Sowmya Vajjala — accepted AI-conference papers

2025

UniversalCEFR: Enabling Open Multilingual Research on Language Proficiency Assessment

Joseph Marvin Imperial, Abdullah Barayan, Regina Stodden, Rodrigo Wilkens, Ricardo Mu{\~n}oz S{\'a}nchez, Lingyun Gao +13

EMNLP 2025

We introduce UniversalCEFR, a large-scale multilingual multidimensional dataset of texts annotated according to the CEFR (Common European Framework of Reference) scale in 13 languages. To enable open research in both automated readability and language proficiency assessment, UniversalCEFR comprises

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

Improving Absent Keyphrase Generation with Diversity Heads

Edwin Thomas, Sowmya Vajjala

NAACL 2024findings

Keyphrase Generation (KPG) is the task of automatically generating appropriate keyphrases for a given text, with a wide range of real-world applications such as document indexing and tagging, information retrieval, and text summarization. NLP research makes a distinction between present and absent k…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Keyphrase Generation: Lessons from a Reproducibility Study

Edwin Thomas, Sowmya Vajjala

COLING 2024main

Reproducibility studies are treated as means to verify the validity of a scientific method, but what else can we learn from such experiments? We addressed this question taking Keyphrase Generation (KPG) as the use case in this paper, by studying three state-of-the-art KPG models in terms of reproduc…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

Methods, Applications, and Directions of Learning-to-Rank in NLP Research

Justin Lee, Gabriel Bernier-Colborne, Tegan Maharaj, Sowmya Vajjala

NAACL 2024findings

Learning-to-rank (LTR) algorithms aim to order a set of items according to some criteria. They are at the core of applications such as web search and social media recommendations, and are an area of rapidly increasing interest, with the rise of large language models (LLMs) and the widespread impact…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2022

A Neural Pairwise Ranking Model for Readability Assessment

Justin Lee, Sowmya Vajjala

ACL 2022findings

Automatic Readability Assessment (ARA), the task of assigning a reading level to a text, is traditionally treated as a classification problem in NLP research. In this paper, we propose the first neural, pairwise ranking approach to ARA and compare it with existing classification, regression, and (no…

Cited by 39 Source ↗PDF ↗code ↗Scholar ↗