Search Results for author: Prithviraj Sen

Found 13 papers, 3 papers with code

Improving Cross-lingual Text Classification with Zero-shot Instance-Weighting

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.

Classification Text Classification +1

Neuro-Symbolic Approaches for Text-Based Policy Learning

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.

text-based games

Combining Rules and Embeddings via Neuro-Symbolic AI for Knowledge Base Completion

no code implementations16 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.

Inductive logic programming Knowledge Base Completion

LNN-EL: A Neuro-Symbolic Approach to Short-text Entity Linking

no code implementations 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.

Entity Linking Fine-tuning +1

Deep Indexed Active Learning for Matching Heterogeneous Entity Representations

1 code implementation8 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.

Active Learning Entity Resolution +1

Logic Embeddings for Complex Query Answering

3 code implementations28 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.

Knowledge Graphs Link Prediction

A Survey of the State of Explainable AI for Natural Language Processing

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.

Forecasting in multivariate irregularly sampled time series with missing values

no code implementations6 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.

General Classification Irregular Time Series +1

A Comprehensive Benchmark Framework for Active Learning Methods in Entity Matching

no code implementations29 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.

Active Learning

HEIDL: Learning Linguistic Expressions with Deep Learning and Human-in-the-Loop

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.

Deep Learning with Apache SystemML

no code implementations8 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.

Cannot find the paper you are looking for? You can Submit a new open access paper.