Papers by Ramesh Manuvinakurike

4 papers
Strategy-level Entrainment of Dialogue System Users in a Creative Visual Reference Resolution Task (2022.lrec-1)

Copied to clipboard

Challenge: entrainment is a phenomenon in which interlocutors start speaking more similarly to each other.
Approach: They propose to use crowd-sourced data to study entrainment of users playing a creative reference resolution game with an autonomous dialogue system.
Outcome: The proposed system adapts the user's descriptive strategy to one that is simpler to parse for the natural language understanding unit without impinging on their creativity.
Cue-bot: A Conversational Agent for Assistive Technology (2022.acl-demo)

Copied to clipboard

Challenge: Large-scale pre-training has achieved significant performance gains across many tasks within NLP, including intent prediction and dialogue state tracking.
Approach: They propose to use eye-tracking, mouse controls and an intelligent agent Cue-bot to represent the user in a conversation.
Outcome: The proposed system can be used by people with different levels of disabilities to interact with the world, supported by eye-tracking, mouse controls and an intelligent agent Cue-bot.
RDG-Map: A Multimodal Corpus of Pedagogical Human-Agent Spoken Interactions. (2020.lrec-1)

Copied to clipboard

Challenge: a corpus of 209 spoken game dialogues between a human and a remote-controlled artificial agent is presented.
Approach: They present a multimodal corpus of 209 spoken game dialogues between a human and a remote-controlled artificial agent.
Outcome: The proposed corpus consists of 209 spoken game dialogues between a human and a remote-controlled artificial agent.
Edit me: A Corpus and a Framework for Understanding Natural Language Image Editing (L18-1)

Copied to clipboard

Challenge: a corpus of image edit requests is elicited for real world images, and an annotation framework is developed . evaluators evaluate crowd-sourced annotation as a means of efficiently creating a sizable corpus at a reasonable cost.
Approach: They propose a natural language interface for interacting with an image editing program . they propose an annotation framework for understanding natural language requests .
Outcome: The proposed tool interprets image edit requests and maps them to actionable commands.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations