Search Results for author: Parag Singla

Found 39 papers, 10 papers with code

Transfer Learning for Related Languages: Submissions to the WMT20 Similar Language Translation Task

no code implementations WMT (EMNLP) 2020 Lovish Madaan, Soumya Sharma, Parag Singla

In this paper, we describe IIT Delhi’s submissions to the WMT 2020 task on Similar Language Translation for four language directions: Hindi <-> Marathi and Spanish <-> Portuguese.

Transfer Learning Translation

Towards Scene Graph Anticipation

no code implementations7 Mar 2024 Rohith Peddi, Saksham Singh, Saurabh, Parag Singla, Vibhav Gogate

In SceneSayer, we leverage object-centric representations of relationships to reason about the observed video frames and model the evolution of relationships between objects.

Graph Generation Long Term Anticipation +2

PuzzleBench: Can LLMs Solve Challenging First-Order Combinatorial Reasoning Problems?

no code implementations4 Feb 2024 Chinmay Mittal, Krishna Kartik, Mausam, Parag Singla

Recent works show that the largest of the large language models (LLMs) can solve many simple reasoning tasks expressed in natural language, without any/much supervision.

Question Answering

Ensembling Textual and Structure-Based Models for Knowledge Graph Completion

no code implementations7 Nov 2023 Ananjan Nandi, Navdeep Kaur, Parag Singla, Mausam

We consider two popular approaches to Knowledge Graph Completion (KGC): textual models that rely on textual entity descriptions, and structure-based models that exploit the connectivity structure of the Knowledge Graph (KG).

Knowledge Graph Completion

ZGUL: Zero-shot Generalization to Unseen Languages using Multi-source Ensembling of Language Adapters

1 code implementation25 Oct 2023 Vipul Rathore, Rajdeep Dhingra, Parag Singla, Mausam

We posit that for more effective cross-lingual transfer, instead of just one source LA, we need to leverage LAs of multiple (linguistically or geographically related) source languages, both at train and test-time - which we investigate via our novel neural architecture, ZGUL.

Language Modelling NER +4

Towards Fair and Calibrated Models

no code implementations16 Oct 2023 Anand Brahmbhatt, Vipul Rathore, Mausam, Parag Singla

Further, we show that ensuring group-wise calibration with respect to the sensitive attributes automatically results in a fair model under our definition.

Fairness

Fill in the Blank: Exploring and Enhancing LLM Capabilities for Backward Reasoning in Math Word Problems

no code implementations3 Oct 2023 Aniruddha Deb, Neeva Oza, Sarthak Singla, Dinesh Khandelwal, Dinesh Garg, Parag Singla

Utilizing the specific format of this task, we propose three novel techniques that improve performance: Rephrase reformulates the given problem into a forward reasoning problem, PAL-Tools combines the idea of Program-Aided LLMs to produce a set of equations that can be solved by an external solver, and Check your Work exploits the availability of natural verifier of high accuracy in the forward direction, interleaving solving and verification steps.

GSM8K Math

Image Manipulation via Multi-Hop Instructions -- A New Dataset and Weakly-Supervised Neuro-Symbolic Approach

no code implementations23 May 2023 Harman Singh, Poorva Garg, Mohit Gupta, Kevin Shah, Ashish Goswami, Satyam Modi, Arnab Kumar Mondal, Dinesh Khandelwal, Dinesh Garg, Parag Singla

We are interested in image manipulation via natural language text -- a task that is useful for multiple AI applications but requires complex reasoning over multi-modal spaces.

Image Manipulation Question Answering +1

Learning Neuro-symbolic Programs for Language Guided Robot Manipulation

no code implementations12 Nov 2022 Namasivayam Kalithasan, Himanshu Singh, Vishal Bindal, Arnav Tuli, Vishwajeet Agrawal, Rahul Jain, Parag Singla, Rohan Paul

Given a natural language instruction and an input scene, our goal is to train a model to output a manipulation program that can be executed by the robot.

Robot Manipulation

A Solver-Free Framework for Scalable Learning in Neural ILP Architectures

1 code implementation17 Oct 2022 Yatin Nandwani, Rishabh Ranjan, Mausam, Parag Singla

Experiments on several problems, both perceptual as well as symbolic, which require learning the constraints of an ILP, show that our approach has superior performance and scales much better compared to purely neural baselines and other state-of-the-art models that require solver-based training.

Neural Models for Output-Space Invariance in Combinatorial Problems

no code implementations ICLR 2022 Yatin Nandwani, Vidit Jain, Mausam, Parag Singla

One drawback of the proposed architectures, which are often based on Graph Neural Networks (GNN), is that they cannot generalize across the size of the output space from which variables are assigned a value, for example, set of colors in a GCP, or board-size in sudoku.

Node Classification

PARE: A Simple and Strong Baseline for Monolingual and Multilingual Distantly Supervised Relation Extraction

1 code implementation ACL 2022 Vipul Rathore, Kartikeya Badola, Mausam, Parag Singla

The contextual embeddings of tokens are aggregated using attention with the candidate relation as query -- this summary of whole passage predicts the candidate relation.

Relation Relation Extraction +1

Explanations for CommonsenseQA: New Dataset and Models

no code implementations AKBC Workshop CSKB 2021 Shourya Aggarwal, Divyanshu Mandowara, Vishwajeet Agrawal, Dinesh Khandelwal, Parag Singla, Dinesh Garg

We human-annotate a first-of-its-kind dataset (called ECQA) of positive and negative properties, as well as free-flow explanations, for $11K$ QA pairs taken from the CQA dataset.

Common Sense Reasoning Explanation Generation +4

ScRAE: Deterministic Regularized Autoencoders with Flexible Priors for Clustering Single-cell Gene Expression Data

1 code implementation16 Jul 2021 Arnab Kumar Mondal, Himanshu Asnani, Parag Singla, Prathosh AP

The basic idea in RAEs is to learn a non-linear mapping from the high-dimensional data space to a low-dimensional latent space and vice-versa, simultaneously imposing a distributional prior on the latent space, which brings in a regularization effect.

Clustering

Towards an Interpretable Latent Space in Structured Models for Video Prediction

no code implementations16 Jul 2021 Rushil Gupta, Vishal Sharma, Yash Jain, Yitao Liang, Guy Van Den Broeck, Parag Singla

We work with models which are object-centric, i. e., explicitly work with object representations, and propagate a loss in the latent space.

Contrastive Learning Inductive Bias +2

Joint Spatio-Textual Reasoning for Answering Tourism Questions

1 code implementation28 Sep 2020 Danish Contractor, Shashank Goel, Mausam, Parag Singla

In response, we develop the first joint spatio-textual reasoning model, which combines geo-spatial knowledge with information in textual corpora to answer questions.

Neural Learning of One-of-Many Solutions for Combinatorial Problems in Structured Output Spaces

no code implementations ICLR 2021 Yatin Nandwani, Deepanshu Jindal, Mausam, Parag Singla

Our framework uses a selection module, whose goal is to dynamically determine, for every input, the solution that is most effective for training the network parameters in any given learning iteration.

To Regularize or Not To Regularize? The Bias Variance Trade-off in Regularized AEs

no code implementations10 Jun 2020 Arnab Kumar Mondal, Himanshu Asnani, Parag Singla, Prathosh AP

Specifically, we consider the class of RAEs with deterministic Encoder-Decoder pairs, Wasserstein Auto-Encoders (WAE), and show that having a fixed prior distribution, \textit{a priori}, oblivious to the dimensionality of the `true' latent space, will lead to the infeasibility of the optimization problem considered.

MaskAAE: Latent space optimization for Adversarial Auto-Encoders

no code implementations10 Dec 2019 Arnab Kumar Mondal, Sankalan Pal Chowdhury, Aravind Jayendran, Parag Singla, Himanshu Asnani, Prathosh AP

The field of neural generative models is dominated by the highly successful Generative Adversarial Networks (GANs) despite their challenges, such as training instability and mode collapse.

A Primal Dual Formulation For Deep Learning With Constraints

1 code implementation NeurIPS 2019 Yatin Nandwani, Abhishek Pathak, Mausam, Parag Singla

In this paper, we present a constrained optimization formulation for training a deep network with a given set of hard constraints on output labels.

Entity Typing named-entity-recognition +4

Large Scale Question Answering using Tourism Data

no code implementations8 Sep 2019 Danish Contractor, Krunal Shah, Aditi Partap, Mausam, Parag Singla

We introduce the novel task of answering entity-seeking recommendation questions using a collection of reviews that describe candidate answer entities.

Information Retrieval Question Answering +1

Domain Aware Markov Logic Networks

no code implementations3 Jul 2018 Happy Mittal, Ayush Bhardwaj, Vibhav Gogate, Parag Singla

Experiments on the benchmark Friends & Smokers domain show that our ap- proach results in significantly higher accuracies compared to existing methods when testing on domains whose sizes different from those seen during training.

Lifted Marginal MAP Inference

no code implementations2 Jul 2018 Vishal Sharma, Noman Ahmed Sheikh, Happy Mittal, Vibhav Gogate, Parag Singla

Lifted inference reduces the complexity of inference in relational probabilistic models by identifying groups of constants (or atoms) which behave symmetric to each other.

Block-Value Symmetries in Probabilistic Graphical Models

1 code implementation2 Jul 2018 Gagan Madan, Ankit Anand, Mausam, Parag Singla

These orbits are represented compactly using permutations over variables, and variable-value (VV) pairs, but they can miss several state symmetries in a domain.

Towards Understanding and Answering Multi-Sentence Recommendation Questions on Tourism

no code implementations5 Jan 2018 Danish Contractor, Barun Patra, Mausam Singla, Parag Singla

We introduce the first system towards the novel task of answering complex multisentence recommendation questions in the tourism domain.

Negation Sentence

Non-Count Symmetries in Boolean & Multi-Valued Prob. Graphical Models

1 code implementation27 Jul 2017 Ankit Anand, Ritesh Noothigattu, Parag Singla, Mausam

Moreover, algorithms for lifted inference in multi-valued domains also compute a multi-valued extension of count symmetries only.

Coarse-to-Fine Lifted MAP Inference in Computer Vision

1 code implementation22 Jul 2017 Haroun Habeeb, Ankit Anand, Mausam, Parag Singla

We demonstrate the performance of C2F inference by developing lifted versions of two near state-of-the-art CV algorithms for stereo vision and interactive image segmentation.

Image Segmentation Semantic Segmentation

Contextual Symmetries in Probabilistic Graphical Models

no code implementations30 Jun 2016 Ankit Anand, Aditya Grover, Mausam, Parag Singla

We extend previous work on exploiting symmetries in the MCMC framework to the case of contextual symmetries.

Lifted Region-Based Belief Propagation

no code implementations30 Jun 2016 David Smith, Parag Singla, Vibhav Gogate

Due to the intractable nature of exact lifted inference, research has recently focused on the discovery of accurate and efficient approximate inference algorithms in Statistical Relational Models (SRMs), such as Lifted First-Order Belief Propagation.

Min Norm Point Algorithm for Higher Order MRF-MAP Inference

no code implementations CVPR 2016 Ishant Shanu, Chetan Arora, Parag Singla

Current state of the art inference algorithms for general submodular function takes many hours for problems with clique size 16, and fail to scale beyond.

Lifted Symmetry Detection and Breaking for MAP Inference

no code implementations NeurIPS 2015 Timothy Kopp, Parag Singla, Henry Kautz

Symmetry breaking is a technique for speeding up propositional satisfiability testing by adding constraints to the theory that restrict the search space while preserving satisfiability.

Relational Reasoning Symmetry Detection

Fast Lifted MAP Inference via Partitioning

no code implementations NeurIPS 2015 Somdeb Sarkhel, Parag Singla, Vibhav G. Gogate

A key advantage of these lifted algorithms is that they have much smaller computational complexity than propositional algorithms when symmetries are present in the MLN and these symmetries can be detected using lifted inference rules.

Lifted Inference Rules With Constraints

no code implementations NeurIPS 2015 Happy Mittal, Anuj Mahajan, Vibhav G. Gogate, Parag Singla

Lifted inference rules exploit symmetries for fast reasoning in statistical rela-tional models.

New Rules for Domain Independent Lifted MAP Inference

no code implementations NeurIPS 2014 Happy Mittal, Prasoon Goyal, Vibhav G. Gogate, Parag Singla

In this paper, we present two new lifting rules, which enable fast MAP inference in a large class of MLNs.

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