<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="king-flanigan-2024-unsupervised">
    <titleInfo>
        <title>Unsupervised End-to-End Task-Oriented Dialogue with LLMs: The Power of the Noisy Channel</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Brendan</namePart>
        <namePart type="family">King</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jeffrey</namePart>
        <namePart type="family">Flanigan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yaser</namePart>
            <namePart type="family">Al-Onaizan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yun-Nung</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, Florida, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Training task-oriented dialogue systems typically requires turn-level annotations for interacting with their APIs: e.g. a dialogue state and the system actions taken at each step. These annotations can be costly to produce, error-prone, and require both domain and annotation expertise. With advances in LLMs, we hypothesize that unlabeled data and a schema definition are sufficient for building a working task-oriented dialogue system, completely unsupervised. We consider a novel unsupervised setting of only (1) a well-defined API schema (2) a set of unlabeled dialogues between a user and agent. We propose an innovative approach using expectation-maximization (EM) that infers turn-level annotations as latent variables using a noisy channel model to build an end-to-end dialogue agent. Evaluating our approach on the MultiWOZ benchmark, our method more than doubles the dialogue success rate of a strong GPT-3.5 baseline.</abstract>
    <identifier type="citekey">king-flanigan-2024-unsupervised</identifier>
    <identifier type="doi">10.18653/v1/2024.emnlp-main.473</identifier>
    <location>
        <url>https://aclanthology.org/2024.emnlp-main.473/</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>8283</start>
            <end>8300</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Unsupervised End-to-End Task-Oriented Dialogue with LLMs: The Power of the Noisy Channel
%A King, Brendan
%A Flanigan, Jeffrey
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F king-flanigan-2024-unsupervised
%X Training task-oriented dialogue systems typically requires turn-level annotations for interacting with their APIs: e.g. a dialogue state and the system actions taken at each step. These annotations can be costly to produce, error-prone, and require both domain and annotation expertise. With advances in LLMs, we hypothesize that unlabeled data and a schema definition are sufficient for building a working task-oriented dialogue system, completely unsupervised. We consider a novel unsupervised setting of only (1) a well-defined API schema (2) a set of unlabeled dialogues between a user and agent. We propose an innovative approach using expectation-maximization (EM) that infers turn-level annotations as latent variables using a noisy channel model to build an end-to-end dialogue agent. Evaluating our approach on the MultiWOZ benchmark, our method more than doubles the dialogue success rate of a strong GPT-3.5 baseline.
%R 10.18653/v1/2024.emnlp-main.473
%U https://aclanthology.org/2024.emnlp-main.473/
%U https://doi.org/10.18653/v1/2024.emnlp-main.473
%P 8283-8300

Markdown (Informal)

[Unsupervised End-to-End Task-Oriented Dialogue with LLMs: The Power of the Noisy Channel](https://aclanthology.org/2024.emnlp-main.473/) (King & Flanigan, EMNLP 2024)

• Unsupervised End-to-End Task-Oriented Dialogue with LLMs: The Power of the Noisy Channel (King & Flanigan, EMNLP 2024)

ACL

• Brendan King and Jeffrey Flanigan. 2024. Unsupervised End-to-End Task-Oriented Dialogue with LLMs: The Power of the Noisy Channel. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 8283–8300, Miami, Florida, USA. Association for Computational Linguistics.