@inproceedings{huang-etal-2020-federated,
title = "Federated Learning for Spoken Language Understanding",
author = "Huang, Zhiqi and
Liu, Fenglin and
Zou, Yuexian",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.310",
doi = "10.18653/v1/2020.coling-main.310",
pages = "3467--3478",
abstract = "Recently, spoken language understanding (SLU) has attracted extensive research interests, and various SLU datasets have been proposed to promote the development. However, most of the existing methods focus on a single individual dataset, the efforts to improve the robustness of models and obtain better performance by combining the merits of various datasets are not well studied. In this paper, we argue that if these SLU datasets are considered together, different knowledge from different datasets could be learned jointly, and there are high chances to promote the performance of each dataset. At the same time, we further attempt to prevent data leakage when unifying multiple datasets which, arguably, is more useful in an industry setting. To this end, we propose a federated learning framework, which could unify various types of datasets as well as tasks to learn and fuse various types of knowledge, i.e., text representations, from different datasets and tasks, without the sharing of downstream task data. The fused text representations merge useful features from different SLU datasets and tasks and are thus much more powerful than the original text representations alone in individual tasks. At last, in order to provide multi-granularity text representations for our framework, we propose a novel Multi-view Encoder (MV-Encoder) as the backbone of our federated learning framework. Experiments on two SLU benchmark datasets, including two tasks (intention detection and slot filling) and federated learning settings (horizontal federated learning, vertical federated learning and federated transfer learning), demonstrate the effectiveness and universality of our approach. Specifically, we are able to get 1.53{\%} improvement on the intent detection metric accuracy. And we could also boost the performance of a strong baseline by up to 5.29{\%} on the slot filling metric F1. Furthermore, by leveraging BERT as an additional encoder, we establish new state-of-the-art results on SNIPS and ATIS datasets, where we get 99.33{\%} and 98.28{\%} in terms of accuracy on intent detection task as well as 97.20{\%} and 96.41{\%} in terms of F1 score on slot filling task, respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2020-federated">
<titleInfo>
<title>Federated Learning for Spoken Language Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhiqi</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fenglin</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuexian</namePart>
<namePart type="family">Zou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recently, spoken language understanding (SLU) has attracted extensive research interests, and various SLU datasets have been proposed to promote the development. However, most of the existing methods focus on a single individual dataset, the efforts to improve the robustness of models and obtain better performance by combining the merits of various datasets are not well studied. In this paper, we argue that if these SLU datasets are considered together, different knowledge from different datasets could be learned jointly, and there are high chances to promote the performance of each dataset. At the same time, we further attempt to prevent data leakage when unifying multiple datasets which, arguably, is more useful in an industry setting. To this end, we propose a federated learning framework, which could unify various types of datasets as well as tasks to learn and fuse various types of knowledge, i.e., text representations, from different datasets and tasks, without the sharing of downstream task data. The fused text representations merge useful features from different SLU datasets and tasks and are thus much more powerful than the original text representations alone in individual tasks. At last, in order to provide multi-granularity text representations for our framework, we propose a novel Multi-view Encoder (MV-Encoder) as the backbone of our federated learning framework. Experiments on two SLU benchmark datasets, including two tasks (intention detection and slot filling) and federated learning settings (horizontal federated learning, vertical federated learning and federated transfer learning), demonstrate the effectiveness and universality of our approach. Specifically, we are able to get 1.53% improvement on the intent detection metric accuracy. And we could also boost the performance of a strong baseline by up to 5.29% on the slot filling metric F1. Furthermore, by leveraging BERT as an additional encoder, we establish new state-of-the-art results on SNIPS and ATIS datasets, where we get 99.33% and 98.28% in terms of accuracy on intent detection task as well as 97.20% and 96.41% in terms of F1 score on slot filling task, respectively.</abstract>
<identifier type="citekey">huang-etal-2020-federated</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.310</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.310</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>3467</start>
<end>3478</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Federated Learning for Spoken Language Understanding
%A Huang, Zhiqi
%A Liu, Fenglin
%A Zou, Yuexian
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F huang-etal-2020-federated
%X Recently, spoken language understanding (SLU) has attracted extensive research interests, and various SLU datasets have been proposed to promote the development. However, most of the existing methods focus on a single individual dataset, the efforts to improve the robustness of models and obtain better performance by combining the merits of various datasets are not well studied. In this paper, we argue that if these SLU datasets are considered together, different knowledge from different datasets could be learned jointly, and there are high chances to promote the performance of each dataset. At the same time, we further attempt to prevent data leakage when unifying multiple datasets which, arguably, is more useful in an industry setting. To this end, we propose a federated learning framework, which could unify various types of datasets as well as tasks to learn and fuse various types of knowledge, i.e., text representations, from different datasets and tasks, without the sharing of downstream task data. The fused text representations merge useful features from different SLU datasets and tasks and are thus much more powerful than the original text representations alone in individual tasks. At last, in order to provide multi-granularity text representations for our framework, we propose a novel Multi-view Encoder (MV-Encoder) as the backbone of our federated learning framework. Experiments on two SLU benchmark datasets, including two tasks (intention detection and slot filling) and federated learning settings (horizontal federated learning, vertical federated learning and federated transfer learning), demonstrate the effectiveness and universality of our approach. Specifically, we are able to get 1.53% improvement on the intent detection metric accuracy. And we could also boost the performance of a strong baseline by up to 5.29% on the slot filling metric F1. Furthermore, by leveraging BERT as an additional encoder, we establish new state-of-the-art results on SNIPS and ATIS datasets, where we get 99.33% and 98.28% in terms of accuracy on intent detection task as well as 97.20% and 96.41% in terms of F1 score on slot filling task, respectively.
%R 10.18653/v1/2020.coling-main.310
%U https://aclanthology.org/2020.coling-main.310
%U https://doi.org/10.18653/v1/2020.coling-main.310
%P 3467-3478
Markdown (Informal)
[Federated Learning for Spoken Language Understanding](https://aclanthology.org/2020.coling-main.310) (Huang et al., COLING 2020)
ACL
- Zhiqi Huang, Fenglin Liu, and Yuexian Zou. 2020. Federated Learning for Spoken Language Understanding. In Proceedings of the 28th International Conference on Computational Linguistics, pages 3467–3478, Barcelona, Spain (Online). International Committee on Computational Linguistics.