Selected Publications

Grammar as Control: Modular Language Generation for the Long Tail
Ndapa Nakashole
ACL 2026
πŸš€ This work is a major component of the project that led to the first usable English–Kwanyama MT system.
Sentiment Analysis and Language Models for Oshikwanyama
Ndapa Nakashole
LREC 2026
1B, 3B, and 8B parameter LLMs for Oshikwanyama
Typology-Guided Adaptation in Multilingual Models πŸ† Outstanding Paper
Ndapa Nakashole
ACL 2025
On Linearizing Structured Data in Encoder-Decoder Language Models: Insights from Text-to-SQL
Yutong Shao, Ndapa Nakashole
NAACL 2024
SYMPTOMIFY: Large-scale Symptom Recognition in post-Vaccine Reports
Bosung Kim, Ndapa Nakashole
EMNLP 2023 (Findings)
Database-aware ASR Error Correction For Speech-to-SQL Parsing
Yutong Shao, Arun Kumar, Ndapa Nakashole
ICASSP 2023
Data Augmentation for Rare Symptoms in Vaccine Side-Effect Detection
Bosung Kim, Ndapa Nakashole
BioNLP 2022
A Gradually Soft Multi-Task and Data-Augmented Approach to Medical Question Understanding
Khalil Mrini, Franck Dernoncourt, Seunghyun Yoon, Trung Bui, Walter Chang, Emilia Farcas, Ndapa Nakashole
ACL 2021
A Grounded Well-being Conversational Agent with Multiple Interaction Modes
Xinxin Yan, Ndapa Nakashole
NLP4PI @ ACL 2021
NORMA: Neighborhood Sensitive Maps for Multilingual Word Embeddings
Ndapa Nakashole
EMNLP 2018
PATTY: A Taxonomy of Relational Patterns with Semantic Types πŸ† Best Paper Runner-Up
Ndapa Nakashole, Gerhard Weikum, Fabian Suchanek
EMNLP 2012