Search Results for author: Mitesh M. Khapra

Found 69 papers, 29 papers with code

On the weak link between importance and prunability of attention heads

no code implementations EMNLP 2020 Aakriti Budhraja, Madhura Pande, Preksha Nema, Pratyush Kumar, Mitesh M. Khapra

Given the success of Transformer-based models, two directions of study have emerged: interpreting role of individual attention heads and down-sizing the models for efficiency.

Aksharantar: Towards building open transliteration tools for the next billion users

1 code implementation6 May 2022 Yash Madhani, Sushane Parthan, Priyanka Bedekar, Ruchi Khapra, Vivek Seshadri, Anoop Kunchukuttan, Pratyush Kumar, Mitesh M. Khapra

We introduce a new, large, diverse testset for Indic language transliteration containing 103k words pairs spanning 19 languages that enables fine-grained analysis of transliteration models.

Transliteration

Joint Transformer/RNN Architecture for Gesture Typing in Indic Languages

no code implementations COLING 2020 Emil Biju, Anirudh Sriram, Mitesh M. Khapra, Pratyush Kumar

Gesture typing is a method of typing words on a touch-based keyboard by creating a continuous trace passing through the relevant keys.

Transliteration

A survey in Adversarial Defences and Robustness in NLP

no code implementations12 Mar 2022 Shreya Goyal, Sumanth Doddapaneni, Mitesh M. Khapra, Balaraman Ravindran

In contrast with image data, generating adversarial attacks and defending these models is not easy in NLP because of the discrete nature of the text data.

Adversarial Defense named-entity-recognition +3

Active Evaluation: Efficient NLG Evaluation with Few Pairwise Comparisons

1 code implementation ACL 2022 Akash Kumar Mohankumar, Mitesh M. Khapra

In this work, we introduce Active Evaluation, a framework to efficiently identify the top-ranked system by actively choosing system pairs for comparison using dueling bandit algorithms.

Towards Building ASR Systems for the Next Billion Users

no code implementations6 Nov 2021 Tahir Javed, Sumanth Doddapaneni, Abhigyan Raman, Kaushal Santosh Bhogale, Gowtham Ramesh, Anoop Kunchukuttan, Pratyush Kumar, Mitesh M. Khapra

Second, using this raw speech data we pretrain several variants of wav2vec style models for 40 Indian languages.

A Framework for Rationale Extraction for Deep QA models

no code implementations9 Oct 2021 Sahana Ramnath, Preksha Nema, Deep Sahni, Mitesh M. Khapra

As neural-network-based QA models become deeper and more complex, there is a demand for robust frameworks which can access a model's rationale for its prediction.

Explanation Generation Question Answering +1

On the Prunability of Attention Heads in Multilingual BERT

no code implementations26 Sep 2021 Aakriti Budhraja, Madhura Pande, Pratyush Kumar, Mitesh M. Khapra

Large multilingual models, such as mBERT, have shown promise in crosslingual transfer.

Perturbation CheckLists for Evaluating NLG Evaluation Metrics

1 code implementation EMNLP 2021 Ananya B. Sai, Tanay Dixit, Dev Yashpal Sheth, Sreyas Mohan, Mitesh M. Khapra

Natural Language Generation (NLG) evaluation is a multifaceted task requiring assessment of multiple desirable criteria, e. g., fluency, coherency, coverage, relevance, adequacy, overall quality, etc.

Data-to-Text Generation

The heads hypothesis: A unifying statistical approach towards understanding multi-headed attention in BERT

1 code implementation22 Jan 2021 Madhura Pande, Aakriti Budhraja, Preksha Nema, Pratyush Kumar, Mitesh M. Khapra

There are two main challenges with existing methods for classification: (a) there are no standard scores across studies or across functional roles, and (b) these scores are often average quantities measured across sentences without capturing statistical significance.

Evaluating a Generative Adversarial Framework for Information Retrieval

no code implementations1 Oct 2020 Ameet Deshpande, Mitesh M. Khapra

Recent advances in Generative Adversarial Networks (GANs) have resulted in its widespread applications to multiple domains.

Information Retrieval Retrieval

Improving Dialog Evaluation with a Multi-reference Adversarial Dataset and Large Scale Pretraining

1 code implementation23 Sep 2020 Ananya B. Sai, Akash Kumar Mohankumar, Siddhartha Arora, Mitesh M. Khapra

However, no such data is publicly available, and hence existing models are usually trained using a single relevant response and multiple randomly selected responses from other contexts (random negatives).

Dialogue Evaluation

A Survey of Evaluation Metrics Used for NLG Systems

no code implementations27 Aug 2020 Ananya B. Sai, Akash Kumar Mohankumar, Mitesh M. Khapra

The expanding number of NLG models and the shortcomings of the current metrics has led to a rapid surge in the number of evaluation metrics proposed since 2014.

Image Captioning Text Generation

A Systematic Evaluation of Object Detection Networks for Scientific Plots

no code implementations5 Jul 2020 Pritha Ganguly, Nitesh Methani, Mitesh M. Khapra, Pratyush Kumar

However, the performance drops drastically when evaluated at a stricter IOU of 0. 9 with the best model giving a mAP of 35. 70%.

object-detection Object Detection +1

On Incorporating Structural Information to improve Dialogue Response Generation

1 code implementation WS 2020 Nikita Moghe, Priyesh Vijayan, Balaraman Ravindran, Mitesh M. Khapra

This requires capturing structural, sequential and semantic information from the conversation context and the background resources.

Response Generation

AI4Bharat-IndicNLP Corpus: Monolingual Corpora and Word Embeddings for Indic Languages

2 code implementations30 Apr 2020 Anoop Kunchukuttan, Divyanshu Kakwani, Satish Golla, Gokul N. C., Avik Bhattacharyya, Mitesh M. Khapra, Pratyush Kumar

We present the IndicNLP corpus, a large-scale, general-domain corpus containing 2. 7 billion words for 10 Indian languages from two language families.

Word Embeddings

Towards Transparent and Explainable Attention Models

2 code implementations ACL 2020 Akash Kumar Mohankumar, Preksha Nema, Sharan Narasimhan, Mitesh M. Khapra, Balaji Vasan Srinivasan, Balaraman Ravindran

To make attention mechanisms more faithful and plausible, we propose a modified LSTM cell with a diversity-driven training objective that ensures that the hidden representations learned at different time steps are diverse.

Scene Graph based Image Retrieval -- A case study on the CLEVR Dataset

no code implementations3 Nov 2019 Sahana Ramnath, Amrita Saha, Soumen Chakrabarti, Mitesh M. Khapra

With the prolification of multimodal interaction in various domains, recently there has been much interest in text based image retrieval in the computer vision community.

Graph Matching Image Retrieval +2

PlotQA: Reasoning over Scientific Plots

no code implementations3 Sep 2019 Nitesh Methani, Pritha Ganguly, Mitesh M. Khapra, Pratyush Kumar

However, in practice, this is an unrealistic assumption because many questions require reasoning and thus have real-valued answers which appear neither in a small fixed size vocabulary nor in the image.

Chart Question Answering Question Answering +1

Let's Ask Again: Refine Network for Automatic Question Generation

1 code implementation IJCNLP 2019 Preksha Nema, Akash Kumar Mohankumar, Mitesh M. Khapra, Balaji Vasan Srinivasan, Balaraman Ravindran

It is desired that the generated question should be (i) grammatically correct (ii) answerable from the passage and (iii) specific to the given answer.

Question Generation Question-Generation

On Knowledge distillation from complex networks for response prediction

no code implementations NAACL 2019 Siddhartha Arora, Mitesh M. Khapra, Harish G. Ramaswamy

In order to overcome this, we use standard simple models which do not capture all pairwise interactions, but learn to emulate certain characteristics of a complex teacher network.

Knowledge Distillation Question Answering

Graph Convolutional Network with Sequential Attention For Goal-Oriented Dialogue Systems

no code implementations ICLR 2019 Suman Banerjee, Mitesh M. Khapra

Domain specific goal-oriented dialogue systems typically require modeling three types of inputs, viz., (i) the knowledge-base associated with the domain, (ii) the history of the conversation, which is a sequence of utterances and (iii) the current utterance for which the response needs to be generated.

Document Dating Goal-Oriented Dialogue Systems +2

Dissecting an Adversarial framework for Information Retrieval

no code implementations ICLR 2019 Ameet Deshpande, Mitesh M. Khapra

Recent advances in Generative Adversarial Networks facilitated by improvements to the framework and successful application to various problems has resulted in extensions to multiple domains.

Information Retrieval Retrieval

Frustratingly Poor Performance of Reading Comprehension Models on Non-adversarial Examples

no code implementations4 Apr 2019 Soham Parikh, Ananya B. Sai, Preksha Nema, Mitesh M. Khapra

We believe that the non-adversarial dataset created as a part of this work would complement the research on adversarial evaluation and give a more realistic assessment of the ability of RC models.

Reading Comprehension

ElimiNet: A Model for Eliminating Options for Reading Comprehension with Multiple Choice Questions

1 code implementation ICLR 2018 Soham Parikh, Ananya B. Sai, Preksha Nema, Mitesh M. Khapra

Specifically, it has gates which decide whether an option can be eliminated given the passage, question pair and if so it tries to make the passage representation orthogonal to this eliminated option (akin to ignoring portions of the passage corresponding to the eliminated option).

Multiple-choice Reading Comprehension

Efficient Video Classification Using Fewer Frames

1 code implementation CVPR 2019 Shweta Bhardwaj, Mukundhan Srinivasan, Mitesh M. Khapra

We focus on building compute-efficient video classification models which process fewer frames and hence have less number of FLOPs.

Classification General Classification +1

Re-evaluating ADEM: A Deeper Look at Scoring Dialogue Responses

no code implementations23 Feb 2019 Ananya B. Sai, Mithun Das Gupta, Mitesh M. Khapra, Mukundhan Srinivasan

ADEM(Lowe et al. 2017) formulated the automatic evaluation of dialogue systems as a learning problem and showed that such a model was able to predict responses which correlate significantly with human judgements, both at utterance and system level.

Dialogue Evaluation Response Generation

Studying the Plasticity in Deep Convolutional Neural Networks using Random Pruning

1 code implementation26 Dec 2018 Deepak Mittal, Shweta Bhardwaj, Mitesh M. Khapra, Balaraman Ravindran

In this work, we report experiments which suggest that the comparable performance of the pruned network is not due to the specific criterion chosen but due to the inherent plasticity of deep neural networks which allows them to recover from the loss of pruned filters once the rest of the filters are fine-tuned.

Image Classification Image Segmentation +3

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

Towards Exploiting Background Knowledge for Building Conversation Systems

1 code implementation EMNLP 2018 Nikita Moghe, Siddhartha Arora, Suman Banerjee, Mitesh M. Khapra

Existing dialog datasets contain a sequence of utterances and responses without any explicit background knowledge associated with them.

Towards a Better Metric for Evaluating Question Generation Systems

1 code implementation EMNLP 2018 Preksha Nema, Mitesh M. Khapra

In particular, it is important to verify whether such metrics used for evaluating AQG systems focus on answerability of the generated question by preferring questions which contain all relevant information such as question type (Wh-types), entities, relations, etc.

Knowledge Graphs Question Generation +1

HOPF: Higher Order Propagation Framework for Deep Collective Classification

1 code implementation31 May 2018 Priyesh Vijayan, Yash Chandak, Mitesh M. Khapra, Srinivasan Parthasarathy, Balaraman Ravindran

Given a graph where every node has certain attributes associated with it and some nodes have labels associated with them, Collective Classification (CC) is the task of assigning labels to every unlabeled node using information from the node as well as its neighbors.

Classification General Classification

Fusion Graph Convolutional Networks

1 code implementation31 May 2018 Priyesh Vijayan, Yash Chandak, Mitesh M. Khapra, Srinivasan Parthasarathy, Balaraman Ravindran

State-of-the-art models for node classification on such attributed graphs use differentiable recursive functions that enable aggregation and filtering of neighborhood information from multiple hops.

General Classification Node Classification

I Have Seen Enough: A Teacher Student Network for Video Classification Using Fewer Frames

no code implementations12 May 2018 Shweta Bhardwaj, Mitesh M. Khapra

We then train a student network whose objective is to process only a small fraction of the frames in the video and still produce a representation which is very close to the representation computed by the teacher network.

Classification General Classification +2

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.

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).

Recovering from Random Pruning: On the Plasticity of Deep Convolutional Neural Networks

1 code implementation31 Jan 2018 Deepak Mittal, Shweta Bhardwaj, Mitesh M. Khapra, Balaraman Ravindran

In this work, we report experiments which suggest that the comparable performance of the pruned network is not due to the specific criterion chosen but due to the inherent plasticity of deep neural networks which allows them to recover from the loss of pruned filters once the rest of the filters are fine-tuned.

Image Classification object-detection +1

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 Correlational Encoder Decoder Architecture for Pivot Based Sequence Generation

no code implementations COLING 2016 Amrita Saha, Mitesh M. Khapra, Sarath Chandar, Janarthanan Rajendran, Kyunghyun Cho

However, there is no parallel training data available between X and Y but, training data is available between X & Z and Z & Y (as is often the case in many real world applications).

Transliteration

Bridge Correlational Neural Networks for Multilingual Multimodal Representation Learning

1 code implementation NAACL 2016 Janarthanan Rajendran, Mitesh M. Khapra, Sarath Chandar, Balaraman Ravindran

In this work, we address a real-world scenario where no direct parallel data is available between two views of interest (say, $V_1$ and $V_2$) but parallel data is available between each of these views and a pivot view ($V_3$).

Document Classification Representation Learning +2

Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domain

2 code implementations10 Oct 2015 Janarthanan Rajendran, Aravind Srinivas, Mitesh M. Khapra, P. Prasanna, Balaraman Ravindran

Second, the agent should be able to selectively transfer, which is the ability to select and transfer from different and multiple source tasks for different parts of the state space of the target task.

Correlational Neural Networks

2 code implementations27 Apr 2015 Sarath Chandar, Mitesh M. Khapra, Hugo Larochelle, Balaraman Ravindran

CCA based approaches learn a joint representation by maximizing correlation of the views when projected to the common subspace.

Representation Learning Transfer Learning

Experiences in Resource Generation for Machine Translation through Crowdsourcing

no code implementations LREC 2012 Anoop Kunchukuttan, Shourya Roy, Pratik Patel, Kushal Ladha, Somya Gupta, Mitesh M. Khapra, Pushpak Bhattacharyya

The logistics of collecting resources for Machine Translation (MT) has always been a cause of concern for some of the resource deprived languages of the world.

Machine Translation Translation

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