research
∙
08/02/2022
AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model
In this work, we demonstrate that multilingual large-scale sequence-to-s...
share
research
∙
06/15/2022
Alexa Teacher Model: Pretraining and Distilling Multi-Billion-Parameter Encoders for Natural Language Understanding Systems
We present results from a large-scale experiment on pretraining encoders...
research
∙
10/01/2021
TEACh: Task-driven Embodied Agents that Chat
Robots operating in human spaces must be able to engage in natural langu...
research
∙
06/15/2021
Generative Conversational Networks
Inspired by recent work in meta-learning and generative teaching network...
research
∙
05/24/2021
Learning Better Visual Dialog Agents with Pretrained Visual-Linguistic Representation
GuessWhat?! is a two-player visual dialog guessing game where player A a...
research
∙
03/26/2021
Correcting Automated and Manual Speech Transcription Errors using Warped Language Models
Masked language models have revolutionized natural language processing s...
research
∙
01/09/2021
Are We There Yet? Learning to Localize in Embodied Instruction Following
Embodied instruction following is a challenging problem requiring an age...
research
∙
12/29/2020
Can You be More Social? Injecting Politeness and Positivity into Task-Oriented Conversational Agents
Goal-oriented conversational agents are becoming prevalent in our daily ...
research
∙
12/02/2020
Interactive Teaching for Conversational AI
Current conversational AI systems aim to understand a set of pre-designe...
research
∙
11/21/2020
LRTA: A Transparent Neural-Symbolic Reasoning Framework with Modular Supervision for Visual Question Answering
The predominant approach to visual question answering (VQA) relies on en...
research
∙
11/05/2020
Language Model is All You Need: Natural Language Understanding as Question Answering
Different flavors of transfer learning have shown tremendous impact in a...
research
∙
11/03/2020
Warped Language Models for Noise Robust Language Understanding
Masked Language Models (MLM) are self-supervised neural networks trained...
research
∙
09/25/2020
Controllable Text Generation with Focused Variation
This work introduces Focused-Variation Network (FVN), a novel model to c...
research
∙
03/20/2020
Improving Embedding Extraction for Speaker Verification with Ladder Network
Speaker verification is an established yet challenging task in speech pr...
research
∙
02/16/2020
Multi-Task Siamese Neural Network for Improving Replay Attack Detection
Automatic speaker verification systems are vulnerable to audio replay at...
research
∙
01/28/2020
Joint Contextual Modeling for ASR Correction and Language Understanding
The quality of automatic speech recognition (ASR) is critical to Dialogu...
research
∙
01/24/2020
Exploration Based Language Learning for Text-Based Games
This work presents an exploration and imitation-learning-based agent cap...
research
∙
01/17/2020
Plato Dialogue System: A Flexible Conversational AI Research Platform
As the field of Spoken Dialogue Systems and Conversational AI grows, so ...
research
∙
08/06/2019
Flexibly-Structured Model for Task-Oriented Dialogues
This paper proposes a novel end-to-end architecture for task-oriented di...
research
∙
07/18/2019
OCC: A Smart Reply System for Efficient In-App Communications
Smart reply systems have been developed for various messaging platforms....
research
∙
07/11/2019
Collaborative Multi-Agent Dialogue Model Training Via Reinforcement Learning
We present the first complete attempt at concurrently training conversat...
research
∙
11/11/2018
User Modeling for Task Oriented Dialogues
We introduce end-to-end neural network based models for simulating users...
research
∙
04/18/2018
Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems
In this work, we present a hybrid learning method for training task-orie...
research
∙
01/15/2018
Building a Conversational Agent Overnight with Dialogue Self-Play
We propose Machines Talking To Machines (M2M), a framework combining aut...
research
∙
11/29/2017
End-to-End Optimization of Task-Oriented Dialogue Model with Deep Reinforcement Learning
In this paper, we present a neural network based task-oriented dialogue ...
research
∙
07/07/2017
Towards Zero-Shot Frame Semantic Parsing for Domain Scaling
State-of-the-art slot filling models for goal-oriented human/machine con...
research
∙
05/08/2017
Sequential Dialogue Context Modeling for Spoken Language Understanding
Spoken Language Understanding (SLU) is a key component of goal oriented ...
research
∙
09/12/2016