Sheshera S Mysore

Editable User Profiles for Controllable Text Recommendation

Methods for making high-quality recommendations often rely on learning latent representations from interaction data. These methods, while performant, do not provide ready mechanisms for users to control the recommendation they receive. Our work tackles this problem by proposing LACE, a novel concept value bottleneck model for controllable text recommendations. LACE represents each user with a succinct set of human-readable concepts through retrieval given user-interacted documents and learns personalized representations of the concepts based on user documents. This concept based user profile is then leveraged to make recommendations. The design of our model affords control over the recommendations through a number of intuitive interactions with a transparent user profile. We first establish the quality of recommendations obtained from LACE in an offline evaluation on three recommendation tasks spanning six datasets in warm-start, cold-start, and zero-shot setups. Next, we validate the controllability of LACE under simulated user interactions. Finally, we implement LACE in an interactive controllable recommender system and conduct a user study to demonstrate that users are able to improve the quality of recommendations they receive through interactions with an editable user profile.

How Data Scientists Review the Scholarly Literature

Keeping up with the research literature plays an important role in the workflow of scientists - allowing them to understand a field, formulate the problems they focus on, and develop the solutions that they contribute, which in turn shape the nature of the discipline. In this paper, we examine the literature review practices of data scientists. Data science represents a field seeing an exponential rise in papers, and increasingly drawing on and being applied in numerous diverse disciplines. Recent efforts have seen the development of several tools intended to help data scientists cope with a deluge of research and coordinated efforts to develop AI tools intended to uncover the research frontier. Despite these trends indicative of the information overload faced by data scientists, no prior work has examined the specific practices and challenges faced by these scientists in an interdisciplinary field with evolving scholarly norms. In this paper, we close this gap through a set of semi-structured interviews and think-aloud protocols of industry and academic data scientists (N = 20). Our results while corroborating other knowledge workers' practices uncover several novel findings: individuals (1) are challenged in seeking and sensemaking of papers beyond their disciplinary bubbles, (2) struggle to understand papers in the face of missing details and mathematical content, (3) grapple with the deluge by leveraging the knowledge context in code, blogs, and talks, and (4) lean on their peers online and in-person. Furthermore, we outline future directions likely to help data scientists cope with the burgeoning research literature.

Controllable Discovery of Research Papers - Sign Up

This is a sign up form for an study being conducted by graduate students at the University of Massachusetts Amherst. The study is intended to help evaluate a system for discovery of scientific research papers. The study will involve exploring a corpus of papers with 2 literature discovery systems built by us. It will be conducted online via Zoom, last up to 1 hour, and participants will be compensated $25. The study will involve no risk to participants, and all identifiable information collected in the study will only be accessed by trained and Institutional Review Board (IRB) approved researchers for research purposes. The study will run from 1st - 13th January 2023. This questionnaire is a screening tool that will ask you questions about your current work to determine your eligibility for participation in our study. It should take you no more than 2 minutes to complete. If you are determined ineligible to participate your completed questionnaire will be destroyed. If you are determined eligible to participate, the completed questionnaire will become part of the study materials, and we will protect your information as confidential and safeguard it from unauthorized disclosure. Only authorized research personnel will have access to the information contained in your questionnaire. If the questionnaire indicates that you are eligible to participate, we will obtain your written informed consent for participation at the scheduled time of the study. In case of questions or concerns please contact: Sheshera Mysore ([email protected]) Project team: Sheshera Mysore, Mahmood Jasim, Andrew McCallum, Hamed Zamani