Salesforce Research advances AI techniques that pave the path for new AI research directions, innovative products and applications with a positive impact on society. Our team of researchers, engineers, product managers, and designers drive AI innovation across pure research, applied research, and new product incubation- all built on our powerful AI platform. We bring companies and customers together using AI that is explainable, transparent, and accountable. As part of our team you’ll learn unique skills, work with talented people, influence the industry standard for fair and ethical use of artificial intelligence and help us to shape the future of AI.
Long
Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Start
Wenpeng Yin, Nazneen Fatema Rajani, Dragomir Radev, Richard Socher, Caiming Xiong
TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue
Chien-Sheng Wu, Steven C.H. Hoi, Richard Socher, Caiming Xiong
Evaluating the Factual Consistency of Abstractive Text Summarization
Wojciech Kryscinski, Bryan McCann, Caiming Xiong, Richard Socher
Probing Task-Oriented Dialogue Representation from Language Models
Chien-Sheng Wu, Caiming Xiong
Mind Your Inflections! Improving NLP for Non-Standard Englishes with Base-Inflection Encoding
Samson Tan, Shafiq Joty, Lav Varshney, Min-Yen Kan
Response Selection for Multi-Party Conversations with Dynamic Topic Tracking
Weishi Wang, Steven C.H. Hoi, Shafiq Joty
VD-BERT: A Unified Vision and Dialog Transformer with BERT
Yue Wang, Shafiq Joty, Michael Lyu, Irwin King, Caiming Xiong, Steven C.H. Hoi
Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading
Yifan Gao, Chien-Sheng Wu, Jingjing Li, Shafiq Joty, Steven C.H. Hoi, Caiming Xiong, Irwin King, Michael Lyu
BiST: Bi-directional Spatio-Temporal Reasoning for Video-Grounded Dialogues
Hung Le, Doyen Sahoo, Nancy Chen, Steven C.H. Hoi
UniConv: A Unified Conversational Neural Architecture for Multi-domain Task-oriented Dialogues
Hung Le, Doyen Sahoo, Chenghao Liu, Nancy Chen, Steven C.H. Hoi
Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference
Jianguo Zhang, Kazuma Hashimoto, Wenhao Liu, Chien-Sheng Wu, Yao Wan, Philip Yu, Richard Socher, Caiming Xiong
Short
The Thieves on Sesame Street are Polyglots - Extracting Multilingual Models from Monolingual APIs
Nitish Shirish Keskar, Bryan McCann, Caiming Xiong, Richard Socher
Simple Data Augmentation with the Mask Token Improves Domain Adaptation for Dialog Act Tagging
Semih Yavuz, Kazuma Hashimoto, Wenhao Liu, Nitish Shirish Keskar, Richard Socher, Caiming Xiong
Findings
Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing
Xi Victoria Lin, Richard Socher, Caiming Xiong
Improving Limited Labeled Dialogue State Tracking with Self-Supervision
Chien-Sheng Wu, Steven C.H. Hoi, Caiming Xiong
Composed Variational Natural Language Generation for Few-shot Intents
Congying Xia, Caiming Xiong, Philip Yu, Richard Socher