pre-print
In this paper, we formulate a more realistic and difficult problem setup for the intent detection task in natural language understanding, namely Generalized Few-Shot Intent Detection (GFSID).  ...  By modeling the utterance distribution with variational inference, CG-BERT can generate diverse utterances for the novel intents even with only a few utterances available.  ...  SMOTE only generates new features within the few-shots, while CG-BERT is able to generate diverse examples beyond these five shots by transfer expressions from existing intents.  ... 
arXiv:2004.01881v1 fatcat:iofdy3sagbdsdmsh7rkzm32yhe

Virtual Augmentation Supported Contrastive Learning of Sentence Representations [article]

Dejiao Zhang, Wei Xiao, Henghui Zhu, Xiaofei Ma, Andrew O. Arnold
2022 arXiv   pre-print
This challenge is magnified in natural language processing where no general rules exist for data augmentation due to the discrete nature of natural language.  ...  Leveraging the large training batch size of contrastive learning, we approximate the neighborhood of an instance via its K-nearest in-batch neighbors in the representation space.  ...  Among them, supervised learning on the Natural Language Inference (NLI) datasets (Bowman et al., 2015a; Williams et al., 2017; Wang et al., 2018) has established benchmark transfer learning performance  ... 
arXiv:2110.08552v2 fatcat:t374n34vsjhh5fqim6q6xodq2e

Knowledge Extraction in Low-Resource Scenarios: Survey and Perspective [article]

Shumin Deng, Ningyu Zhang, Hui Chen, Feiyu Xiong, Jeff Z. Pan, Huajun Chen
2022 arXiv   pre-print
[He et al., 2021] have regarded nearest neighbors as the augmentation on the language model predictions by using neighbors of the predictions as targets for language model learning, which demonstrated  ...  Meta Learning promptly assimilates new knowledge and deduce new classes by learning from few instances, with the ability of "learning to learn", which is naturally suitable for few-shot KE tasks.  ... 
arXiv:2202.08063v1 fatcat:2q64tx2mzne53gt24adi6ymj7a

New Intent Discovery with Pre-training and Contrastive Learning [article]

Yuwei Zhang, Haode Zhang, Li-Ming Zhan, Xiao-Ming Wu, Albert Y.S. Lam
2022 arXiv   pre-print
Extensive experiments on three intent recognition benchmarks demonstrate the high effectiveness of our proposed method, which outperforms state-of-the-art methods by a large margin in both unsupervised  ...  New intent discovery aims to uncover novel intent categories from user utterances to expand the set of supported intent classes.  ...  of few-shot intent detection.  ... 
arXiv:2205.12914v1 fatcat:7tm5vjfdn5ajjbxa66v42dkyii

VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding [article]

Hu Xu, Gargi Ghosh, Po-Yao Huang, Dmytro Okhonko, Armen Aghajanyan, Florian Metze, Luke Zettlemoyer, Christoph Feichtenhofer
2021 arXiv   pre-print
VideoCLIP trains a transformer for video and text by contrasting temporally overlapping positive video-text pairs with hard negatives from nearest neighbor retrieval.  ...  We present VideoCLIP, a contrastive approach to pre-train a unified model for zero-shot video and text understanding, without using any labels on downstream tasks.  ...  This suggests that using a joint backbone for video and text is effective. retrieve k indicates direct searching k nearest neighbors instead of sampling k videos from 2k nearest neighbors (used by VideoCLIP  ... 
arXiv:2109.14084v2 fatcat:bbv6j5ekcfhg3c5ladvx5ytdae

Improving Semantic Embedding Consistency by Metric Learning for Zero-Shot Classiffication [chapter]

Maxime Bucher, Stéphane Herbin, Frédéric Jurie
2016 Lecture Notes in Computer Science  
The key contribution of the proposed approach is to control the semantic embedding of images -one of the main ingredients of zero-shot learning -by formulating it as a metric learning problem.  ...  The optimized empirical criterion associates two types of sub-task constraints: metric discriminating capacity and accurate attribute prediction.  ...  [33] exploit natural language processing technologies to generate event descriptions.  ... 
doi:10.1007/978-3-319-46454-1_44 fatcat:jvxlw24xazgtll745xgoaw6m7q

Improving Semantic Embedding Consistency by Metric Learning for Zero-Shot Classification [article]

Maxime Bucher, Frédéric Jurie
2016 arXiv   pre-print
The key contribution of the proposed approach is to control the semantic embedding of images -- one of the main ingredients of zero-shot learning -- by formulating it as a metric learning problem.  ...  The optimized empirical criterion associates two types of sub-task constraints: metric discriminating capacity and accurate attribute prediction.  ...  [33] exploit natural language processing technologies to generate event descriptions.  ... 
arXiv:1607.08085v1 fatcat:emy4eektarakhebwltkij37gie

SECaps: A Sequence Enhanced Capsule Model for Charge Prediction [article]

Congqing He, Li Peng, Yuquan Le, Jiawei He
2018 arXiv   pre-print
Nevertheless, most existing works on automatic charge prediction perform adequately on those high-frequency charges but are not yet capable of predicting few-shot charges with lim-ited cases.  ...  In addition, we construct our SE-Caps model by making use of seq-caps layer.  ...  However, this work cannot handle few-shot problem. Hu et al. [9] propose an attention-based neural model by incorporating several discriminative legal attributes.  ... 
arXiv:1810.04465v1 fatcat:pbtwqaqh5fclxkamsgqdzcqanq

Fast and Light-Weight Answer Text Retrieval in Dialogue Systems [article]

Hui Wan, Siva Sankalp Patel, J. William Murdock, Saloni Potdar, Sachindra Joshi
2022 arXiv   pre-print
During inference time, only the query needs to be encoded; ANN (approx-imate nearest neighbor) search libraries such as FAISS (Johnson et al., 2017) are used to efficiently search for the most relevant  ...  once; also they leverage ANN (approximate nearest neighbor) algorithms to efficiently search for relevant dense vectors.  ...  Our work is exploring the efficient and effective approaches of text retrieval on answer text corpus curated by chat-bot administrators.  ... 
arXiv:2205.14226v2 fatcat:y4tphpneabcjjeimvdenkvj5ky

Open-world Machine Learning: Applications, Challenges, and Opportunities [article]

Jitendra Parmar, Satyendra Singh Chouhan, Vaskar Raychoudhury, Santosh Singh Rathore
2022 arXiv   pre-print
TOP-ID can detect a user's intent automatically in natural language. It does not need any prior knowledge for intent detection.  ...  The loss layer detects the known intents from discriminative deep features while LOF detects unknown intents.  ...  52312 DBpedia [81] https://wiki.dbpedia.org/datasets EMNIST [77] https://www.nist.gov/itl/products-andservices/emnist-dataset Auslan [65] https://archive.ics.uci.edu/ml/datasets/ Australian +Sign+Language  ... 
arXiv:2105.13448v2 fatcat:rv6f42sdvvajnhub4uguuhb2cy

CLEAR: Cumulative LEARning for One-Shot One-Class Image Recognition

Jedrzej Kozerawski, Matthew Turk
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
Our method exploits transfer learning to model the transformation from a representation of the input, extracted by a Convolutional Neural Network, to a classification decision boundary.  ...  This work addresses the novel problem of one-shot oneclass classification. The goal is to estimate a classification decision boundary for a novel class based on a single image example.  ...  Tax [35] provided a novel method, called Nearest Neighbor Description (NN-d), for using a Nearest Neighbor classifier to deal with the OCC problem.  ... 
doi:10.1109/cvpr.2018.00363 dblp:conf/cvpr/KozerawskiT18 fatcat:u62jgmqci5gm7mpg2z7wluxo74

A Review on Text-Based Emotion Detection – Techniques, Applications, Datasets, and Future Directions [article]

Sheetal Kusal, Shruti Patil, Jyoti Choudrie, Ketan Kotecha, Deepali Vora, Ilias Pappas
2022 arXiv   pre-print
The field of text-based emotion detection (TBED) is advancing to provide automated solutions to various applications, such as businesses, and finances, to name a few.  ...  It produces better predictions compared to a single decision tree. k-NN (k -Nearest Neighbor)k-NN is one of the simplest categories. The nearest neighbor of K is the meaning of k nearest neighbor.  ...  the time of the testing when there are a few labeled instances, it is referred as few-shot learning.  ... 
arXiv:2205.03235v1 fatcat:b3m25fg6xfc3leeym22eqysq5a
« Previous Showing results 1 — 15 out of 820 results