Explaining Solutions to Physical Reasoning Tasks

We show that deep neural models can describe common sense physics in a valid and sufficient way that is also generalizable. Our ESPRIT framework is trained on a new dataset with physics simulations and descriptions that we collected and have open-sourced.

05 May 2020 • Nazneen Rajani #research

ERASER: A Benchmark to Evaluate Rationalized NLP Models

Many NLP applications today deploy state-of-the-art deep neural networks that are essentially black-boxes. One of the goals of Explainable AI (XAI) is to have AI models reveal why and how they make their predictions so that these predictions are interpretable by a human. But work in this direction has been

08 Nov 2019 • Nazneen Rajani #research

Living Ethics in AI: How to Expand from Principles to Impact

Published: August 6, 2019 Earlier this year, Danielle Cass and I ran a workshop with 23 ethical AI practitioners from 15 organizations and shared out insights of what they are doing that has been successful and the open questions or challenges they are working through. A few months later, Matt

06 Aug 2019 • Kathy Baxter #ethics

Q&A with Salesforce Research Intern Kevin (Chih-Yao) Ma on Self-Monitoring Navigation Agent via Auxiliary Progress Estimation

For some, the world we live in today can be represented as data in high-dimensional spatiotemporal space—which we humans typically use language to describe, interpret, and reason about. For Salesforce Research Intern, Kevin (Chih-Yao) Ma, this topic became a key focal point in his research “Self-Monitoring Navigation Agent via

01 May 2019 • Alexandria Murray #news

Salesforce Research at ICLR 2019

May 6th - May 9th @ Ernest N. Morial Convention Center, New Orleans ABOUT:Salesforce is excited to be a diamond sponsor of the Seventh International Conference on Learning Representations happening Monday, May 6th through Thursday, May 9th in New Orleans, Louisiana. We encourage you to stop by our Salesforce Booth

22 Apr 2019 • Alexandria Murray #news

Q&A with Salesforce Research Intern Akhilesh Gotmare on how "Optimization and Machine Learning" led him to ICLR.

In the research paper, “A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and Distillation” Futureforce PhD Intern Akhilesh Gotmare, worked with Research Scientist Nitish Shirish Keskar, Director of Research Caiming Xiong, and Salesforce Chief Scientist Richard Socher, to leverage recent tools built specifically for analyzing deep networks,

16 Apr 2019 • Alexandria Murray #news

Ethics in AI research papers and articles

This is my obsessively curated list of research papers and articles on ethics in AI that I have been collecting over the years. Ones in bold are those that I refer back to and found particularly useful. Let me know if I am missing your favorites.

20 Jan 2019 • Kathy Baxter #ethics

The Natural Language Decathlon

Deep learning has significantly improved state-of-the-art performance for natural language processing tasks like machine translation, summarization, question answering, and text classification.

20 Jun 2018 • Bryan McCann #research

Interpretable Counting for Visual Question Answering

Learning to answer open-ended questions about images, a task known as visual question answering (VQA), has received much attention over the last several years. VQA has been put forth as a benchmark for complete scene understanding and flexible reasoning, two fundamental goals of AI.

14 Dec 2017 • Alex Trott #research

Improving end-to-end Speech Recognition Models

Speech recognition has been successfully depolyed on various smart devices, and is changing the way we interact with them. Traditional phonetic-based recognition approaches require training of separate components such as pronouciation, acoustic and language model.

14 Dec 2017 • Yingbo Zhou #research

How to Talk to Your Database

A vast amount of today’s information is stored in relational databases. These databases provide the foundation of systems such as medical records, financial markets, and electronic commerce.

29 Aug 2017 • Victor Zhong #research

Learned in Translation: Contextualized Word Vectors

There are times when word vectors are initialized to lists of random numbers before a model is trained for a specific task, but it is also quite common to initialize the word vectors of a model with those obtained by running methods like word2vec, GloVe, or FastText.

31 Jul 2017 • Bryan McCann #research