More Like this

1. Asking Clarifying Questions Based on Negative Feedback in Conversational Search

   https://doi.org/10.1145/3471158.3472232  

   Ai, Q.; Bi, K.; Croft, W. B. (July 2021, Proceedings of the 7th ACM International Conference on the Theory of Information Retrieval (ICTIR 2021))

   null (Ed.)

   Users often need to look through multiple search result pages or reformulate queries when they have complex information-seeking needs. Conversational search systems make it possible to improve user satisfaction by asking questions to clarify users’ search intents. This, however, can take significant effort to answer a series of questions starting with “what/why/how”. To quickly identify user intent and reduce effort during interactions, we propose an intent clarification task based on yes/no questions where the system needs to ask the correct question about intents within the fewest conversation turns. In this task, it is essential to use negative feedback about the previous questions in the conversation history. To this end, we propose a Maximum-Marginal-Relevance (MMR) based BERT model (MMR-BERT) to leverage negative feedback based on the MMR principle for the next clarifying question selection. Experiments on the Qulac dataset show that MMR-BERT outperforms state-of-the-art baselines significantly on the intent identification task and the selected questions also achieve significantly better performance in the associated document retrieval tasks. 

   more » « less
2. Early Prediction of Human Intention For Human-Robot Collaboration Using Transformer Network,

   Zhang, Xinyao; Tian, Sibo; Liang, Xiao; Zheng, Minghui; Behdad, Sara (August 2023, Proceedings of the ASME 2023 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE2023)

   Activity recognition is a crucial aspect in smart manufacturing and human-robot collaboration, as robots play a vital role in improving efficiency and safety by accurately recognizing human intentions and proactively assisting with tasks. Current human intention recognition applications only consider the accuracy of recognition but ignore the importance of predicting it in advance. Given human reaching movements, we want to equip the robot with the ability to predict human intent not only with precise recognition but also at an early stage. In this paper, we propose a framework to apply Transformer-based and LSTM-based models to learn motion intentions. Second, based on the observation of distances of human joints along the motion trajectory, we explore how we can use the hidden Markov model to find intent state transitions, i.e., intent uncertainty and intent certainty. Finally, two data types are generated, one for the full data and the other for the length of data before state transitions; both data are evaluated on models to assess the robustness of intention prediction. We conducted experiments in a manufacturing workspace where the experimenter reaches multiple scattered targets and further this experimental scenario was designed to examine how intents differ, but motions are only slightly different. The proposed models were then evaluated with experimental data, and further performance comparisons were made between models and between different intents. Finally, early predictions were validated to be better than using full-length data. 

   more » « less
3. Persist: Persistent and Reusable Interactions in Computational Notebooks

   https://doi.org/10.1111/cgf.15092  

   Gadhave, K; Cutler, Z; Lex, A (June 2024, Computer Graphics Forum)

   Computational notebooks, such as Jupyter, support rich data visualization. However, even when visualizations in notebooks are interactive, they are a dead end: Interactive data manipulations, such as selections, applying labels, filters, categorizations, or fixes to column or cell values, could be efficiently applied in interactive visual components, but interactive components typically cannot manipulate Python data structures. Furthermore, actions performed in interactive plots are lost as soon as the cell is re‐run, prohibiting reusability and reproducibility. To remedy this problem, we introduce Persist, a family of techniques to (a) capture interaction provenance, enabling the persistence of interactions, and (b) map interactions to data manipulations that can be applied to dataframes. We implement our approach as a JupyterLab extension that supports tracking interactions in Vega‐Altair plots and in a data table view. Persist can re‐execute interaction provenance when a notebook or a cell is re‐executed, enabling reproducibility and re‐use. We evaluate Persist in a user study targeting data manipulations with 11 participants skilled in Python and Pandas, comparing it to traditional code‐based approaches. Participants were consistently faster and were able to correctly complete more tasks with Persist. 

   more » « less
4. Situational Confidence Assistance for Lifelong Shared Autonomy

   https://doi.org/10.1109/ICRA48506.2021.9561839  

   Zurek, Matthew; Bobu, Andreea; Brown, Daniel; Dragan, Anca (April 2021, International Conference on Robotics and Automation)

   Shared autonomy enables robots to infer user intent and assist in accomplishing it. But when the user wants to do a new task that the robot does not know about, shared autonomy will hinder their performance by attempting to assist them with something that is not their intent. Our key idea is that the robot can detect when its repertoire of intents is insufficient to explain the user’s input, and give them back control. This then enables the robot to observe unhindered task execution, learn the new intent behind it, and add it to this repertoire. We demonstrate with both a case study and a user study that our proposed method maintains good performance when the human’s intent is in the robot’s repertoire, outperforms prior shared autonomy approaches when it isn’t, and successfully learns new skills, enabling efficient lifelong learning for confidence-based shared autonomy. 

   more » « less
5. DeepLINK: Deep learning inference using knockoffs with applications to genomics

   https://doi.org/10.1073/pnas.2104683118  

   Zhu, Zifan; Fan, Yingying; Kong, Yinfei; Lv, Jinchi; Sun, Fengzhu (September 2021, Proceedings of the National Academy of Sciences)

   Significance Although practically attractive with high prediction and classification power, complicated learning methods often lack interpretability and reproducibility, limiting their scientific usage. A useful remedy is to select truly important variables contributing to the response of interest. We develop a method for deep learning inference using knockoffs, DeepLINK, to achieve the goal of variable selection with controlled error rate in deep learning models. We show that DeepLINK can also have high power in variable selection with a broad class of model designs. We then apply DeepLINK to three real datasets and produce statistical inference results with both reproducibility and biological meanings, demonstrating its promising usage to a broad range of scientific applications. 

   more » « less