Papers by Shereen Oraby

8 papers
FLAMES: Improving LLM Math Reasoning via a Fine-Grained Analysis of the Data Synthesis Pipeline (2025.findings-emnlp)

Copied to clipboard

Challenge: Recent work improving LLM math reasoning with synthetic data uses unique setups, making comparison of data synthesis strategies impractical.
Approach: They propose a framework for LLM assessment of math reasoning with synthetic data . they use 10 existing data synthesis strategies and multiple other factors to study performance .
Outcome: The proposed data synthesis strategies outperform public datasets on OlympiadBench, CollegeMath, GSMPlus and MATH.
SlugNERDS: A Named Entity Recognition Tool for Open Domain Dialogue Systems (L18-1)

Copied to clipboard

Challenge: UCSC researchers have developed an open domain social bot aimed at casual conversation . NER and NEL are important preprocessing steps for understanding user intent in open domain dialogue systems.
Approach: They propose a tool for NER and NEL in open domain dialogue that addresses these challenges . they also propose two corpora based on 10,000 real user conversations .
Outcome: The proposed open domain social bot is aimed at casual conversation.
ExPUNations: Augmenting Puns with Keywords and Explanations (2022.emnlp-main)

Copied to clipboard

Challenge: Puns add the challenge of fusing commonsense and world knowledge with the ability to interpret lexical-semantic ambiguity.
Approach: They propose to augment existing datasets with detailed crowdsourced annotations of puns, keywords and fine-grained funniness ratings to challenge current models' ability to understand and generate humor.
Outcome: The proposed tasks include explanation generation to aid with pun classification and keyword-conditioned pun generation to challenge state-of-the-art models' ability to understand and generate humor.
LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent studies have shown that LLMs struggle with instructions containing multiple constraints.
Approach: They propose a self-correction pipeline that decomposes the original instruction into a list of constraints and uses a Critic model to decide when and where the LLM’s response needs refinement.
Outcome: The proposed model outperforms GPT-4 on RealInstruct and IFEval even with weak feedback.
Curate and Generate: A Corpus and Method for Joint Control of Semantics and Style in Neural NLG (P19-1)

Copied to clipboard

Challenge: Neural natural language generation (NNLG) models generate syntactically correct utterances from structured inputs without needing hand-crafted rules or templates.
Approach: They propose a method for generating a corpus of parallel meaning representations with rich style markup using freely available and naturally descriptive user reviews.
Outcome: The proposed method can be scalably reused to generate NLG datasets for other domains.
Exploring Conversational Language Generation for Rich Content about Hotels (L18-1)

Copied to clipboard

Challenge: a new method is needed to generate natural dialogues for hotel information . a recent study shows that hotel descriptions are not a good match for conversational interaction .
Approach: They propose to use stylistic features to generate and score hotel dialogues from hotel descriptions . they use hotel descriptions written by human writers within Google Content Studio .
Outcome: The proposed models can be used to generate natural dialogues for hotels . the authors show that the sentences in the original written hotel descriptions are not a good match for conversational interaction.
Unsupervised Melody-to-Lyrics Generation (2023.acl-long)

Copied to clipboard

Challenge: Existing methods for automatic melody-to-lyric generation are limited due to the limited amount of melody-lyrical aligned data.
Approach: They propose a method for automatic melody-to-lyric generation without training on any aligned melody-lyr data.
Outcome: The proposed model generates high-quality lyrics that are singable, intelligible, and coherent than baseline models.
Context-Situated Pun Generation (2022.emnlp-main)

Copied to clipboard

Challenge: a new task for context-situated pun generation uses a given context to generate puns . human evaluation shows that 69% of top retrieved pun words can be used to generate context-based puns.
Approach: They propose a task where puns are generated based on contextual keywords and pun words.
Outcome: The proposed system generates successful puns 31% of the time given a plausible tuple of context words and pun pairs.

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