Related papers: Minimally Supervised Hierarchical Domain Intent Le…
We present our work on Track 2 in the Dialog System Technology Challenges 11 (DSTC11). DSTC11-Track2 aims to provide a benchmark for zero-shot, cross-domain, intent-set induction. In the absence of in-domain training dataset, robust…
Intent understanding plays an important role in dialog systems, and is typically formulated as a supervised learning problem. However, it is challenging and time-consuming to design the intents for a new domain from scratch, which usually…
A key challenge of dialog systems research is to effectively and efficiently adapt to new domains. A scalable paradigm for adaptation necessitates the development of generalizable models that perform well in few-shot settings. In this…
Conversational systems are of primary interest in the AI community. Chatbots are increasingly being deployed to provide round-the-clock support and to increase customer engagement. Many of the commercial bot building frameworks follow a…
Discovering new intents is a crucial task in dialogue systems. Most existing methods are limited in transferring the prior knowledge from known intents to new intents. They also have difficulties in providing high-quality supervised signals…
User queries for a real-world dialog system may sometimes fall outside the scope of the system's capabilities, but appropriate system responses will enable smooth processing throughout the human-computer interaction. This paper is concerned…
Identifying new user intents is an essential task in the dialogue system. However, it is hard to get satisfying clustering results since the definition of intents is strongly guided by prior knowledge. Existing methods incorporate prior…
Recently, research on open domain dialogue systems have attracted extensive interests of academic and industrial researchers. The goal of an open domain dialogue system is to imitate humans in conversations. Previous works on single turn…
While unsupervised domain adaptation methods based on deep architectures have achieved remarkable success in many computer vision tasks, they rely on a strong assumption, i.e. labeled source data must be available. In this work we overcome…
The focus of this work is to investigate unsupervised approaches to overcome quintessential challenges in designing task-oriented dialog schema: assigning intent labels to each dialog turn (intent clustering) and generating a set of intents…
Target-guided open-domain conversation aims to proactively and naturally guide a dialogue agent or human to achieve specific goals, topics or keywords during open-ended conversations. Existing methods mainly rely on single-turn datadriven…
Deriving value from a conversational AI system depends on the capacity of a user to translate the prior knowledge into a configuration. In most cases, discovering the set of relevant turn-level speaker intents is often one of the key steps.…
Most dialogue systems in real world rely on predefined intents and answers for QA service, so discovering potential intents from large corpus previously is really important for building such dialogue services. Considering that most…
Neural network-based clustering has recently gained popularity, and in particular a constrained clustering formulation has been proposed to perform transfer learning and image category discovery using deep learning. The core idea is to…
Intent discovery is the task of inferring latent intents from a set of unlabeled utterances, and is a useful step towards the efficient creation of new conversational agents. We show that recent competitive methods in intent discovery can…
New intent discovery is of great value to natural language processing, allowing for a better understanding of user needs and providing friendly services. However, most existing methods struggle to capture the complicated semantics of…
Recent cross-domain recommendation (CDR) studies assume that disentangled domain-shared and domain-specific user representations can mitigate domain gaps and facilitate effective knowledge transfer. However, achieving perfect…
For companies with customer service, mapping intents inside their conversational data is crucial in building applications based on natural language understanding (NLU). Nevertheless, there is no established automated technique to gather the…
Hierarchical clustering is a popular unsupervised data analysis method. For many real-world applications, we would like to exploit prior information about the data that imposes constraints on the clustering hierarchy, and is not captured by…
Proactively and naturally guiding the dialog from the non-recommendation context (e.g., Chit-chat) to the recommendation scenario (e.g., Music) is crucial for the Conversational Recommender System (CRS). Prior studies mainly focus on…