Search Results for author: Karthik Sankaranarayanan

Found 25 papers, 14 papers with code

Role of Language Relatedness in Multilingual Fine-tuning of Language Models: A Case Study in Indo-Aryan Languages

1 code implementation EMNLP 2021 Tejas Indulal Dhamecha, Rudra Murthy V, Samarth Bharadwaj, Karthik Sankaranarayanan, Pushpak Bhattacharyya

We hypothesize and validate that multilingual fine-tuning of pre-trained language models can yield better performance on downstream NLP applications, compared to models fine-tuned on individual languages.

Fine-tuning Natural Language Inference +2

Topic Transferable Table Question Answering

1 code implementation EMNLP 2021 Saneem Ahmed Chemmengath, Vishwajeet Kumar, Samarth Bharadwaj, Jaydeep Sen, Mustafa Canim, Soumen Chakrabarti, Alfio Gliozzo, Karthik Sankaranarayanan

Weakly-supervised table question-answering(TableQA) models have achieved state-of-art performance by using pre-trained BERT transformer to jointly encoding a question and a table to produce structured query for the question.

Question Answering Question Generation

AIT-QA: Question Answering Dataset over Complex Tables in the Airline Industry

1 code implementation24 Jun 2021 Yannis Katsis, Saneem Chemmengath, Vishwajeet Kumar, Samarth Bharadwaj, Mustafa Canim, Michael Glass, Alfio Gliozzo, Feifei Pan, Jaydeep Sen, Karthik Sankaranarayanan, Soumen Chakrabarti

Recent advances in transformers have enabled Table Question Answering (Table QA) systems to achieve high accuracy and SOTA results on open domain datasets like WikiTableQuestions and WikiSQL.

Question Answering Semantic Parsing

Addressing target shift in zero-shot learning using grouped adversarial learning

1 code implementation2 Mar 2020 Saneem Ahmed Chemmengath, Soumava Paul, Samarth Bharadwaj, Suranjana Samanta, Karthik Sankaranarayanan

Zero-shot learning (ZSL) algorithms typically work by exploiting attribute correlations to be able to make predictions in unseen classes.

Zero-Shot Learning

A Modular Architecture for Unsupervised Sarcasm Generation

no code implementations IJCNLP 2019 Abhijit Mishra, Tarun Tater, Karthik Sankaranarayanan

In this paper, we propose a novel framework for sarcasm generation; the system takes a literal negative opinion as input and translates it into a sarcastic version.

Information Retrieval Machine Translation +2

Storytelling from Structured Data and Knowledge Graphs : An NLG Perspective

no code implementations ACL 2019 Abhijit Mishra, Anirban Laha, Karthik Sankaranarayanan, Parag Jain, Saravanan Krishnan

In this tutorial, we wish to cover the foundational, methodological, and system development aspects of translating structured data (such as data in tabular form) and knowledge bases (such as knowledge graphs) into natural language.

Knowledge Graphs Translation

Unified Semantic Parsing with Weak Supervision

1 code implementation ACL 2019 Priyanka Agrawal, Parag Jain, Ayushi Dalmia, Abhishek Bansal, Ashish Mittal, Karthik Sankaranarayanan

Semantic parsing over multiple knowledge bases enables a parser to exploit structural similarities of programs across the multiple domains.

Semantic Parsing


no code implementations ICLR 2019 Saneem Ahmed Chemmengath, Samarth Bharadwaj, Suranjana Samanta, Karthik Sankaranarayanan

An unintended consequence of feature sharing is the model fitting to correlated tasks within the dataset, termed negative transfer.

Domain Adaptation

On Controllable Sparse Alternatives to Softmax

no code implementations NeurIPS 2018 Anirban Laha, Saneem A. Chemmengath, Priyanka Agrawal, Mitesh M. Khapra, Karthik Sankaranarayanan, Harish G. Ramaswamy

Converting an n-dimensional vector to a probability distribution over n objects is a commonly used component in many machine learning tasks like multiclass classification, multilabel classification, attention mechanisms etc.

Abstractive Text Summarization Classification +3

Unsupervised Neural Text Simplification

1 code implementation ACL 2019 Sai Surya, Abhijit Mishra, Anirban Laha, Parag Jain, Karthik Sankaranarayanan

The paper presents a first attempt towards unsupervised neural text simplification that relies only on unlabeled text corpora.

Denoising Text Simplification

Scalable Micro-planned Generation of Discourse from Structured Data

1 code implementation CL 2019 Anirban Laha, Parag Jain, Abhijit Mishra, Karthik Sankaranarayanan

We present a framework for generating natural language description from structured data such as tables; the problem comes under the category of data-to-text natural language generation (NLG).

Knowledge Graphs Text Generation

Unsupervised Controllable Text Formalization

1 code implementation10 Sep 2018 Parag Jain, Abhijit Mishra, Amar Prakash Azad, Karthik Sankaranarayanan

We propose a novel framework for controllable natural language transformation.

Modeling Topical Coherence in Discourse without Supervision

no code implementations2 Sep 2018 Disha Shrivastava, Abhijit Mishra, Karthik Sankaranarayanan

Our evaluation shows that the measured coherence scores are positively correlated with the ground truth for both the datasets.

DuoRC: Towards Complex Language Understanding with Paraphrased Reading Comprehension

1 code implementation ACL 2018 Amrita Saha, Rahul Aralikatte, Mitesh M. Khapra, Karthik Sankaranarayanan

We propose DuoRC, a novel dataset for Reading Comprehension (RC) that motivates several new challenges for neural approaches in language understanding beyond those offered by existing RC datasets.

Language understanding Reading Comprehension

Generating Descriptions from Structured Data Using a Bifocal Attention Mechanism and Gated Orthogonalization

2 code implementations NAACL 2018 Preksha Nema, Shreyas Shetty, Parag Jain, Anirban Laha, Karthik Sankaranarayanan, Mitesh M. Khapra

For example, while generating descriptions from a table, a human would attend to information at two levels: (i) the fields (macro level) and (ii) the values within the field (micro level).

Complex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graph

1 code implementation31 Jan 2018 Amrita Saha, Vardaan Pahuja, Mitesh M. Khapra, Karthik Sankaranarayanan, Sarath Chandar

Further, unlike existing large scale QA datasets which contain simple questions that can be answered from a single tuple, the questions in our dialogs require a larger subgraph of the KG.

Knowledge Graphs Question Answering

A Machine Learning Approach for Evaluating Creative Artifacts

no code implementations18 Jul 2017 Disha Shrivastava, Saneem Ahmed CG, Anirban Laha, Karthik Sankaranarayanan

Our proposed learning framework is applicable to all creative domains; yet we evaluate it on a dataset of movies created from IMDb and Rotten Tomatoes due to availability of audience and critic scores, which can be used as proxy ground truth labels for creativity.

Story Generation from Sequence of Independent Short Descriptions

no code implementations18 Jul 2017 Parag Jain, Priyanka Agrawal, Abhijit Mishra, Mohak Sukhwani, Anirban Laha, Karthik Sankaranarayanan

Existing Natural Language Generation (NLG) systems are weak AI systems and exhibit limited capabilities when language generation tasks demand higher levels of creativity, originality and brevity.

Machine Translation Story Generation +1

Towards Building Large Scale Multimodal Domain-Aware Conversation Systems

no code implementations1 Apr 2017 Amrita Saha, Mitesh Khapra, Karthik Sankaranarayanan

With this dataset, we propose 5 new sub-tasks for multimodal conversations along with their evaluation methodology.

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