Papers by Arash Einolghozati

4 papers
Small But Funny: A Feedback-Driven Approach to Humor Distillation (2024.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have been used to transfer knowledge from LLMs to smaller, smaller language models (SLMs).
Approach: They propose to assign a dual role to the LLM as a “teacher” generating data, as well as evaluating the student’s performance.
Outcome: The proposed approach narrows the performance gap between LLMs and larger models by incorporating feedback into the data.
El Volumen Louder Por Favor: Code-switching in Task-oriented Semantic Parsing (2021.eacl-main)

Copied to clipboard

Challenge: Code-switching (CS) is the alternation of languages within an utterance or conversation.
Approach: They propose to use translation-and-align and augment with a generation model followed by match-and filter to improve CS generalizability of cross-lingual models when data for only one language is available.
Outcome: The proposed models improve when only English data is available alongside zero or a few CS training instances.
A Study on the Efficiency and Generalization of Light Hybrid Retrievers (2023.acl-short)

Copied to clipboard

Challenge: Recent research focuses on building neural retrievers which learn dense embeddings of query and document into a semantic space.
Approach: They propose to use an indexing-efficient dense retriever to reduce hybrid retrievers' memory by using the state-based indexing algorithm.
Outcome: The proposed hybrid retriever saves 13 memory while maintaining 98.0% performance on out-of-domain datasets and adversarial attacks datasets.
Sound Natural: Content Rephrasing in Dialog Systems (2020.emnlp-main)

Copied to clipboard

Challenge: Currently, virtual assistants work in the paradigm of intent-slot tagging and the slot values are directly passed as-is to the execution engine.
Approach: They propose to use BART to rephrase a query to make it more natural . they propose to add a copy-pointer and copy loss to it to improve performance .
Outcome: The proposed model improves on existing models by adding a copy-pointer and copy loss.

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