@inproceedings{shi-etal-2023-adaptive,
title = "Adaptive End-to-End Metric Learning for Zero-Shot Cross-Domain Slot Filling",
author = "Shi, Yuanjun and
Wu, Linzhi and
Shao, Minglai",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.387",
doi = "10.18653/v1/2023.emnlp-main.387",
pages = "6291--6301",
abstract = "Recently slot filling has witnessed great development thanks to deep learning and the availability of large-scale annotated data. However, it poses a critical challenge to handle a novel domain whose samples are never seen during training. The recognition performance might be greatly degraded due to severe domain shifts. Most prior works deal with this problem in a two-pass pipeline manner based on metric learning. In practice, these dominant pipeline models may be limited in computational efficiency and generalization capacity because of non-parallel inference and context-free discrete label embeddings. To this end, we re-examine the typical metric-based methods, and propose a new adaptive end-to-end metric learning scheme for the challenging zero-shot slot filling. Considering simplicity, efficiency and generalizability, we present a cascade-style joint learning framework coupled with context-aware soft label representations and slot-level contrastive representation learning to mitigate the data and label shift problems effectively. Extensive experiments on public benchmarks demonstrate the superiority of the proposed approach over a series of competitive baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shi-etal-2023-adaptive">
<titleInfo>
<title>Adaptive End-to-End Metric Learning for Zero-Shot Cross-Domain Slot Filling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuanjun</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linzhi</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minglai</namePart>
<namePart type="family">Shao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recently slot filling has witnessed great development thanks to deep learning and the availability of large-scale annotated data. However, it poses a critical challenge to handle a novel domain whose samples are never seen during training. The recognition performance might be greatly degraded due to severe domain shifts. Most prior works deal with this problem in a two-pass pipeline manner based on metric learning. In practice, these dominant pipeline models may be limited in computational efficiency and generalization capacity because of non-parallel inference and context-free discrete label embeddings. To this end, we re-examine the typical metric-based methods, and propose a new adaptive end-to-end metric learning scheme for the challenging zero-shot slot filling. Considering simplicity, efficiency and generalizability, we present a cascade-style joint learning framework coupled with context-aware soft label representations and slot-level contrastive representation learning to mitigate the data and label shift problems effectively. Extensive experiments on public benchmarks demonstrate the superiority of the proposed approach over a series of competitive baselines.</abstract>
<identifier type="citekey">shi-etal-2023-adaptive</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.387</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.387</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>6291</start>
<end>6301</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adaptive End-to-End Metric Learning for Zero-Shot Cross-Domain Slot Filling
%A Shi, Yuanjun
%A Wu, Linzhi
%A Shao, Minglai
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F shi-etal-2023-adaptive
%X Recently slot filling has witnessed great development thanks to deep learning and the availability of large-scale annotated data. However, it poses a critical challenge to handle a novel domain whose samples are never seen during training. The recognition performance might be greatly degraded due to severe domain shifts. Most prior works deal with this problem in a two-pass pipeline manner based on metric learning. In practice, these dominant pipeline models may be limited in computational efficiency and generalization capacity because of non-parallel inference and context-free discrete label embeddings. To this end, we re-examine the typical metric-based methods, and propose a new adaptive end-to-end metric learning scheme for the challenging zero-shot slot filling. Considering simplicity, efficiency and generalizability, we present a cascade-style joint learning framework coupled with context-aware soft label representations and slot-level contrastive representation learning to mitigate the data and label shift problems effectively. Extensive experiments on public benchmarks demonstrate the superiority of the proposed approach over a series of competitive baselines.
%R 10.18653/v1/2023.emnlp-main.387
%U https://aclanthology.org/2023.emnlp-main.387
%U https://doi.org/10.18653/v1/2023.emnlp-main.387
%P 6291-6301
Markdown (Informal)
[Adaptive End-to-End Metric Learning for Zero-Shot Cross-Domain Slot Filling](https://aclanthology.org/2023.emnlp-main.387) (Shi et al., EMNLP 2023)
ACL