Probing the Robustness of Trained Metrics for Conversational Dialogue Systems

被引:0
|
作者
Deriu, Jan [1 ]
Tuggener, Don [1 ]
von Daeniken, Pius [1 ]
Cieliebak, Mark [1 ]
机构
[1] Zurich Univ Appl Sci ZHAW, Winterthur, Switzerland
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper introduces an adversarial method to stress-test trained metrics to evaluate conversational dialogue systems. The method leverages Reinforcement Learning to find response strategies that elicit optimal scores from the trained metrics. We apply our method to test recently proposed trained metrics. We find that they all are susceptible to giving high scores to responses generated by relatively simple and obviously flawed strategies that our method converges on. For instance, simply copying parts of the conversation context to form a response yields competitive scores or even outperforms responses written by humans.
引用
收藏
页码:750 / 761
页数:12
相关论文
共 50 条
  • [21] STABILITY ROBUSTNESS OF CLOSED-LOOP SYSTEMS IN ANGULAR METRICS
    Liu, Bin
    Li, Wei
    Zhang, Lingchuan
    ASIAN JOURNAL OF CONTROL, 2016, 18 (05) : 1867 - 1876
  • [22] On the Robustness of Dialogue History Representation in Conversational Question Answering: A Comprehensive Study and a New Prompt-based Method
    Gekhman, Zorik
    Oved, Nadav
    Keller, Orgad
    Szpektor, Idan
    Reichart, Roi
    TRANSACTIONS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, 2023, 11 : 351 - 366
  • [23] DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization
    Wu, Zeqiu
    Lu, Bo-Ru
    Hajishirzi, Hannaneh
    Ostendorf, Mari
    2021 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2021), 2021, : 1852 - 1863
  • [24] Dialogue Systems and Conversational Agents for Patients with Dementia: The Human-Robot Interaction
    Russo, Alessandro
    D'Onofrio, Grazia
    Gangemi, Aldo
    Giuliani, Francesco
    Mongiovi, Misael
    Ricciardi, Francesco
    Greco, Francesca
    Cavallo, Filippo
    Dario, Paolo
    Sancarlo, Daniele
    Presutti, Valentina
    Greco, Antonio
    REJUVENATION RESEARCH, 2019, 22 (02) : 109 - 120
  • [25] Knowledge-Based Conversational Recommender Systems Enhanced by Dialogue Policy Learning
    Chen, Keyu
    Sun, Shiliang
    PROCEEDINGS OF THE 10TH INTERNATIONAL JOINT CONFERENCE ON KNOWLEDGE GRAPHS (IJCKG 2021), 2021, : 10 - 18
  • [26] Linguistics-based dialogue simulations to evaluate argumentative conversational recommender systems
    Di Bratto, Martina
    Origlia, Antonio
    Di Maro, Maria
    Mennella, Sabrina
    USER MODELING AND USER-ADAPTED INTERACTION, 2024, 34 (05) : 1581 - 1611
  • [27] VISUAL DIALOGUE THROUGH CONVERSATIONAL DRAWINGS
    DAVIS, JW
    LEONARDO, 1970, 3 (02) : 139 - 147
  • [28] Evaluating and Enhancing the Robustness of Dialogue Systems: A Case Study on a Negotiation Agent
    Cheng, Minhao
    Wei, Wei
    Hsieh, Cho-Jui
    2019 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL HLT 2019), VOL. 1, 2019, : 3325 - 3335
  • [29] Using Knowledge about Misunderstandings to Increase the Robustness of Spoken Dialogue Systems
    Lopez-Cozar, Ramon
    Callejas, Zoraida
    Abalos, Nieves
    Espejo, Gonzalo
    Griol, David
    TEXT, SPEECH AND DIALOGUE, 2010, 6231 : 523 - +
  • [30] Converness: Ontology-driven conversational awareness and context understanding in multimodal dialogue systems
    Meditskos, Georgios
    Kontopoulos, Efstratios
    Vrochidis, Stefanos
    Kompatsiaris, Ioannis
    EXPERT SYSTEMS, 2020, 37 (01)