Dialogue Generation

39 papers with code · Natural Language Processing
Subtask of Dialogue · Text Generation

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.

Source: Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey

Benchmarks

Greatest papers with code

Towards Empathetic Open-domain Conversation Models: a New Benchmark and Dataset

ACL 2019 facebookresearch/ParlAI

One challenge for dialogue agents is recognizing feelings in the conversation partner and replying accordingly, a key communicative skill.

DIALOGUE GENERATION

ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation

26 Jan 2020PaddlePaddle/ERNIE

Current pre-training works in natural language generation pay little attention to the problem of exposure bias on downstream tasks.

 Ranked #1 on Generative Question Answering on CoQA (using extra training data)

ABSTRACTIVE TEXT SUMMARIZATION DIALOGUE GENERATION GENERATIVE QUESTION ANSWERING QUESTION GENERATION

Relevance of Unsupervised Metrics in Task-Oriented Dialogue for Evaluating Natural Language Generation

ICLR 2018 Maluuba/nlg-eval

However, previous work in dialogue response generation has shown that these metrics do not correlate strongly with human judgment in the non task-oriented dialogue setting.

DIALOGUE GENERATION MACHINE TRANSLATION

End-to-end Adversarial Learning for Generative Conversational Agents

28 Nov 2017oswaldoludwig/Seq2seq-Chatbot-for-Keras

This paper presents a new adversarial learning method for generative conversational agents (GCA) besides a new model of GCA.

ADVERSARIAL TRAINING DIALOGUE GENERATION

MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations

ACL 2019 SenticNet/MELD

We propose several strong multimodal baselines and show the importance of contextual and multimodal information for emotion recognition in conversations.

DIALOGUE GENERATION EMOTION RECOGNITION IN CONVERSATION

Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation

2 Jun 2016julianser/hed-dlg-truncated

We introduce the multiresolution recurrent neural network, which extends the sequence-to-sequence framework to model natural language generation as two parallel discrete stochastic processes: a sequence of high-level coarse tokens, and a sequence of natural language tokens.

DIALOGUE GENERATION

Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders

ACL 2017 snakeztc/NeuralDialog-CVAE

While recent neural encoder-decoder models have shown great promise in modeling open-domain conversations, they often generate dull and generic responses.

DECISION MAKING DIALOGUE GENERATION

Adversarial Learning for Neural Dialogue Generation

EMNLP 2017 liuyuemaicha/Adversarial-Learning-for-Neural-Dialogue-Generation-in-Tensorflow

In this paper, drawing intuition from the Turing test, we propose using adversarial training for open-domain dialogue generation: the system is trained to produce sequences that are indistinguishable from human-generated dialogue utterances.

ADVERSARIAL TRAINING DIALOGUE GENERATION

Deep Reinforcement Learning for Dialogue Generation

EMNLP 2016 liuyuemaicha/Deep-Reinforcement-Learning-for-Dialogue-Generation-in-tensorflow

Recent neural models of dialogue generation offer great promise for generating responses for conversational agents, but tend to be shortsighted, predicting utterances one at a time while ignoring their influence on future outcomes.

CHATBOT DIALOGUE GENERATION POLICY GRADIENT METHODS