Weak supervision for Question Type Detection with large language models

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F22%3A43967256" target="_blank" >RIV/49777513:23520/22:43967256 - isvavai.cz</a>

Výsledek na webu

<a href="https://hal.science/hal-03786135/file/paper.pdf" target="_blank" >https://hal.science/hal-03786135/file/paper.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.21437/Interspeech.2022-345" target="_blank" >10.21437/Interspeech.2022-345</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Weak supervision for Question Type Detection with large language models

Popis výsledku v původním jazyce

Large pre-trained language models (LLM) have shown remarkable Zero-Shot Learning performances in many Natural Language Processing tasks. However, designing effective prompts is still very difficult for some tasks, in particular for dialogue act recognition. We propose an alternative way to leverage pretrained LLM for such tasks that replace manual prompts with simple rules, which are more intuitive and easier to design for some tasks. We demonstrate this approach on the question type recognition task, and show that our zero-shot model obtains competitive performances both with a supervised LSTM trained on the full training corpus, and another supervised model from previously published works on the MRDA corpus. We further analyze the limits of the proposed approach, which can not be applied on any task, but may advantageously complement prompt programming for specific classes.

Název v anglickém jazyce

Weak supervision for Question Type Detection with large language models

Popis výsledku anglicky

Large pre-trained language models (LLM) have shown remarkable Zero-Shot Learning performances in many Natural Language Processing tasks. However, designing effective prompts is still very difficult for some tasks, in particular for dialogue act recognition. We propose an alternative way to leverage pretrained LLM for such tasks that replace manual prompts with simple rules, which are more intuitive and easier to design for some tasks. We demonstrate this approach on the question type recognition task, and show that our zero-shot model obtains competitive performances both with a supervised LSTM trained on the full training corpus, and another supervised model from previously published works on the MRDA corpus. We further analyze the limits of the proposed approach, which can not be applied on any task, but may advantageously complement prompt programming for specific classes.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

23rd Annual Conference of the International Speech Communication, Interspeech 2022

ISBN

—

ISSN

2308-457X

e-ISSN

—

Počet stran výsledku

5

Strana od-do

3283-3287

Název nakladatele

International Speech Communication Association (ISCA)

Místo vydání

Baixas

Místo konání akce

Incheon, Jižní Korea

Datum konání akce

18. 9. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000900724503090