Search Results for author: Dinesh Raghu

Found 13 papers, 5 papers with code

Joint Reasoning on Hybrid-knowledge sources for Task-Oriented Dialog

1 code implementation13 Oct 2022 Mayank Mishra, Danish Contractor, Dinesh Raghu

Traditional systems designed for task oriented dialog utilize knowledge present only in structured knowledge sources to generate responses.

Response Generation

Matching Papers and Reviewers at Large Conferences

1 code implementation24 Feb 2022 Kevin Leyton-Brown, Mausam, Yatin Nandwani, Hedayat Zarkoob, Chris Cameron, Neil Newman, Dinesh Raghu

Peer-reviewed conferences, the main publication venues in CS, rely critically on matching highly qualified reviewers for each paper.

End-to-End Learning of Flowchart Grounded Task-Oriented Dialogs

1 code implementation EMNLP 2021 Dinesh Raghu, Shantanu Agarwal, Sachindra Joshi, Mausam

We propose a novel problem within end-to-end learning of task-oriented dialogs (TOD), in which the dialog system mimics a troubleshooting agent who helps a user by diagnosing their problem (e. g., car not starting).

Flowchart Grounded Dialog Response Generation Retrieval +1

Constraint based Knowledge Base Distillation in End-to-End Task Oriented Dialogs

no code implementations Findings (ACL) 2021 Dinesh Raghu, Atishya Jain, Mausam, Sachindra Joshi

In this paper, we propose a novel filtering technique that consists of (1) a pairwise similarity based filter that identifies relevant information by respecting the n-ary structure in a KB record.

Response Generation Task-Oriented Dialogue Systems

Unsupervised Learning of KB Queries in Task-Oriented Dialogs

no code implementations30 Apr 2020 Dinesh Raghu, Nikhil Gupta, Mausam

Task-oriented dialog (TOD) systems often need to formulate knowledge base (KB) queries corresponding to the user intent and use the query results to generate system responses.

Reinforcement Learning (RL)

Mask & Focus: Conversation Modelling by Learning Concepts

no code implementations11 Feb 2020 Gaurav Pandey, Dinesh Raghu, Sachindra Joshi

The proposed model, referred to as Mask \& Focus maps the input context to a sequence of concepts which are then used to generate the response concepts.

Machine Translation Response Generation

Unsupervised Learning of Interpretable Dialog Models

no code implementations2 Nov 2018 Dhiraj Madan, Dinesh Raghu, Gaurav Pandey, Sachindra Joshi

However these states need to be handcrafted and annotated in the data.

Multi-level Memory for Task Oriented Dialogs

1 code implementation NAACL 2019 Revanth Reddy, Danish Contractor, Dinesh Raghu, Sachindra Joshi

Instead of using triples to store KB results, we introduce a novel multi-level memory architecture consisting of cells for each query and their corresponding results.

Disentangling Language and Knowledge in Task-Oriented Dialogs

1 code implementation NAACL 2019 Dinesh Raghu, Nikhil Gupta, Mausam

We also systematically modify existing datasets to measure disentanglement and show BoSsNet to be robust to KB modifications.

Disentanglement Language Modelling

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