Data augmentation (DA) methods have been proven to be effective for pre-trained language models (PLMs) in low-resource settings, including few-shot named entity recognition (NER). However, existing NER DA techniques either perform rule-based manipulations on words that break the semantic coherence of the sentence, or exploit generative models for entity or context substitution, which requires a substantial amount of labeled data and contradicts the objective of operating in low-resource settings. In this work, we propose order-agnostic data augmentation (OaDA), an alternative solution that exploits the often overlooked order-agnostic property in the training data construction phase of sequence-to-sequence NER methods for data augmentation. To effectively utilize the augmented data without suffering from the one-to-many issue, where multiple augmented target sequences exist for one single sentence, we further propose the use of ordering instructions and an innovative OaDA-XE loss. Specifically, by treating each permutation of entity types as an ordering instruction, we rearrange the entity set accordingly, ensuring a distinct input-output pair, while OaDA-XE assigns loss based on the best match between the target sequence and model predictions. We conduct comprehensive experiments and analyses across three major NER benchmarks and significantly enhance the few-shot capabilities of PLMs with OaDA.
Huiming Wang, Liying Cheng, Wenxuan Zhang, De Wen Soh, and Lidong Bing. 2024.Order-Agnostic Data Augmentation for Few-Shot Named Entity Recognition. InProceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7792–7807, Bangkok, Thailand. Association for Computational Linguistics.
@inproceedings{wang-etal-2024-order, title = "Order-Agnostic Data Augmentation for Few-Shot Named Entity Recognition", author = "Wang, Huiming and Cheng, Liying and Zhang, Wenxuan and Soh, De Wen and Bing, Lidong", editor = "Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek", booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", month = aug, year = "2024", address = "Bangkok, Thailand", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2024.acl-long.421/", doi = "10.18653/v1/2024.acl-long.421", pages = "7792--7807", abstract = "Data augmentation (DA) methods have been proven to be effective for pre-trained language models (PLMs) in low-resource settings, including few-shot named entity recognition (NER). However, existing NER DA techniques either perform rule-based manipulations on words that break the semantic coherence of the sentence, or exploit generative models for entity or context substitution, which requires a substantial amount of labeled data and contradicts the objective of operating in low-resource settings. In this work, we propose order-agnostic data augmentation (OaDA), an alternative solution that exploits the often overlooked order-agnostic property in the training data construction phase of sequence-to-sequence NER methods for data augmentation. To effectively utilize the augmented data without suffering from the one-to-many issue, where multiple augmented target sequences exist for one single sentence, we further propose the use of ordering instructions and an innovative OaDA-XE loss. Specifically, by treating each permutation of entity types as an ordering instruction, we rearrange the entity set accordingly, ensuring a distinct input-output pair, while OaDA-XE assigns loss based on the best match between the target sequence and model predictions. We conduct comprehensive experiments and analyses across three major NER benchmarks and significantly enhance the few-shot capabilities of PLMs with OaDA."}
<?xml version="1.0" encoding="UTF-8"?><modsCollection xmlns="http://www.loc.gov/mods/v3"><mods ID="wang-etal-2024-order"> <titleInfo> <title>Order-Agnostic Data Augmentation for Few-Shot Named Entity Recognition</title> </titleInfo> <name type="personal"> <namePart type="given">Huiming</namePart> <namePart type="family">Wang</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Liying</namePart> <namePart type="family">Cheng</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Wenxuan</namePart> <namePart type="family">Zhang</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">De</namePart> <namePart type="given">Wen</namePart> <namePart type="family">Soh</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Lidong</namePart> <namePart type="family">Bing</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <originInfo> <dateIssued>2024-08</dateIssued> </originInfo> <typeOfResource>text</typeOfResource> <relatedItem type="host"> <titleInfo> <title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title> </titleInfo> <name type="personal"> <namePart type="given">Lun-Wei</namePart> <namePart type="family">Ku</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Andre</namePart> <namePart type="family">Martins</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Vivek</namePart> <namePart type="family">Srikumar</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <originInfo> <publisher>Association for Computational Linguistics</publisher> <place> <placeTerm type="text">Bangkok, Thailand</placeTerm> </place> </originInfo> <genre authority="marcgt">conference publication</genre> </relatedItem> <abstract>Data augmentation (DA) methods have been proven to be effective for pre-trained language models (PLMs) in low-resource settings, including few-shot named entity recognition (NER). However, existing NER DA techniques either perform rule-based manipulations on words that break the semantic coherence of the sentence, or exploit generative models for entity or context substitution, which requires a substantial amount of labeled data and contradicts the objective of operating in low-resource settings. In this work, we propose order-agnostic data augmentation (OaDA), an alternative solution that exploits the often overlooked order-agnostic property in the training data construction phase of sequence-to-sequence NER methods for data augmentation. To effectively utilize the augmented data without suffering from the one-to-many issue, where multiple augmented target sequences exist for one single sentence, we further propose the use of ordering instructions and an innovative OaDA-XE loss. Specifically, by treating each permutation of entity types as an ordering instruction, we rearrange the entity set accordingly, ensuring a distinct input-output pair, while OaDA-XE assigns loss based on the best match between the target sequence and model predictions. We conduct comprehensive experiments and analyses across three major NER benchmarks and significantly enhance the few-shot capabilities of PLMs with OaDA.</abstract> <identifier type="citekey">wang-etal-2024-order</identifier> <identifier type="doi">10.18653/v1/2024.acl-long.421</identifier> <location> <url>https://aclanthology.org/2024.acl-long.421/</url> </location> <part> <date>2024-08</date> <extent unit="page"> <start>7792</start> <end>7807</end> </extent> </part></mods></modsCollection>
%0 Conference Proceedings%T Order-Agnostic Data Augmentation for Few-Shot Named Entity Recognition%A Wang, Huiming%A Cheng, Liying%A Zhang, Wenxuan%A Soh, De Wen%A Bing, Lidong%Y Ku, Lun-Wei%Y Martins, Andre%Y Srikumar, Vivek%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)%D 2024%8 August%I Association for Computational Linguistics%C Bangkok, Thailand%F wang-etal-2024-order%X Data augmentation (DA) methods have been proven to be effective for pre-trained language models (PLMs) in low-resource settings, including few-shot named entity recognition (NER). However, existing NER DA techniques either perform rule-based manipulations on words that break the semantic coherence of the sentence, or exploit generative models for entity or context substitution, which requires a substantial amount of labeled data and contradicts the objective of operating in low-resource settings. In this work, we propose order-agnostic data augmentation (OaDA), an alternative solution that exploits the often overlooked order-agnostic property in the training data construction phase of sequence-to-sequence NER methods for data augmentation. To effectively utilize the augmented data without suffering from the one-to-many issue, where multiple augmented target sequences exist for one single sentence, we further propose the use of ordering instructions and an innovative OaDA-XE loss. Specifically, by treating each permutation of entity types as an ordering instruction, we rearrange the entity set accordingly, ensuring a distinct input-output pair, while OaDA-XE assigns loss based on the best match between the target sequence and model predictions. We conduct comprehensive experiments and analyses across three major NER benchmarks and significantly enhance the few-shot capabilities of PLMs with OaDA.%R 10.18653/v1/2024.acl-long.421%U https://aclanthology.org/2024.acl-long.421/%U https://doi.org/10.18653/v1/2024.acl-long.421%P 7792-7807
Huiming Wang, Liying Cheng, Wenxuan Zhang, De Wen Soh, and Lidong Bing. 2024.Order-Agnostic Data Augmentation for Few-Shot Named Entity Recognition. InProceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7792–7807, Bangkok, Thailand. Association for Computational Linguistics.