natural language processing

New research helps make AI fairer in decision-making

To tackle bias in AI, our IBM Research team in collaboration with the University of Michigan has developed practical procedures and tools to help machine learning and AI achieve Individual Fairness. The key idea of Individual Fairness is to treat similar individuals well, similarly, to achieve fairness for everyone.

Continue reading

IBM RXN for Chemistry: Automatically cleaning chemical reaction datasets

In our latest paper, “Unassisted Noise Reduction of Chemical Reaction Data Sets” in Nature Machine Intelligence, we explore the application of NLP techniques to automate the identification of “language outliers” or the noise in chemical datasets.

Continue reading

IBM’s AI learns to navigate around a virtual home using common sense

In a recent paper introduced at the 2021 AAAI Conference on Artificial Intelligence (AAAI), we describe an AI that trades off ‘exploration’ of the world with ‘exploitation’ of its action strategy to maximize rewards. In Reinforcement Learning, an AI gets a reward – such as a bag of gold behind a locked door in a video game – every time it reaches specific desirable states. We have greatly improved this exploration vs exploitation tradeoff using additional commonsense knowledge – in the form of crowdsourced text. Our work could lead to better mapping and navigation applications, and to a new generation of interactive assistive agents able to reason like humans.

Continue reading

IBM Research at SIGMOD 2020

ACM SIGMOD/PODS 2020 like many other events impacted by COVID-19 pandemic will be taking place virtually from June 14 through June 19. The focus of work at SIGMOD 2020 ranges from adding graph querying to relational databases, to natural language interfaces to data, to operationalizing data for new AI workloads. Results to be presented includes work done at our IBM Research-Almaden and IBM Research-India labs, as well as by our summer interns from universities and our partners in other IBM units.

Continue reading

Moving Beyond the Lab: IBM Research Powers Pipeline of AI Advances for the Enterprise

IBM AI researchers are responsible for developing many of the NLP capabilities IBM has brought to market. With the announcement that IBM will begin integrating NLP features developed for Project Debater into Watson, IBM Research once again delivers unique technology from the lab to the enterprise.

Continue reading

Bringing AI to the Command Line

For decades, developers and researchers have been using the command line interface (CLI) to build, execute, and deploy the software that runs the world around us. Users have come to love, hate and, eventually, embrace the unique, idiosyncratic, and sometimes antiquated challenges associated with using the terminal shell; and have adapted their behaviors and usage […]

Continue reading

Advancing Natural Language Processing for Enterprise Domains

IBM Fellow Salim Roukos provides some specifics on IBM Research’s enterprise NLP work by highlighting four papers IBM Research AI is presenting at the ACL 2019 conference.

Continue reading

Graph2Seq: A Generalized Seq2Seq Model for Graph Inputs

In a recent paper “Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks,” we describe a general end-to-end Graph-to-Sequence attention-based neural encoder-decoder architecture that encodes an input graph and decodes the target sequence. Graph encoder and attention-based decoder are two important building blocks in the development and widespread acceptance of machine learning solutions. Two of […]

Continue reading

Word Mover’s Embedding: Universal Text Embedding from Word2Vec

Text representation plays an important role in many natural language processing (NLP) tasks such as document classification and clustering, sense disambiguation, machine translation, and document matching. Since there are no explicit features in text, developing effective text representations is an important goal in AI and NLP research. A fundamental challenge in this respect is learning […]

Continue reading

Towards Language Inference in Medicine

Recent times have witnessed significant progress in natural language understanding by AI, such as machine translation and question answering. A vital reason behind these developments is the creation of datasets, which use machine learning models to learn and perform a specific task. Construction of such datasets in the open domain often consists of text originating […]

Continue reading

Improving AI’s Language Skills at ACL 2018

The 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018) will be held July 15–20 in Melbourne, Australia. ACL received 1,544 submissions and accepted 384, for an overall acceptance rate of 24.9 percent. IBM Research AI will present multiple papers at ACL 2018 and is proud to be a Gold sponsor. Please plan […]

Continue reading

Natural Language Processing Facilitates Collaborative Decisions

The Decision Science, AI and Natural Language Processing team at IBM Research-Ireland recently presented a conference paper called “Decision Conversations Decoded” at the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL HLT). The team also presented a demo of our virtual assistant prototype, which analyses collaborative decision […]

Continue reading