Stephen Roller
24 papers · 2012–2024 · 10 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (46) π Academic Marathon Β· Half π Conference Polyglot Β· Gold π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π§¬
Topic Evolution
π€
Dynamic Duo
(11)
π
Trend Setter
β
The Questioner
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
ποΈ
Keyword Collector
(82)
Venues
Top co-authors
Research topics
Machine Learning
(12)
Natural Language Processing
(10)
Artificial Intelligence
(9)
Core AI
(9)
Generation
(9)
Deep Learning
(8)
Learning Types Β· Machine Learning
(6)
Architectures
(4)
Core Methods
(4)
Learning Types Β· Deep Learning
(4)
Models
(4)
Optimization & Theory
(4)
Resources & Methods
(3)
Application Areas
(2)
Applications
(2)
Keywords
dialogue system
(6)
text generation
(4)
conversational agent
(3)
language model
(2)
conversational ai
(2)
unlikelihood training
(2)
knowledge retrieval
(2)
sequence modeling
(2)
text corpus
(2)
open-domain dialogue
(2)
human evaluation
(2)
dialogue generation
(2)
language modeling
(1)
bayesian inference
(1)
multi-task learning
(1)
transformer architecture
(1)
information extraction
(1)
maximum likelihood
(1)
lexical semantics
(1)
reinforcement learning
(1)
Papers
Leveraging Implicit Feedback from Deployment Data in Dialogue
EACL 2024
Scaling Laws for Generative Mixed-Modal Language Models
ICML 2023
Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agents
ACL 2022
Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion
EMNLP 2022
Staircase Attention for Recurrent Processing of Sequences
NeurIPS 2022
Adding Chit-Chat to Enhance Task-Oriented Dialogues
NAACL 2021
Hash Layers For Large Sparse Models
NeurIPS 2021
Not All Memories are Created Equal: Learning to Forget by Expiring
ICML 2021
Recipes for Building an Open-Domain Chatbot
EACL 2021
Donβt Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training
ACL 2020
Neural Text Generation With Unlikelihood Training
ICLR 2020
The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents
ACL 2020
Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings
ACL 2019
What makes a good conversation? How controllable attributes affect human judgments
NAACL 2019
Wizard of Wikipedia: Knowledge-Powered Conversational Agents
ICLR 2019
Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora
ACL 2018
Distributional Modeling on a Diet: One-shot Word Learning from Text Only
IJCNLP 2017
MGNC-CNN: A Simple Approach to Exploiting Multiple Word Embeddings for Sentence Classification
NAACL 2016
PIC a Different Word: A Simple Model for Lexical Substitution in Context
NAACL 2016
Relations such as Hypernymy: Identifying and Exploiting Hearst Patterns in Distributional Vectors for Lexical Entailment
EMNLP 2016
Inclusive yet Selective: Supervised Distributional Hypernymy Detection
COLING 2014
UTexas: Natural Language Semantics using Distributional Semantics and Probabilistic Logic
SemEval 2014
A Multimodal LDA Model integrating Textual, Cognitive and Visual Modalities
EMNLP 2013
Supervised Text-based Geolocation Using Language Models on an Adaptive Grid
EMNLP 2012