Dialogue Generation is a fundamental component for real-world virtual assistants such as Siri and Alexa. It is the text generation task that automatically generate a response given a post by the user.
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Generating knowledge grounded responses in both goal and non-goal oriented dialogue systems is an important research challenge.
Dialogue generation models face the challenge of producing generic and repetitive responses.
Learning such transformations is challenging and requires a deep understanding of empathy while maintaining conversation quality through text fluency and specificity to the conversational context.
Based on this dataset, we propose a family of encoder-decoder models leveraging both textual and visual contexts, from coarse-grained image features extracted from CNNs to fine-grained object features extracted from Faster R-CNNs.
Besides, we develop a Graph-Evolving Meta-Learning (GEML) framework that learns to evolve the commonsense graph for reasoning disease-symptom correlations in a new disease, which effectively alleviates the needs of a large number of dialogues.
We study knowledge-grounded dialogue generation with pre-trained language models.
Extensive experiments on two real-world conversation datasets show that our framework significantly reduces gender bias in dialogue models while maintaining the response quality.
However, this task is far from well-explored due to the difficulties of rendering a particular style in coherent responses, especially when the target style is embedded only in unpaired texts that cannot be directly used to train the dialogue model.