← Authors

Michael White

28 papers · 2005–2026 · 7 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (15) πŸƒ Academic Marathon (20) 🌈 Renaissance Researcher (6) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (31) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (6) 🧬 Topic Evolution πŸ‘₯ Mega-Team (77) πŸ’Ž Century Club (27) ❓ The Questioner πŸ”₯ Unstoppable (8) πŸ—ƒοΈ Keyword Collector (70)

Conferences

ACL (11) EMNLP (6) COLING (5) NAACL (3) CONLL (1) EACL (1) IJCNLP (1)

Top co-authors

Rajakrishnan Rajkumar (6) Ankit Arun (4) Soumya Batra (4) Huan Sun (4) Shashank Jain (4) Peyman Heidari (4) Dominic Espinosa (3) Ashley Lewis (3) David King (3) Shreyan Bakshi (2)

Keywords

acceptability classifier (3) natural language generation (3) semantic parsing (3) surface realization (2) knowledge distillation (2) sequence-to-sequence model (2) morphological inflection (2) semantic correctness (2) knowledge base question answering (2) question answering (1) question classification (1) semantic representation (1) synthetic data generation (1) tree search (1) text classification (1) interactive systems (1) data efficiency (1) language modeling (1) model fine-tuning (1) pre-trained model (1)

Papers

Beyond Length: Context-Aware Expansion and Independence as Developmentally Sensitive Evaluation in Child Utterances EACL 2026
Winning Big with Small Models: Knowledge Distillation vs. Self-Training for Reducing Hallucination in QA Agents ACL 2025
When is Tree Search Useful for LLM Planning? It Depends on the Discriminator ACL 2024
Insights of a Usability Study for KBQA Interactive Semantic Parsing: Generation Yields Benefits over Templates but External Validity Remains Challenging COLING 2024
Text-to-SQL Error Correction with Language Models of Code ACL 2023
Towards Transparent Interactive Semantic Parsing via Step-by-Step Correction ACL 2022
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code EMNLP 2022
Building Adaptive Acceptability Classifiers for Neural NLG EMNLP 2021
Structure-to-Text Generation with Self-Training, Acceptability Classifiers and Context-Conditioning for the GEM Shared Task IJCNLP 2021
Structure-to-Text Generation with Self-Training, Acceptability Classifiers and Context-Conditioning for the GEM Shared Task ACL 2021
Best Practices for Data-Efficient Modeling in NLG:How to Train Production-Ready Neural Models with Less Data COLING 2020
The OSU/Facebook Realizer for SRST 2019: Seq2Seq Inflection and Serialized Tree2Tree Linearization EMNLP 2019
Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue ACL 2019
Madly Ambiguous: A Game for Learning about Structural Ambiguity and Why It’s Hard for Computers NAACL 2018
The OSU Realizer for SRST β€˜18: Neural Sequence-to-Sequence Inflection and Incremental Locality-Based Linearization ACL 2018
Using Paraphrasing and Memory-Augmented Models to Combat Data Sparsity in Question Interpretation with a Virtual Patient Dialogue System NAACL 2018
That’s Not What I Meant! Using Parsers to Avoid Structural Ambiguities in Generated Text ACL 2014
Minimal Dependency Length in Realization Ranking CONLL 2012
Minimal Dependency Length in Realization Ranking EMNLP 2012
A Joint Phrasal and Dependency Model for Paraphrase Alignment COLING 2012
Further Meta-Evaluation of Broad-Coverage Surface Realization EMNLP 2010
Designing Agreement Features for Realization Ranking COLING 2010
Perceptron Reranking for CCG Realization EMNLP 2009
Exploiting Named Entity Classes in CCG Surface Realization NAACL 2009
Hypertagging: Supertagging for Surface Realization with CCG ACL 2008
Learning to Say It Well: Reranking Realizations by Predicted Synthesis Quality ACL 2006
Learning to Say It Well: Reranking Realizations by Predicted Synthesis Quality COLING 2006
Multimodal Generation in the COMIC Dialogue System ACL 2005