About

I am a Senior Applied Scientist at Amazon Web Services. My research interests are in the fields of Natural Language Processing, Machine Learning and Artificial Intelligence. My recent research focuses are document-grounded dialogue modeling, discourse analysis and interactive text generation based on multimodal data.

  • Office: Building JFK 14 (7 W. 34th St. New York, NY)
  • Email: sofeng@amazon.com

Song FENG

Publications

DG2: Data Augmentation Through Document Grounded Dialogue Generation
Qingyang Wu, Song Feng, Derek Chen, Sachindra Joshi, Luis A. Lastras, Zhou Yu.
The 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), 2022

MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documents
Song Feng, Siva Sankalp Patel, Hui Wan, Sachindra Joshi.
Empirical Methods in Natural Language Processing (EMNLP), 2021
[leaderboard] [Shared Task - DialDoc Workshop@ACL2022]

Does Structure Matter? Encoding Documents for Machine Reading Comprehension
Hui Wan, Song Feng, Chulaka Gunasekara, Siva Sankalp Patel, Sachindra Joshi, Luis Lastras.
North American Chapter of the Association for Computational Linguistics (NAACL-HLT), 2021

Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks
Hanjie Chen, Song Feng, Jatin Ganhotra, Hui Wan, Chulaka Gunasekara, Sachindra Joshi, Yangfeng Ji.
North American Chapter of the Association for Computational Linguistics (NAACL-HLT), 2021

doc2dial: A Goal-Oriented Document-Grounded Dialogue Dataset
Song Feng, Hui Wan, Chulaka Gunasekara, Siva Sankalp Patel, Sachindra Joshi, Luis Lastras.
Empirical Methods in Natural Language Processing (EMNLP), 2020
[leaderboard] [Shared Task - DialDoc Workshop@ACL2021]

Implicit Discourse Relation Classification: We Need to Talk About Evaluation
Najoung Kim, Song Feng, Chulaka Gunasekara, Luis A. Lastras.
Annual Conference of the Association for Computational Linguistics (ACL) , 2020

Doc2Dial: a Framework for Dialogue Composition Grounded in Documents
Song Feng, Kshitij Fadnis, Vera Liao, Luis Lastras.
The Thirty-Fourth Conference on Artificial Intelligence (AAAI), 2020

Drill-down: Interactive Retrieval of Complex Scenes using Natural Language Queries
Fuwen Tan, Paola Cascante-Bonilla, Hui Wu, Xiaoxiao Guo, Song Feng, Vicente Ordonez.
Conference on Neural Information Processing Systems. NeurIPS, 2019
https://arxiv.org/abs/1911.03826

Chat-crowd: A Dialog-based Platform for Visual Layout Composition
Paola Cascante-Bonilla, Xuwang Yin, Vicente Ordonez, Song Feng.
North American Chapter of the Association for Computational Linguistics (NAACL), 2019

Text2Scene: Generating Compositional Scenes from Textual Descriptions
Fuwen Tan, Song Feng, Vicente Ordonez.
International Conference on Computer Vision and Pattern Recognition (CVPR), 2019

World Knowledge for Semantic Parsing with Abstract Meaning Representation
Charlie Welch, Jonathan Kummerfeld, Song Feng, Rada Mihalcea.
Language Resources and Evaluation Conference (LREC), 2018

A Unified Implicit Dialog Framework for Conversational Commerce
Song Feng, R. Chulaka Gunasekara, Sunil Shashidhara, Kshitij Fadnis, Lazaros C. Polymenakos.
The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI), 2018

Please check Google Scholar for my other publications.