A Two-phase Prototypical Network Model for Incremental Few-shot Relation Classification

Ren, Haopeng; Cai, Yi; Chen, Xiaofeng; Wang, Guohua; Li, Qing

doi:10.18653/v1/2020.coling-main.142

“…Relation network [19] adapted the convolutional neural network to extract the features of support and query samples, and the relation classification scores were obtained by concatenating the vectors of support and query samples into the relation network. To overcome the catastrophic forgetting problem, Cai et al [20] introduced a two-phase prototypical network, which adapted prototype attention alignment and triplet loss to dynamically recognize the novel relations with a few support instances without catastrophic forgetting. Similarly, Fan et al [21] proposed the large-margin prototypical network with fine-grained features (LM-ProtoNet), which could generalize well on few-shot relations classification.…”

Section: Few-shot Relation Classificationmentioning

confidence: 99%

Commonsense Knowledge-Aware Prompt Tuning for Few-Shot NOTA Relation Classification

Lv

¹

,

Jin

²

,

Zhang

³

et al. 2022

View full text Add to dashboard Cite

Compared with the traditional few-shot task, the few-shot none-of-the-above (NOTA) relation classification focuses on the realistic scenario of few-shot learning, in which a test instance might not belong to any of the target categories. This undoubtedly increases the task’s difficulty because given only a few support samples, this cannot represent the distribution of NOTA categories in space. The model needs to make full use of the syntactic information and word meaning information learned in the pre-training stage to distinguish the NOTA category and the support sample category in the embedding space. However, previous fine-tuning methods mainly focus on optimizing the extra classifiers (on top of pre-trained language models (PLMs)) and neglect the connection between pre-training objectives and downstream tasks. In this paper, we propose the commonsense knowledge-aware prompt tuning (CKPT) method for a few-shot NOTA relation classification task. First, a simple and effective prompt-learning method is developed by constructing relation-oriented templates, which can further stimulate the rich knowledge distributed in PLMs to better serve downstream tasks. Second, external knowledge is incorporated into the model by a label-extension operation, which forms knowledgeable prompt tuning to improve and stabilize prompt tuning. Third, to distinguish the NOTA pairs and positive pairs in embedding space more accurately, a learned scoring strategy is proposed, which introduces a learned threshold classification function and improves the loss function by adding a new term focused on NOTA identification. Experiments on two widely used benchmarks (FewRel 2.0 and Few-shot TACRED) show that our method is a simple and effective framework, and a new state of the art is established in the few-shot classification field.

show abstract

“…As Al-Shedivat et al (2021) recently showed it, such approaches are the most efficient when working with a low amount of training samples. Many variants have been proposed, on different tasks and topics such as relation classification in text (Gao et al, 2019;Hui et al, 2020;Ren et al, 2020), sentiment classification in Amazon comments (Bao et al, 2020), named entity recognition (Fritzler et al, 2019;Hou et al, 2020;Perl et al, 2020;Safranchik et al, 2020), or even speech classification in conversation (Koluguri et al, 2020). This surge of interest on applying few-shot learning to these topics can be attributed to specific datasets, such as Few-Rel (Han et al, 2018) for relation classification.…”

Section: Related Workmentioning

confidence: 99%

Few-Shot Emotion Recognition in Conversation with Sequential Prototypical Networks

Guibon¹,

Labeau²,

Flamein³

et al. 2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Several recent studies on dyadic humanhuman interactions have been done on conversations without specific business objectives. However, many companies might benefit from studies dedicated to more precise environments such as after sales services or customer satisfaction surveys. In this work, we place ourselves in the scope of a live chat customer service in which we want to detect emotions and their evolution in the conversation flow. This context leads to multiple challenges that range from exploiting restricted, small and mostly unlabeled datasets to finding and adapting methods for such context. We tackle these challenges by using Few-Shot Learning while making the hypothesis it can serve conversational emotion classification for different languages and sparse labels. We contribute by proposing a variation of Prototypical Networks for sequence labeling in conversation that we name ProtoSeq. We test this method on two datasets with different languages: daily conversations in English and customer service chat conversations in French. When applied to emotion classification in conversations, our method proved to be competitive even when compared to other ones. The code for Proto-Seq is available at https://github.com/ gguibon/ProtoSeq.

show abstract

“…As Al-Shedivat et al (2021) recently showed it, such approaches are the most efficient when working with a low amount of training samples. Many variants have been proposed, on different tasks and topics such as relation classification in text (Gao et al, 2019;Hui et al, 2020;Ren et al, 2020), sentiment classification in Amazon comments (Bao et al, 2020), named entity recognition (Fritzler et al, 2019;Hou et al, 2020;Perl et al, 2020;Safranchik et al, 2020), or even speech classification in conversation (Koluguri et al, 2020). This surge of interest on applying few-shot learning to these topics can be attributed to specific datasets, such as Few-Rel (Han et al, 2018) for relation classification.…”

Section: Related Workmentioning

confidence: 99%

Few-Shot Emotion Recognition in Conversation with Sequential Prototypical Networks

Guibon,

Labeau,

Flamein

et al. 2021

Preprint

0

View full text Add to dashboard Cite

Several recent studies on dyadic humanhuman interactions have been done on conversations without specific business objectives. However, many companies might benefit from studies dedicated to more precise environments such as after sales services or customer satisfaction surveys. In this work, we place ourselves in the scope of a live chat customer service in which we want to detect emotions and their evolution in the conversation flow. This context leads to multiple challenges that range from exploiting restricted, small and mostly unlabeled datasets to finding and adapting methods for such context. We tackle these challenges by using Few-Shot Learning while making the hypothesis it can serve conversational emotion classification for different languages and sparse labels. We contribute by proposing a variation of Prototypical Networks for sequence labeling in conversation that we name ProtoSeq. We test this method on two datasets with different languages: daily conversations in English and customer service chat conversations in French. When applied to emotion classification in conversations, our method proved to be competitive even when compared to other ones. The code for Proto-Seq is available at https://github.com/ gguibon/ProtoSeq.

show abstract

A Two-phase Prototypical Network Model for Incremental Few-shot Relation Classification

Cited by 37 publications

References 28 publications

Commonsense Knowledge-Aware Prompt Tuning for Few-Shot NOTA Relation Classification

Commonsense Knowledge-Aware Prompt Tuning for Few-Shot NOTA Relation Classification

Few-Shot Emotion Recognition in Conversation with Sequential Prototypical Networks

Few-Shot Emotion Recognition in Conversation with Sequential Prototypical Networks

Contact Info

Product

Resources

About