Related papers: MDD-Eval: Self-Training on Augmented Data for Mult…
Large Language Models have demonstrated remarkable capabilities in open-domain dialogues. However, current methods exhibit suboptimal performance in service dialogues, as they rely on noisy, low-quality human conversation data. This…
Automatic dialogue response evaluator has been proposed as an alternative to automated metrics and human evaluation. However, existing automatic evaluators achieve only moderate correlation with human judgement and they are not robust. In…
Goal-oriented dialog systems enable users to complete specific goals like requesting information about a movie or booking a ticket. Typically the dialog system pipeline contains multiple ML models, including natural language understanding,…
With the rapid development of artificial intelligence, conversational bots have became prevalent in mainstream E-commerce platforms, which can provide convenient customer service timely. To satisfy the user, the conversational bots need to…
Large language models (LLMs) are powerful dialogue agents, but specializing them towards fulfilling a specific function can be challenging. Instructing tuning, i.e. tuning models on instruction and sample responses generated by humans…
End-to-end Task-oriented Dialogue Systems (TDSs) have attracted a lot of attention for their superiority (e.g., in terms of global optimization) over pipeline modularized TDSs. Previous studies on end-to-end TDSs use a single-module model…
A major bottleneck for building statistical spoken dialogue systems for new domains and applications is the need for large amounts of training data. To address this problem, we adopt the multi-dimensional approach to dialogue management and…
Improving user experience of a dialogue system often requires intensive developer effort to read conversation logs, run statistical analyses, and intuit the relative importance of system shortcomings. This paper presents a novel approach to…
As an agent-level reasoning and coordination paradigm, Multi-Agent Debate (MAD) orchestrates multiple agents through structured debate to improve answer quality and support complex reasoning. However, existing research on MAD suffers from…
Domain adaptation is an essential task in dialog system building because there are so many new dialog tasks created for different needs every day. Collecting and annotating training data for these new tasks is costly since it involves real…
Developing high-performing dialogue systems benefits from the automatic identification of undesirable behaviors in system responses. However, detecting such behaviors remains challenging, as it draws on a breadth of general knowledge and…
Evaluation of open-domain dialogue systems is highly challenging and development of better techniques is highlighted time and again as desperately needed. Despite substantial efforts to carry out reliable live evaluation of systems in…
Non-task-oriented dialog models suffer from poor quality and non-diverse responses. To overcome limited conversational data, we apply Simulated Multiple Reference Training (SMRT; Khayrallah et al., 2020), and use a paraphraser to simulate…
Dialogue assistants are rapidly becoming an indispensable daily aid. To avoid the significant effort needed to hand-craft the required dialogue flow, the Dialogue Management (DM) module can be cast as a continuous Markov Decision Process…
One challenge for evaluating current sequence- or dialogue-level chatbots, such as Empathetic Open-domain Conversation Models, is to determine whether the chatbot performs in an emotionally consistent way. The most recent work only…
A conversational agent (chatbot) is a piece of software that is able to communicate with humans using natural language. Modeling conversation is an important task in natural language processing and artificial intelligence. While chatbots…
Open-domain dialogue systems have started to engage in continuous conversations with humans. Those dialogue systems are required to be adjusted to the human interlocutor and evaluated in terms of their perspective. However, it is…
We present the first complete spoken dialogue system driven by a multi-dimensional statistical dialogue manager. This framework has been shown to substantially reduce data needs by leveraging domain-independent dimensions, such as social…
Tuning language models for dialogue generation has been a prevalent paradigm for building capable dialogue agents. Yet, traditional tuning narrowly views dialogue generation as resembling other language generation tasks, ignoring the role…
There is an increasing focus on model-based dialog evaluation metrics such as ADEM, RUBER, and the more recent BERT-based metrics. These models aim to assign a high score to all relevant responses and a low score to all irrelevant…