• Corpus ID: 246015733

ULTRA: A Data-driven Approach for Recommending Team Formation in Response to Proposal Calls

  title={ULTRA: A Data-driven Approach for Recommending Team Formation in Response to Proposal Calls},
  author={Biplav Srivastava and Tarmo Koppel and Ronak Shah and Owen Bond and Sai Teja Paladi and Rohit Sharma and Austin Hetherington},
We introduce an emerging AI-based approach and prototype system for assisting team formation when researchers respond to calls for proposals from funding agencies. This is an instance of the general problem of building teams when demand opportunities come periodically and potential members may vary over time. The novelties of our approach are that we: (a) extract technical skills needed about researchers and calls from multiple data sources and normalize them using Natural Language Processing… 

Figures and Tables from this paper


SPECTER: Document-level Representation Learning using Citation-informed Transformers
This work proposes SPECTER, a new method to generate document-level embedding of scientific papers based on pretraining a Transformer language model on a powerful signal of document- level relatedness: the citation graph, and shows that Specter outperforms a variety of competitive baselines on the benchmark.
On Finding Stable and Efficient Solutions for the Team Formation Problem
A mathematical-programming approach to "team formation" focused on the interplay between two of the most common objectives considered in the related literature: economic efficiency and game-theoretic stability is studied.
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
A new language representation model, BERT, designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.
A Survey of Text Matching Techniques
The survey attempted in the present study covers a new research premise that uses text-matching to solve problems and summarizes different approaches that are being used in this domain.
Fractional Hedonic Games
This article proposes a number of conditions under which the core of FHGs is non-empty and provides algorithms for computing a core stable outcome and shows that the core may be empty in other cases, and that it is computationally hard in general to decide non-emptiness of the core.
Status and Future Maintenance Report of the CCS Update Committee
Acm classification scheme
    An unsupervised system for exploring text documents
    • In UoSC Research Report
    • 2021
    Introduction to multi - armed bandits Contextual word representations : Putting words into computers
    • Communications of the ACM
    Contextual word representations: Putting words into computers
    • In Communications of the ACM,
    • 2020