Papers by Ozan Irsoy

6 papers
Collective Entity Disambiguation with Structured Gradient Tree Boosting (N18-1)

Copied to clipboard

Challenge: Existing work on structured gradient tree boosting for collective entity disambiguation is limited to regular classification or regression problems.
Approach: They propose a structured learning model that uses gradient tree boosting to disambiguate named entities in a document.
Outcome: The proposed model outperforms the previous state-of-the-art neural system by near 1% absolute accuracy on the popular AIDA-CoNLL dataset.
Distillation of encoder-decoder transformers for sequence labelling (2023.findings-eacl)

Copied to clipboard

Challenge: despite the strong trend in NLP to explore the use of large language models, there is still limited work evaluating prompting and decoding mechanisms for SL tasks.
Approach: They propose a hallucination-free framework for sequence tagging that is especially suited for distillation.
Outcome: The proposed framework performs well across multiple sequence labelling datasets and in a few-shot learning scenario.
Semantic Role Labeling as Syntactic Dependency Parsing (2020.emnlp-main)

Copied to clipboard

Challenge: Using propBank-style semantic role labeling, we reduce the task to syntactic dependency parsing.
Approach: They propose to convert SRL annotations into dependency tree representations through joint labels that permit highly accurate recovery back to the original format.
Outcome: The proposed scheme reduces the task of (span-based) PropBank-style semantic role labeling to syntactic dependency parsing.
Academics Can Contribute to Domain-Specialized Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Commercially available models dominate academic leaderboards, focusing on creating and adapting general-purpose models . however, general- purpose models often underperform in specialized domains, and domain-specific models yield superior results.
Approach: They advocate for a renewed focus on developing and evaluating domain- and task-specific models . they advocate for an adapted or adapted model that can be used to improve academic leaderboard standings .
Outcome: The proposed model can do well on professional and linguistic examinations, college-level knowledge questions, and collections of reasoning tasks.
MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies (2023.acl-long)

Copied to clipboard

Challenge: Autoregressive language models are trained by minimizing the cross-entropy of the model distribution Q relative to the data distribution P. However, these systems still struggle in many openended generation settings, where they are asked to produce a long text following a short prompt.
Approach: They propose to combine forward and reverse cross-entropy to train autoregressive language models by minimizing the cross-Entropy of the model distribution Q relative to the data distribution P.
Outcome: The proposed model overgeneralizes and produces non-human-like text without complex decoding strategies.
Improving Instruct Models for Free: A Study on Partial Adaptation (2025.emnlp-main)

Copied to clipboard

Challenge: Instruct models are deemed superior and more usable but can be eroded by instruction tuning . a recent study shows that instruct models are better at following instructions than base models .
Approach: They scale down the strength of instruction tuning to improve model performance . they show that reducing instruction tuning results in material improvement .
Outcome: The proposed model improves on a few-shot in-context learning benchmark . but it loses some degree of its in-training ability .

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