About Me

I am a 4th year PhD student in the UKP Lab at the Department of Computer Science, Technical University Darmstadt, co-advised by Prof. Iryna Gurevych and Nafise Sadat Moosavi. Before joining UKP, I received my B.Sc. in Computer Science at the University of Indonesia, and later received my M.Sc. from Brown University, advised by James Tompkin and Pedro Felzenszwalb.

I am broadly interested in the problem of human language understanding using techniques from natural language processing and deep learning. My current research focuses on improving the generalization and robustness of neural network models for language understanding tasks, especially in adversarial settings, in which neural models are still lagging behind human performance. Prior to this, I also worked on a semantic parsing problem to translate natural language utterances to executable database queries.

Publications

• Falsesum: Generating Document-level NLI Examples for Recognizing Factual Inconsistency in Summarization
  Prasetya Ajie Utama, Joshua Bambrick, Nafise Sadat Moosavi, Iryna Gurevych
  NAACL 2022 - long paper
  

• IMPLI: Investigating NLI Models’ Performance on Figurative Language
  Kevin Stowe, Prasetya Ajie Utama, Iryna Gurevych
  ACL 2022 - long paper
  

• Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning
  Prasetya Ajie Utama, Nafise Sadat Moosavi, Victor Sanh, Iryna Gurevych
  EMNLP 2021 - short paper
  Code: github

• Towards Debiasing NLU Models from Unknown Biases
  Prasetya Ajie Utama, Nafise Sadat Moosavi, Iryna Gurevych
  EMNLP 2020 - long paper
  Code: github

• Mind the Trade-off: Debiasing NLU Models without Degrading In-Distribution Performance
  Prasetya Ajie Utama, Nafise Sadat Moosavi, Iryna Gurevych
  ACL 2020 - long paper
  Code: github Presentation: video & slides

• Ranking Generated Summaries by Correctness: An Interesting but Challenging Application for Natural Language Inference
  Tobias Falke, Leonardo Ribeiro, Prasetya Ajie Utama, Ido Dagan, Iryna Gurevych
  ACL 2019 - short paper
  Dataset: tudatalib

• DBPal: A Fully Pluggable NL2SQL Training Pipeline
  Nathaniel Weir*, Prasetya Ajie Utama*, Alex Galakatos, Andrew Crotty, Ugur Cetintemel, Carsten Binnig
  SIGMOD 2019 - long paper
  

• DBPal: A Learned NL-Interface for Databases
  Prasetya Ajie Utama*, Nathaniel Weir*, Ugur Cetintemel, Carsten Binnig
  SIGMOD 2018 - demo paper
  

• Improving Generalization by Incorporating Coverage in Natural Language Inference
  Nafise Sadat Moosavi, Prasetya Ajie Utama, Andreas Rücklé, Iryna Gurevych
  Arxiv Pre-print 2019
  

• Evaluating Attribute-Object Compositionality in Text-Image Multimodal Embeddings
  Prasetya Ajie Utama, James Tompkin
  Brown University - Master’s Final Project 2018
  

• Spark-gram: Mining frequent N-grams using parallel processing in Spark
  Prasetya Ajie Utama, Bayu Distiawan Trisedya
  ICACSIS 2015 - long paper paper
  

Contact:

lastname@ukp.informatik.tu-darmstadt.de