1 code implementation • EMNLP 2021 • Subhajit Chaudhury, Prithviraj Sen, Masaki Ono, Daiki Kimura, Michiaki Tatsubori, Asim Munawar
We outline a method for end-to-end differentiable symbolic rule learning and show that such symbolic policies outperform previous state-of-the-art methods in text-based RL for the coin collector environment from 5-10x fewer training games.
no code implementations • ACL (RepL4NLP) 2021 • Irene Li, Prithviraj Sen, Huaiyu Zhu, Yunyao Li, Dragomir Radev
In this paper, we propose zero-shot instance-weighting, a general model-agnostic zero-shot learning framework for improving CLTC by leveraging source instance weighting.
no code implementations • EMNLP 2020 • Prithviraj Sen, Marina Danilevsky, Yunyao Li, Siddhartha Brahma, Matthias Boehm, Laura Chiticariu, Rajasekar Krishnamurthy
Our user studies confirm that the learned LEs are explainable and capture domain semantics.
no code implementations • 15 Oct 2022 • HANLIN ZHANG, Xuechen Li, Prithviraj Sen, Salim Roukos, Tatsunori Hashimoto
Across 7 tasks, temperature scaling and Platt scaling with DP-SGD result in an average 3. 1-fold reduction in the in-domain expected calibration error and only incur at most a minor percent drop in accuracy.
1 code implementation • 6 Dec 2021 • Prithviraj Sen, Breno W. S. R. de Carvalho, Ryan Riegel, Alexander Gray
Recent work on neuro-symbolic inductive logic programming has led to promising approaches that can learn explanatory rules from noisy, real-world data.
no code implementations • 16 Sep 2021 • Prithviraj Sen, Breno W. S. R. Carvalho, Ibrahim Abdelaziz, Pavan Kapanipathi, Francois Luus, Salim Roukos, Alexander Gray
Recent interest in Knowledge Base Completion (KBC) has led to a plethora of approaches based on reinforcement learning, inductive logic programming and graph embeddings.
1 code implementation • ACL 2021 • Hang Jiang, Sairam Gurajada, Qiuhao Lu, Sumit Neelam, Lucian Popa, Prithviraj Sen, Yunyao Li, Alexander Gray
Entity linking (EL), the task of disambiguating mentions in text by linking them to entities in a knowledge graph, is crucial for text understanding, question answering or conversational systems.
1 code implementation • 8 Apr 2021 • Arjit Jain, Sunita Sarawagi, Prithviraj Sen
We propose DIAL, a scalable active learning approach that jointly learns embeddings to maximize recall for blocking and accuracy for matching blocked pairs.
4 code implementations • 28 Feb 2021 • Francois Luus, Prithviraj Sen, Pavan Kapanipathi, Ryan Riegel, Ndivhuwo Makondo, Thabang Lebese, Alexander Gray
Answering logical queries over incomplete knowledge bases is challenging because: 1) it calls for implicit link prediction, and 2) brute force answering of existential first-order logic queries is exponential in the number of existential variables.
Ranked #1 on Question Answering on Mathematics Dataset
no code implementations • COLING 2020 • Qiuhao Lu, Nisansa de Silva, Dejing Dou, Thien Huu Nguyen, Prithviraj Sen, Berthold Reinwald, Yunyao Li
Network representation learning (NRL) is crucial in the area of graph learning.
no code implementations • Asian Chapter of the Association for Computational Linguistics 2020 • Marina Danilevsky, Kun Qian, Ranit Aharonov, Yannis Katsis, Ban Kawas, Prithviraj Sen
Recent years have seen important advances in the quality of state-of-the-art models, but this has come at the expense of models becoming less interpretable.
no code implementations • 6 Apr 2020 • Shivam Srivastava, Prithviraj Sen, Berthold Reinwald
Sparse and irregularly sampled multivariate time series are common in clinical, climate, financial and many other domains.
no code implementations • 29 Mar 2020 • Venkata Vamsikrishna Meduri, Lucian Popa, Prithviraj Sen, Mohamed Sarwat
Entity Matching (EM) is a core data cleaning task, aiming to identify different mentions of the same real-world entity.
no code implementations • ACL 2019 • Yiwei Yang, Eser Kandogan, Yunyao Li, Walter S. Lasecki, Prithviraj Sen
While the role of humans is increasingly recognized in machine learning community, representation of and interaction with models in current human-in-the-loop machine learning (HITL-ML) approaches are too low-level and far-removed from human's conceptual models.
no code implementations • 8 Feb 2018 • Niketan Pansare, Michael Dusenberry, Nakul Jindal, Matthias Boehm, Berthold Reinwald, Prithviraj Sen
Enterprises operate large data lakes using Hadoop and Spark frameworks that (1) run a plethora of tools to automate powerful data preparation/transformation pipelines, (2) run on shared, large clusters to (3) perform many different analytics tasks ranging from model preparation, building, evaluation, and tuning for both machine learning and deep learning.