Over the last several years, end-to-end neural conversational agents have vastly improved in their ability to carry a chit-chat conversation with humans.
Conversational agents trained on large unlabeled corpora of human interactions will learn patterns and mimic behaviors therein, which include offensive or otherwise toxic behavior.
Open-domain dialogue agents have vastly improved, but still confidently hallucinate knowledge or express doubt when asked straightforward questions.
As argued in de Vries et al. (2020), crowdsourced data has the issues of lack of naturalness and relevance to real-world use cases, while the static dataset paradigm does not allow for a model to learn from its experiences of using language (Silver et al., 2013).
We present our view of what is necessary to build an engaging open-domain conversational agent: covering the qualities of such an agent, the pieces of the puzzle that have been built so far, and the gaping holes we have not filled yet.
We show our classifiers prove valuable for a variety of important applications, such as controlling for gender bias in generative models, detecting gender bias in arbitrary text, and shed light on offensive language in terms of genderedness.
Dialogue research tends to distinguish between chit-chat and goal-oriented tasks.
Models often easily learn biases present in the training data, and their predictions directly reflect this bias.
Text style transfer is usually performed using attributes that can take a handful of discrete values (e. g., positive to negative reviews).
We introduce dodecaDialogue: a set of 12 tasks that measures if a conversational agent can communicate engagingly with personality and empathy, ask questions, answer questions by utilizing knowledge resources, discuss topics and situations, and perceive and converse about images.
We introduce a new large-scale NLI benchmark dataset, collected via an iterative, adversarial human-and-model-in-the-loop procedure.
The detection of offensive language in the context of a dialogue has become an increasingly important application of natural language processing.
We analyze the ingredients necessary for successful grounding in this setting, and how each of these factors relate to agents that can talk and act successfully.
We describe the setting and results of the ConvAI2 NeurIPS competition that aims to further the state-of-the-art in open-domain chatbots.
In open-domain dialogue intelligent agents should exhibit the use of knowledge, however there are few convincing demonstrations of this to date.
Sequence generation models for dialogue are known to have several problems: they tend to produce short, generic sentences that are uninformative and unengaging.
Chit-chat models are known to have several problems: they lack specificity, do not display a consistent personality and are often not very captivating.
Ranked #4 on Dialogue Generation on Persona-Chat