Related papers: A Conditional Variational Framework for Dialog Gen…

In open-domain conversational systems, it is important but challenging to leverage background knowledge. We can use the incorporation of knowledge to make the generation of dialogue controllable, and can generate more diverse sentences that…

Evaluating AI systems that interact with humans requires understanding their behavior across diverse user populations, but collecting representative human data is often expensive or infeasible, particularly for novel technologies or…

We present a novel architecture for explainable modeling of task-oriented dialogues with discrete latent variables to represent dialogue actions. Our model is based on variational recurrent neural networks (VRNN) and requires no explicit…

Generative classifiers offer potential advantages over their discriminative counterparts, namely in the areas of data efficiency, robustness to data shift and adversarial examples, and zero-shot learning (Ng and Jordan,2002; Yogatama et…

Human dialogues are scenario-based and appropriate responses generally relate to the latent context knowledge entailed by the specific scenario. To enable responses that are more meaningful and context-specific, we propose to improve…

Despite the great promise of Transformers in many sequence modeling tasks (e.g., machine translation), their deterministic nature hinders them from generalizing to high entropy tasks such as dialogue response generation. Previous work…

In human dialogue, a single query may elicit numerous appropriate responses. The Transformer-based dialogue model produces frequently occurring sentences in the corpus since it is a one-to-one mapping function. CVAE is a technique for…

Open-domain dialogue systems aim to generate relevant, informative and engaging responses. Seq2seq neural response generation approaches do not have explicit mechanisms to control the content or style of the generated response, and…

In response generation task, proper sentimental expressions can obviously improve the human-like level of the responses. However, for real application in online systems, high QPS (queries per second, an indicator of the flow capacity of…

Providing dialogue agents with a profile representation can improve their consistency and coherence, leading to better conversations. However, current profile-based dialogue datasets for training such agents contain either explicit profile…

The natural language generation (NLG) component of a spoken dialogue system (SDS) usually needs a substantial amount of handcrafting or a well-labeled dataset to be trained on. These limitations add significantly to development costs and…

Large, general purpose language models have demonstrated impressive performance across many different conversational domains. While multi-domain language models achieve low overall perplexity, their outputs are not guaranteed to stay within…

Research on dialogue constructiveness assessment focuses on (i) analysing conversational factors that influence individuals to take specific actions, win debates, change their perspectives or broaden their open-mindedness and (ii)…

Medical dialogue generation aims to generate responses according to a history of dialogue turns between doctors and patients. Unlike open-domain dialogue generation, this requires background knowledge specific to the medical domain.…

While research on dialogue response generation has primarily focused on generating coherent responses conditioning on textual context, the critical question of when to respond grounded on the temporal context remains underexplored. To…

The ability of large language models (LLMs) to process and reason over long textual inputs is critical for a wide range of real-world applications. However, progress in this area is significantly constrained by the absence of high-quality,…

Neural generative models have been become increasingly popular when building conversational agents. They offer flexibility, can be easily adapted to new domains, and require minimal domain engineering. A common criticism of these systems is…

We study open domain dialogue generation with dialogue acts designed to explain how people engage in social chat. To imitate human behavior, we propose managing the flow of human-machine interactions with the dialogue acts as policies. The…

We present an empirical investigation of pre-trained Transformer-based auto-regressive language models for the task of open-domain dialogue generation. Training paradigm of pre-training and fine-tuning is employed to conduct the parameter…

Models trained on large unlabeled corpora of human interactions will learn patterns and mimic behaviors therein, which include offensive or otherwise toxic behavior and unwanted biases. We investigate a variety of methods to mitigate these…