Search Results for author:
Found 28 papers, 14 papers with code
Think Before You Speak: Learning to Generate Implicit Knowledge for Response Generation by Self-Talk
We further investigate can such models identify when to generate implicit background knowledge and when it is not necessary.
Policy-Driven Neural Response Generation for Knowledge-Grounded Dialog Systems
Open-domain dialog systems aim to generate relevant, informative and engaging responses.
Rethinking the Role of Scale for In-Context Learning: An Interpretability-based Case Study at 66 Billion Scale
Using a 66 billion parameter language model (OPT-66B) across a diverse set of 14 downstream tasks, we find this is indeed the case: $\sim$70% of attention heads and $\sim$20% of feed forward networks can be removed with minimal decline in task performance.
Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation
We consider the problem of multi-agent navigation and collision avoidance when observations are limited to the local neighborhood of each agent.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Differentially Private Stochastic Convex Optimization for Network Routing Applications
In this paper, we present a differentially private algorithm for network routing problems.
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 with non-embedding parameter counts ranging from 700M to 9. 3B, their subsequent distillation into smaller models ranging from 17M-170M parameters, and their application to the Natural Language Understanding (NLU) component of a virtual assistant system.
Cross-Lingual Natural Language Inference
intent-classification
+5
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models.
Online Learning for Traffic Routing under Unknown Preferences
at each period, we show that our approach obtains an expected regret and road capacity violation of $O(\sqrt{T})$, where $T$ is the number of periods over which tolls are updated.
Multi-Sentence Knowledge Selection in Open-Domain Dialogue
Incorporating external knowledge sources effectively in conversations is a longstanding problem in open-domain dialogue research.
Analyzing the Limits of Self-Supervision in Handling Bias in Language
We define three broad classes of task descriptions for these tasks: statement, question, and completion, with numerous lexical variants within each class.
Think Before You Speak: Explicitly Generating Implicit Commonsense Knowledge for Response Generation
Implicit knowledge, such as common sense, is key to fluid human conversations.
"How Robust r u?": Evaluating Task-Oriented Dialogue Systems on Spoken Conversations
Most prior work in dialogue modeling has been on written conversations mostly because of existing data sets.
Commonsense-Focused Dialogues for Response Generation: An Empirical Study
Moreover, existing dialogue datasets do not explicitly focus on exhibiting commonsense as a facet.
Generative Conversational Networks
We show an average improvement of 35% in intent detection and 21% in slot tagging over a baseline model trained from the seed data.
VISITRON: Visual Semantics-Aligned Interactively Trained Object-Navigator
Interactive robots navigating photo-realistic environments need to be trained to effectively leverage and handle the dynamic nature of dialogue in addition to the challenges underlying vision-and-language navigation (VLN).
Incorporating Commonsense Knowledge Graph in Pretrained Models for Social Commonsense Tasks
Pretrained language models have excelled at many NLP tasks recently; however, their social intelligence is still unsatisfactory.
Go Beyond Plain Fine-tuning: Improving Pretrained Models for Social Commonsense
Towards improving language models' social intelligence, we focus on the Social IQA dataset, a task requiring social and emotional commonsense reasoning.
Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access Track in DSTC9
This challenge track aims to expand the coverage of task-oriented dialogue systems by incorporating external unstructured knowledge sources.
Overview of the Ninth Dialog System Technology Challenge: DSTC9
Interactive evaluation of dialog, and 4.
Are Neural Open-Domain Dialog Systems Robust to Speech Recognition Errors in the Dialog History? An Empirical Study
Large end-to-end neural open-domain chatbots are becoming increasingly popular.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access
In this paper, we propose to expand coverage of task-oriented dialogue systems by incorporating external unstructured knowledge sources.
Policy-Driven Neural Response Generation for Knowledge-Grounded Dialogue Systems
In this paper, we propose using a dialogue policy to plan the content and style of target responses in the form of an action plan, which includes knowledge sentences related to the dialogue context, targeted dialogue acts, topic information, etc.
Sentiment Analysis Using Simplified Long Short-term Memory Recurrent Neural Networks
We evaluate two of these models on the dataset.
Topical-Chat: Towards Knowledge-Grounded Open-Domain Conversations
We introduce Topical-Chat, a knowledge-grounded human-human conversation dataset where the underlying knowledge spans 8 broad topics and conversation partners don’t have explicitly defined roles, to help further research in open-domain conversational AI.
Advancing the State of the Art in Open Domain Dialog Systems through the Alexa Prize
In the second iteration of the competition in 2018, university teams advanced the state of the art by using context in dialog models, leveraging knowledge graphs for language understanding, handling complex utterances, building statistical and hierarchical dialog managers, and leveraging model-driven signals from user responses.
Social Interaction in the Flickr Social Network
Online social networking sites such as Facebook, Twitter and Flickr are among the most popular sites on the Web, providing platforms for sharing information and interacting with a large number of people.
Social and Information Networks C.4; H.3.5; J.4
Get 'em Moles! : Learning Spelling and Pronunciation through an Educational Game
Get 'em Moles!
Human-Computer Interaction K.3.1
Bublz! : Playing with Bubbles to Develop Mathematical Thinking
We encounter mathematical problems in various forms in our lives, thus making mathematical thinking an important human ability.
Human-Computer Interaction History and Overview K.3.1
