Papers by Ramesh Manuvinakurike
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
Shachi H Kumar, Hsuan Su, Ramesh Manuvinakurike, Maximilian C. Pinaroc, Sai Prasad, Saurav Sahay, Lama Nachman
| 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
Ramesh Manuvinakurike, Jacqueline Brixey, Trung Bui, Walter Chang, Doo Soon Kim, Ron Artstein, Kallirroi Georgila
| 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. |