Search Results for author: Khyathi Raghavi Chandu

Found 14 papers, 1 papers with code

Switch Point biased Self-Training: Re-purposing Pretrained Models for Code-Switching

no code implementations Findings (EMNLP) 2021 Parul Chopra, Sai Krishna Rallabandi, Alan W Black, Khyathi Raghavi Chandu

Code-switching (CS), a ubiquitous phenomenon due to the ease of communication it offers in multilingual communities still remains an understudied problem in language processing.

NER POS

CodemixedNLP: An Extensible and Open NLP Toolkit for Code-Mixing

1 code implementation NAACL (CALCS) 2021 Sai Muralidhar Jayanthi, Kavya Nerella, Khyathi Raghavi Chandu, Alan W Black

The NLP community has witnessed steep progress in a variety of tasks across the realms of monolingual and multilingual language processing recently.

Grounding 'Grounding' in NLP

no code implementations4 Jun 2021 Khyathi Raghavi Chandu, Yonatan Bisk, Alan W Black

And finally, (3) How to advance our current definition to bridge the gap with Cognitive Science?

Reading Between the Lines: Exploring Infilling in Visual Narratives

no code implementations EMNLP 2020 Khyathi Raghavi Chandu, Ruo-Ping Dong, Alan Black

In this paper, we tackle this problem by using \textit{infilling} techniques involving prediction of missing steps in a narrative while generating textual descriptions from a sequence of images.

Visual Storytelling

Positioning yourself in the maze of Neural Text Generation: A Task-Agnostic Survey

no code implementations14 Oct 2020 Khyathi Raghavi Chandu, Alan W Black

Neural text generation metamorphosed into several critical natural language applications ranging from text completion to free form narrative generation.

Image Captioning Machine Translation +2

Denoising Large-Scale Image Captioning from Alt-text Data using Content Selection Models

no code implementations10 Sep 2020 Khyathi Raghavi Chandu, Piyush Sharma, Soravit Changpinyo, Ashish Thapliyal, Radu Soricut

Training large-scale image captioning (IC) models demands access to a rich and diverse set of training examples, gathered from the wild, often from noisy alt-text data.

Denoising Image Captioning

Style Variation as a Vantage Point for Code-Switching

no code implementations1 May 2020 Khyathi Raghavi Chandu, Alan W. black

We believe this viewpoint of CS as style variations opens new perspectives for modeling various tasks in CS text.

Speech Recognition Speech Synthesis +1

Induction and Reference of Entities in a Visual Story

no code implementations15 Sep 2019 Ruo-Ping Dong, Khyathi Raghavi Chandu, Alan W. black

We also conduct human evaluation from which it is concluded that the visual stories generated by our model are preferred 82% of the times.

Visual Storytelling

"My Way of Telling a Story": Persona based Grounded Story Generation

no code implementations14 Jun 2019 Shrimai Prabhumoye, Khyathi Raghavi Chandu, Ruslan Salakhutdinov, Alan W. black

To this end, we propose five models which are incremental extensions to the baseline model to perform the task at hand.

Story Generation Visual Storytelling

A Survey of Code-switched Speech and Language Processing

no code implementations25 Mar 2019 Sunayana Sitaram, Khyathi Raghavi Chandu, Sai Krishna Rallabandi, Alan W. black

Code-switching, the alternation of languages within a conversation or utterance, is a common communicative phenomenon that occurs in multilingual communities across the world.

Textually Enriched Neural Module Networks for Visual Question Answering

no code implementations23 Sep 2018 Khyathi Raghavi Chandu, Mary Arpita Pyreddy, Matthieu Felix, Narendra Nath Joshi

Problems at the intersection of language and vision, like visual question answering, have recently been gaining a lot of attention in the field of multi-modal machine learning as computer vision research moves beyond traditional recognition tasks.

Image Captioning Question Answering +2

Comparative Analysis of Neural QA models on SQuAD

no code implementations WS 2018 Soumya Wadhwa, Khyathi Raghavi Chandu, Eric Nyberg

The task of Question Answering has gained prominence in the past few decades for testing the ability of machines to understand natural language.

Information Retrieval Question Answering +1

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