@inproceedings{sun-etal-2024-speech,
title = "Speech-based Slot Filling using Large Language Models",
author = "Sun, Guangzhi and
Feng, Shutong and
Jiang, Dongcheng and
Zhang, Chao and
Gasic, Milica and
Woodland, Phil",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.379",
pages = "6351--6362",
abstract = "Recently, advancements in large language models (LLMs) have shown an unprecedented ability across various language tasks. This paper investigates the potential application of LLMs to slot filling with noisy ASR transcriptions, via both in-context learning and task-specific fine-tuning. Dedicated prompt designs and noise-robust LoRA fine-tuning are proposed to improve the robustness of LLMs for slot filling with noisy ASR transcriptions. Moreover, a linearised knowledge injection (LKI) scheme is also proposed to integrate dynamic external knowledge into LLMs. Experiments were performed on SLURP to quantify the performance of LLMs, including GPT-3.5-turbo, GPT-4, LLaMA-13B, LLaMA-2-13B and Vicuna-13B (v1.1 and v1.5) with different ASR error rates. The use of the noise-robust fine-tuning together with LKI for Vicuna-13B-v1.5 achieved 6.7{\%} and 17.6{\%} absolute SLU-F1 improvements compared to a fully fine-tuned Flan-T5-XL model on the limited data setup and the zero-shot setup respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2024-speech">
<titleInfo>
<title>Speech-based Slot Filling using Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guangzhi</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shutong</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongcheng</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Milica</namePart>
<namePart type="family">Gasic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phil</namePart>
<namePart type="family">Woodland</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>Findings of the Association for Computational Linguistics ACL 2024</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 and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recently, advancements in large language models (LLMs) have shown an unprecedented ability across various language tasks. This paper investigates the potential application of LLMs to slot filling with noisy ASR transcriptions, via both in-context learning and task-specific fine-tuning. Dedicated prompt designs and noise-robust LoRA fine-tuning are proposed to improve the robustness of LLMs for slot filling with noisy ASR transcriptions. Moreover, a linearised knowledge injection (LKI) scheme is also proposed to integrate dynamic external knowledge into LLMs. Experiments were performed on SLURP to quantify the performance of LLMs, including GPT-3.5-turbo, GPT-4, LLaMA-13B, LLaMA-2-13B and Vicuna-13B (v1.1 and v1.5) with different ASR error rates. The use of the noise-robust fine-tuning together with LKI for Vicuna-13B-v1.5 achieved 6.7% and 17.6% absolute SLU-F1 improvements compared to a fully fine-tuned Flan-T5-XL model on the limited data setup and the zero-shot setup respectively.</abstract>
<identifier type="citekey">sun-etal-2024-speech</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.379</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>6351</start>
<end>6362</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Speech-based Slot Filling using Large Language Models
%A Sun, Guangzhi
%A Feng, Shutong
%A Jiang, Dongcheng
%A Zhang, Chao
%A Gasic, Milica
%A Woodland, Phil
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F sun-etal-2024-speech
%X Recently, advancements in large language models (LLMs) have shown an unprecedented ability across various language tasks. This paper investigates the potential application of LLMs to slot filling with noisy ASR transcriptions, via both in-context learning and task-specific fine-tuning. Dedicated prompt designs and noise-robust LoRA fine-tuning are proposed to improve the robustness of LLMs for slot filling with noisy ASR transcriptions. Moreover, a linearised knowledge injection (LKI) scheme is also proposed to integrate dynamic external knowledge into LLMs. Experiments were performed on SLURP to quantify the performance of LLMs, including GPT-3.5-turbo, GPT-4, LLaMA-13B, LLaMA-2-13B and Vicuna-13B (v1.1 and v1.5) with different ASR error rates. The use of the noise-robust fine-tuning together with LKI for Vicuna-13B-v1.5 achieved 6.7% and 17.6% absolute SLU-F1 improvements compared to a fully fine-tuned Flan-T5-XL model on the limited data setup and the zero-shot setup respectively.
%U https://aclanthology.org/2024.findings-acl.379
%P 6351-6362
Markdown (Informal)
[Speech-based Slot Filling using Large Language Models](https://aclanthology.org/2024.findings-acl.379) (Sun et al., Findings 2024)
ACL
- Guangzhi Sun, Shutong Feng, Dongcheng Jiang, Chao Zhang, Milica Gasic, and Phil Woodland. 2024. Speech-based Slot Filling using Large Language Models. In Findings of the Association for Computational Linguistics ACL 2024, pages 6351–6362, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.