Papers by Harshit Kumar

5 papers
A Practical Dialogue-Act-Driven Conversation Model for Multi-Turn Response Selection (D19-1)

Copied to clipboard

Challenge: Dialogue acts are important in conversation modeling, but they are rarely available for new conversations.
Approach: They propose an end-to-end multi-task model that integrates dialogue acts with context and response in a crossway fashion.
Outcome: The proposed model improves the accuracy of the dialogue act prediction task and the MRR for the response selection task.
Naamapadam: A Large-Scale Named Entity Annotated Data for Indic Languages (2023.acl-long)

Copied to clipboard

Challenge: Named Entity Recognition (NER) is a fundamental task in natural language processing (NLP).
Approach: They present the largest publicly available Named Entity Recognition dataset for the 11 major Indian languages from two language families.
Outcome: The proposed dataset is the largest publicly available Named Entity Recognition (NER) dataset for the 11 major Indian languages from two language families.
Neural Conversational QA: Learning to Reason vs Exploiting Patterns (2020.emnlp-main)

Copied to clipboard

Challenge: Neural Conversational QA tasks such as ShARC require systems to answer questions based on the contents of a given passage.
Approach: They propose to modify a data-set with fewer spurious patterns to exploit them . they also propose to build a heuristic-based program to exploit spurious clues .
Outcome: The proposed program exploits spurious patterns in the ShARC dataset, compared to neural models.
VeeAlign: Multifaceted Context Representation Using Dual Attention for Ontology Alignment (2021.emnlp-main)

Copied to clipboard

Challenge: State-of-the-art Ontology Alignment systems are based on domain-dependent approaches with handcrafted rules or domain-specific architectures, making them unscalable and inefficient.
Approach: They propose a Deep Learning based model that exploits syntactic and semantic information encoded in ontologies by using a dual-attention mechanism.
Outcome: The proposed model exploits syntactic and semantic information encoded in ontologies and is flexible and scalable to different domains with minimal effort.
Dialogue-act-driven Conversation Model : An Experimental Study (C18-1)

Copied to clipboard

Challenge: In the last decade, natural language processing and machine learning have come a long way towards building an automated dialogue system.
Approach: They propose a way to encode dialogue act information and use it to build a model that can use it in a natural way.
Outcome: The proposed model outperforms baseline models on a new daily dialogue dataset and achieves an MRR of about 84.8%.

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