565 citations · 760 across the 20 of their papers we have counts for
22 papers
Topical-Chat: Towards Knowledge-Grounded Open-Domain Conversations
Karthik Gopalakrishnan, Behnam Hedayatnia, Qinlang Chen +5
Building socialbots that can have deep, engaging open-domain conversations with humans is one of the grand challenges of artificial intelligence (AI). To this end, bots need to be…
Don't Stop Self-Supervision: Accent Adaptation of Speech Representations via Residual Adapters
Anshu Bhatia, Sanchit Sinha, Saket Dingliwal +3
Speech representations learned in a self-supervised fashion from massive unlabeled speech corpora have been adapted successfully toward several downstream tasks. However, such repr…
Rethinking the Role of Scale for In-Context Learning: An Interpretability-based Case Study at 66 Billion Scale
Hritik Bansal, Karthik Gopalakrishnan, Saket Dingliwal +3
Language models have been shown to perform better with an increase in scale on a wide variety of tasks via the in-context learning paradigm. In this paper, we investigate the hypot…
Alexa Teacher Model: Pretraining and Distilling Multi-Billion-Parameter Encoders for Natural Language Understanding Systems
Jack FitzGerald, Shankar Ananthakrishnan, Konstantine Arkoudas +38
We present results from a large-scale experiment on pretraining encoders with non-embedding parameter counts ranging from 700M to 9.3B, their subsequent distillation into smaller m…
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao +448
Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabil…
Multi-Sentence Knowledge Selection in Open-Domain Dialogue
Mihail Eric, Nicole Chartier, Behnam Hedayatnia +4
Incorporating external knowledge sources effectively in conversations is a longstanding problem in open-domain dialogue research. The existing literature on open-domain knowledge s…
Analyzing the Limits of Self-Supervision in Handling Bias in Language
Lisa Bauer, Karthik Gopalakrishnan, Spandana Gella +3
Prompting inputs with natural language task descriptions has emerged as a popular mechanism to elicit reasonably accurate outputs from large-scale generative language models with l…
Think Before You Speak: Explicitly Generating Implicit Commonsense Knowledge for Response Generation
Pei Zhou, Karthik Gopalakrishnan, Behnam Hedayatnia +5
Implicit knowledge, such as common sense, is key to fluid human conversations. Current neural response generation (RG) models are trained to generate responses directly, omitting u…
"How Robust r u?": Evaluating Task-Oriented Dialogue Systems on Spoken Conversations
Seokhwan Kim, Yang Liu, Di Jin +4
Most prior work in dialogue modeling has been on written conversations mostly because of existing data sets. However, written dialogues are not sufficient to fully capture the natu…
Commonsense-Focused Dialogues for Response Generation: An Empirical Study
Pei Zhou, Karthik Gopalakrishnan, Behnam Hedayatnia +5
Smooth and effective communication requires the ability to perform latent or explicit commonsense inference. Prior commonsense reasoning benchmarks (such as SocialIQA and Commonsen…
Generative Conversational Networks
Alexandros Papangelis, Karthik Gopalakrishnan, Aishwarya Padmakumar +3
Inspired by recent work in meta-learning and generative teaching networks, we propose a framework called Generative Conversational Networks, in which conversational agents learn to…
Go Beyond Plain Fine-tuning: Improving Pretrained Models for Social Commonsense
Ting-Yun Chang, Yang Liu, Karthik Gopalakrishnan +3
Pretrained language models have demonstrated outstanding performance in many NLP tasks recently. However, their social intelligence, which requires commonsense reasoning about the…
Incorporating Commonsense Knowledge Graph in Pretrained Models for Social Commonsense Tasks
Ting-Yun Chang, Yang Liu, Karthik Gopalakrishnan +3
Pretrained language models have excelled at many NLP tasks recently; however, their social intelligence is still unsatisfactory. To enable this, machines need to have a more genera…
VISITRON: Visual Semantics-Aligned Interactively Trained Object-Navigator
Ayush Shrivastava, Karthik Gopalakrishnan, Yang Liu +4
Interactive robots navigating photo-realistic environments need to be trained to effectively leverage and handle the dynamic nature of dialogue in addition to the challenges underl…
Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access Track in DSTC9
Seokhwan Kim, Mihail Eric, Behnam Hedayatnia +4
Most prior work on task-oriented dialogue systems are restricted to a limited coverage of domain APIs, while users oftentimes have domain related requests that are not covered by t…
Overview of the Ninth Dialog System Technology Challenge: DSTC9
Chulaka Gunasekara, Seokhwan Kim, Luis Fernando D'Haro +36
This paper introduces the Ninth Dialog System Technology Challenge (DSTC-9). This edition of the DSTC focuses on applying end-to-end dialog technologies for four distinct tasks in…
Are Neural Open-Domain Dialog Systems Robust to Speech Recognition Errors in the Dialog History? An Empirical Study
Karthik Gopalakrishnan, Behnam Hedayatnia, Longshaokan Wang +2
Large end-to-end neural open-domain chatbots are becoming increasingly popular. However, research on building such chatbots has typically assumed that the user input is written in…
Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access
Seokhwan Kim, Mihail Eric, Karthik Gopalakrishnan +3
Most prior work on task-oriented dialogue systems are restricted to a limited coverage of domain APIs, while users oftentimes have domain related requests that are not covered by t…
Policy-Driven Neural Response Generation for Knowledge-Grounded Dialogue Systems
Behnam Hedayatnia, Karthik Gopalakrishnan, Seokhwan Kim +3
Open-domain dialogue systems aim to generate relevant, informative and engaging responses. Seq2seq neural response generation approaches do not have explicit mechanisms to control…
Advancing the State of the Art in Open Domain Dialog Systems through the Alexa Prize
Chandra Khatri, Behnam Hedayatnia, Anu Venkatesh +19
Building open domain conversational systems that allow users to have engaging conversations on topics of their choice is a challenging task. Alexa Prize was launched in 2016 to tac…
Social Interaction in the Flickr Social Network
Karthik Gopalakrishnan, Arun Pandey, Joydeep Chandra
Online social networking sites such as Facebook, Twitter and Flickr are among the most popular sites on the Web, providing platforms for sharing information and interacting with a…
Bublz! : Playing with Bubbles to Develop Mathematical Thinking
Dhruv Chand, Karthik Gopalakrishnan, Nisha KK +2
We encounter mathematical problems in various forms in our lives, thus making mathematical thinking an important human ability. In this paper, we present Bublz!, a simple, click-dr…