IBM Research AI at the AAAI Conference on Artificial Intelligence

Share this post:

At the 32nd AAAI conference on artificial intelligence, IBM will share significant progress from its AI research team, including technical papers as well as results from the company’s ongoing collaboration with academic institutions through the MIT IBM Watson AI Lab and the AI Horizons Network.

Among the featured IBM AI research projects that will be detailed at AAAI is a new system called Reinforced Ranker-Reader (R^3) for Open-Domain Question Answering, a new approach to enable machines to correctly answer questions. The system breaks the problem down into three simple steps: retrieve a small number of documents where the answer might be; rank those documents according to how likely they are to contain the answer; and then “read” the answer from the most likely document.  The key innovation is in combining all these pieces together in a single neural network which learns using how to combine ranking and reading using deep reinforcement learning.  The team’s results show that their method significantly improves on the state of the art for multiple open-domain QA datasets.

Another paper being presented at AAAI, “DLPaper2Code: Auto-generation of Code from Deep Learning Research Papers,” details a technology IBM researchers developed that can read research papers and auto generate the source code behind these models. With this research, the team hopes to reduce the time it takes to implement deep learning models from a few days or few hours to a few minutes, improving researchers’ productivity and accelerating new innovations and applications.

IBM Research, a gold sponsor of AAAI 18, is also sponsoring the AAAI/ACM conference on Artificial Intelligence, Ethics and Society (AIES). Below is a complete look at the papers, workshops, conference demos, talks and tutorials IBM Research will present at AAAI, AIES and the co-located Innovative Applications for Artificial Intelligence (IAAI) conference.

If you’re in New Orleans, come visit us at table 16 in the conference expo or at the job fair on Monday, February 5 from 4-6 pm in the Jefferson Ballroom on the 3rd floor.

Accepted papers at AAAI

Bernoulli Embeddings for Graphs
Vinith Misra, Sumit Bhatia

Neural Cross-Lingual Entity Linking
Avirup Sil, Gourab Kundu, Radu Florian, Wael Hamza

Statistical Inference Using SGD
Tianyang Li, Liu Liu, Anastasios Kyrillidis, Constantine Caramanis

R^3: Reinforced Ranker-Reader for Open-Domain Question Answering
Shuohang Wang, Mo Yu, Xiaoxiao Guo, Zhiguo Wang, Tim Klinger, Wei Zhang, Shiyu Chang, Gerry Tesauro, Bowen Zhou, Jing Jiang

The Conference Paper Assignment Problem: Using Order Weighted Averages to Assign Indivisible Goods
Jing Wu Lian, Nicholas Mattei, Renee Noble, Toby Walsh

Dynamic Determinantal Point Processes
Takayuki Osogami, Rudy Raymond, Akshay Goel, Tomoyuki Shirai, Takanori Maehara

A Deep Generative Framework for Paraphrase Generation
Ankush Gupta, Arvind Agarwal, Prawaan Singh, Piyush Rai

Semi-Black Box: Rapid Development of Planning Based Solutions
Michael Katz, Dany Moshkovich, Erez Karpas

Content and Context: Two-Pronged Bootstrapped Learning for Regex-Formatted Entity Extraction
Stanley Simoes, Deepak P, Munu Sairamesh, Deepak Khemani, Sameep Mehta

Towards Building Large Scale Multimodal Domain-Aware Conversation Systems
Amrita Saha, Mitesh M. Khapra, Karthik Sankaranarayanan

Complex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graph
Amrita Saha, Vardaan Pahuja, Mitesh M. Khapra, Karthik Sankaranarayanan, Sarath Chanda

Dialogue Act Sequence Labeling Using Hierarchical Encoder With CRF
Harshit Kumar, Arvind Agarwal, Riddhiman Dasgupta, Sachindra Joshi

An AI Planning Solution to Scenario Generation for Enterprise Risk Management
Shirin Sohrabi, Anton V. Riabov, Michael Katz, Octavian Udrea

Early Prediction of Diabetes Complications from Electronic Health Records: A Multi-Task Survival Analysis Approach
Bin Liu, Ying Li, Zhaonan Sun, Soumya Ghosh, Kenney Ng

Attend and Diagnose: Clinical Time Series Analysis Using Attention Models
Huan Song, Deepta Rajan, Jayaraman J. Thiagarajan, Andreas Spanias

DLPaper2Code: Auto-Generation of Code From Deep Learning Research Papers
Akshay Sethi, Anush Sankaran, Naveen Panwar, Shreya Khare, Senthil Mani

Cognition-Cognizant Sentiment Analysis With Multitask Subjectivity Summarization Based on Annotators’ Gaze Behavior
Abhijit Mishra, Srikanth Tamilselvam, Riddhiman Dasgupta, Seema Nagar, Kuntal Dey

EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples
Pin-Yu Chen, Yash Sharma, Huan Zhang, Jinfeng Yi, Cho-Jui Hsieh

Feature Engineering for Predictive Modeling Using Reinforcement Learning
Udayan Khurana, Horst Samulowitz, Deepak Turaga

AdaComp : Adaptive Residual Gradient Compression for Data-Parallel Distributed Training
Chia-Yu Chen, Jungwook Choi, Daniel Brand, Ankur Agrawal, Wei Zhang, Kailash Gopalakrishnan

Accepted papers at AIES

Towards Composable Bias Rating of AI Systems
Biplav Srivastava, Francesca Rossi

Data Driven Platform for Organizing Scientific Articles Relevant to Biomimicry
Yuanshuo Zhao, Ioana Baldini, Prasanna Sattigeri, Inkit Padhi, Yoong Keok Lee, Ethan Smith     

Fairness in Deceased Organ Matching
Nicholas Mattei, Abdallah Saffidine, Toby Walsh

Modeling Epistemological Principles for Bias Mitigation in AI Systems: An Illustration in Hiring Decisions
Marisa Vasconcelos, Bernardo Goncalves, Carlos Henrique Cardonha

Preferences and Ethical Principles in Decision Making
Andrea Loreggia, Nicholas Mattei, Francesca Rossi, Kristen Brent Vernable

Accepted papers at IAAI

Hi, how can I help you?: Automating enterprise IT support help desks
Senthil Mani, Neelamadhav Gantayat, Rahul Aralikatte, Monika Gupta, Sampath Dechu, Anush Sankaran, Shreya Khare, Barry Mitchell, Hemamalini Subramanian, Hema Venkatarangan              

Assessing National Development Plans for Alignment with Sustainable Development Goals via Semantic Search
Jonathan Galsurkar, Moninder Singh, Lingei Wu, Aditya Vempaty, Mikhail Sushkov, Devika Iyer, Serge Kapto, Kush Varshney            

Deploying Novel Exploration Techniques (NETs) for Malaria Policy Interventions           
Oliver Bent, Sekou Remy, Stephen Roberts, Aisha Walcott            

Invited Talks

AIES Invited Talk, AI and Law
Panel 2: Prioritizing Ethical Considerations in Intelligent and Autonomous Systems – Who Sets the Standards?
Takashi Egawa, Simson Garfinkel, John Havens, Annette Reilly, Francesca Rossi

Workshop on Plan, Activity, and Intent Recognition (PAIR)
Plan Recognition as Planning: Theory and Practice
Shirin Sohrabi

What’s Hot Talks

What’s Hot in Combinatorial Search (SOCs)
Akihiro Kishimoto                           


AI & Marketing Science Workshop
Thematic Distillation and Point of View Extraction for Enterprise-level Documents
Elham Khabiri

Workshop on Reasoning and Learning for Human-Machine Dialogues
Making Personalized Recommendation through Conversation: Architecture Design and Recommendation Methods
Sunhwan Lee

Workshop on Engineering Dependable and Secure Machine Learning Systsems
Eitan Farchi, Oded Margalit, Orna Raz, Peter Santhanam

Feature Extraction from Electronic Health Records of Diabetic Nephropathy Patients with Convolutional Autoencoder
Takayuki Katsuki, Masaki Ono, Akira Koseki, Michiharu Kudo, Kyoichi Haida, Jun Kuroda Masaki Makino, Ryosuke Yanagiya, and Atsushi Suzuki

Water Advisor – A Data-Driven, Multi-Modal, Contextual Assistant to Help with Water Usage Decisions
Jason Ellis, Biplav Srivastava, Rachel K. E. Bellamy, Andy Aaron

Democratization of Deep Learning Using DARVIZ
Anush Sankaran, Naveen Panwar, Shreya Khare, Senthil Mani, Akshay Sethi, Rahul Aralikatte, Neelamadhav Gantayat           

A Cognitive Assistant for Visualizing and Analyzing Exoplanets
Jeffrey O. Kephart, Victor C. Dibia, Jason Ellis, Biplav Srivastava, Kartik Talamadupula, Mishal Dholakia

Dataset Evolver: An Interactive Feature Engineering Notebook
Fatemeh Nargesian, Udayan Khurana, Tejaswini Pedapati, Horst Samulowitz, Deepak Turaga

Agent Assist: Automating Enterprise IT Support Help Desks
Senthil Mani, Neelamadhav Gantayat, Rahul Aralikatte, Monika Gupta, Sampath Dechu, Anush Sankaran, Shreya Khare, Barry Mitchell, Hemamalini Subramanian, Hema Venkatarangan              

A Unified Implicit Dialog Framework for Conversational Commerce
Song Feng, R. Chulaka Gunasekara, Sunil Shashidhara, Kshitij P. Fadnis, Lazaros C. Polymenakos


Strategic, Online Learning, and Computational Aspects of Social Network Science
Ramasuri Narayanam  

AI Techniques for Price Prediction in Commodity Markets
Ramasuri Narayanam

Senior Member Track

AI Meets Chemistry
Akihiro Kishimoto, Beat Buesser, Adi Botea         

More AI stories

We’ve moved! The IBM Research blog has a new home

In an effort better integrate the IBM Research blog with the IBM Research web experience, we have migrated to a new landing page:

Continue reading

Pushing the boundaries of human-AI interaction at IUI 2021

At the 2021 virtual edition of the ACM International Conference on Intelligent User Interfaces (IUI), researchers at IBM will present five full papers, two workshop papers, and two demos.

Continue reading

From HPC Consortium’s success to National Strategic Computing Reserve

Founded in March 2020 just as the pandemic’s wave was starting to wash over the world, the Consortium has brought together 43 members with supercomputing resources. Private and public enterprises, academia, government and technology companies, many of whom are typically rivals. “It is simply unprecedented,” said Dario Gil, Senior Vice President and Director of IBM Research, one of the founding organizations. “The outcomes we’ve achieved, the lessons we’ve learned, and the next steps we have to pursue are all the result of the collective efforts of these Consortium’s community.” The next step? Creating the National Strategic Computing Reserve to help the world be better prepared for future global emergencies.

Continue reading