research
∙
05/22/2023
Towards Dialogue Systems with Agency in Human-AI Collaboration Tasks
Agency, the capacity to proactively shape events, is crucial to how huma...
share
research
∙
03/02/2023
Interactive Text Generation
Users interact with text, image, code, or other editors on a daily basis...
research
∙
12/04/2022
Grounded Keys-to-Text Generation: Towards Factual Open-Ended Generation
Large pre-trained language models have recently enabled open-ended gener...
research
∙
06/22/2022
GODEL: Large-Scale Pre-Training for Goal-Directed Dialog
We introduce GODEL (Grounded Open Dialogue Language Model), a large pre-...
research
∙
12/12/2021
Towards More Efficient Insertion Transformer with Fractional Positional Encoding
Auto-regressive neural sequence models have been shown to be effective a...
research
∙
06/14/2021
Automatic Document Sketching: Generating Drafts from Analogous Texts
The advent of large pre-trained language models has made it possible to ...
research
∙
05/14/2021
Joint Retrieval and Generation Training for Grounded Text Generation
Recent advances in large-scale pre-training such as GPT-3 allow seemingl...
research
∙
04/18/2021
A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation
Large pretrained generative models like GPT-3 often suffer from hallucin...
research
∙
04/16/2021
An Adversarially-Learned Turing Test for Dialog Generation Models
The design of better automated dialogue evaluation metrics offers the po...
research
∙
01/17/2021
What Makes Good In-Context Examples for GPT-3?
GPT-3 has attracted lots of attention due to its superior performance ac...
research
∙
12/21/2020
Narrative Incoherence Detection
Motivated by the increasing popularity of intelligent editing assistant,...
research
∙
10/24/2020
Text Editing by Command
A prevailing paradigm in neural text generation is one-shot generation, ...
research
∙
10/16/2020
Substance over Style: Document-Level Targeted Content Transfer
Existing language models excel at writing from scratch, but many real-wo...
research
∙
09/16/2020
Contextualized Perturbation for Textual Adversarial Attack
Adversarial examples expose the vulnerabilities of natural language proc...
research
∙
09/15/2020
Dialogue Response Ranking Training with Large-Scale Human Feedback Data
Existing open-domain dialog models are generally trained to minimize the...
research
∙
06/18/2020
Reparameterized Variational Divergence Minimization for Stable Imitation
While recent state-of-the-art results for adversarial imitation-learning...
research
∙
05/19/2020
A Recipe for Creating Multimodal Aligned Datasets for Sequential Tasks
Many high-level procedural tasks can be decomposed into sequences of ins...
research
∙
05/17/2020
MixingBoard: a Knowledgeable Stylized Integrated Text Generation Platform
We present MixingBoard, a platform for quickly building demos with a foc...
research
∙
05/01/2020
A Controllable Model of Grounded Response Generation
Current end-to-end neural conversation models inherently lack the flexib...
research
∙
05/01/2020
POINTER: Constrained Text Generation via Insertion-based Generative Pre-training
Large-scale pre-trained language models, such as BERT and GPT-2, have ac...
research
∙
11/08/2019
Unsupervised Common Question Generation from Multiple Documents using Reinforced Contrastive Coordinator
Web search engines today return a ranked list of document links in respo...
research
∙
11/01/2019
DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation
We present a large, tunable neural conversational response generation mo...
research
∙
09/03/2019
Structuring Latent Spaces for Stylized Response Generation
Generating responses in a targeted style is a useful yet challenging tas...
research
∙
08/25/2019
Domain Adaptive Text Style Transfer
Text style transfer without parallel data has achieved some practical su...
research
∙
06/06/2019
Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading
Although neural conversation models are effective in learning how to pro...
research
∙
03/13/2019
Consistent Dialogue Generation with Self-supervised Feature Learning
Generating responses that are consistent with the dialogue context is on...
research
∙
02/28/2019
Jointly Optimizing Diversity and Relevance in Neural Response Generation
Although recent neural conversation models have shown great potential, t...
research
∙
01/11/2019
Dialog System Technology Challenge 7
This paper introduces the Seventh Dialog System Technology Challenges (D...
research
∙
12/10/2018
Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Intervention
We present Vision-based Navigation with Language-based Assistance (VNLA)...
research
∙
09/16/2018
Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization
Responses generated by neural conversational models tend to lack informa...
research
∙
09/04/2018
Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints
Neural conversation models tend to generate safe, generic responses for ...
research
∙
10/20/2017
Multi-Task Learning for Speaker-Role Adaptation in Neural Conversation Models
Building a persona-based conversation agent is challenging owing to the ...
research
∙
02/07/2017
A Knowledge-Grounded Neural Conversation Model
Neural network models are capable of generating extremely natural soundi...
research
∙
01/28/2017
Image-Grounded Conversations: Multimodal Context for Natural Question and Response Generation
The popularity of image sharing on social media and the engagement it cr...
research
∙
03/19/2016
A Persona-Based Neural Conversation Model
We present persona-based models for handling the issue of speaker consis...
research
∙
10/11/2015
A Diversity-Promoting Objective Function for Neural Conversation Models
Sequence-to-sequence neural network models for generation of conversatio...
research
∙
06/23/2015
deltaBLEU: A Discriminative Metric for Generation Tasks with Intrinsically Diverse Targets
We introduce Discriminative BLEU (deltaBLEU), a novel metric for intrins...
research
∙
06/22/2015