Papers by Sowmya Vajjala
A Neural Pairwise Ranking Model for Readability Assessment (2022.findings-acl)
Copied to clipboard
| Challenge: | Automatic Readability Assessment (ARA) is traditionally treated as a classification problem in NLP research. |
| Approach: | They propose a neural ranking approach to automatic readability assessment (ARA) they propose 'neural' ranking methods that can be used to rank texts by reading level . |
| Outcome: | The proposed approach performs well in monolingual single/cross corpus testing scenarios and achieves a zero-shot cross-lingual ranking accuracy of over 80% for both French and Spanish when trained on English data. |
CommonLID: Re-evaluating State-of-the-Art Language Identification Performance on Web Data (2026.acl-long)
Copied to clipboard
Pedro Ortiz Suarez, Laurie Burchell, Catherine Arnett, Rafael Mosquera, Sara Hincapié Monsalve, Thom Vaughan, Damian Stewart, Malte Ostendorff, Idris Abdulmumin, Vukosi Marivate, Shamsuddeen Hassan Muhammad, Atnafu Lambebo Tonja, Hend Al-Khalifa, Nadia Ghezaiel Hammouda, Verrah Akinyi Otiende, Tack Hwa Wong, Jakhongir Saydaliev, Melika Nobakhtian, Muhammad Ravi Shulthan Habibi, Chalamalasetti Kranti, Carol Muchemi, Khang Nguyen, Faisal Muhammad Adam, Luis Frentzen Salim, Reem Alqifari, Cynthia Jayne Amol, Joseph Marvin Imperial, Ilker Kesen, Ahmad Mustafid, Pavel Stepachev, Leshem Choshen, David Anugraha, Hamada Nayel, Seid Muhie Yimam, Vallerie Alexandra Putra, My Chiffon Nguyen, Azmine Toushik Wasi, Gouthami Vadithya, Rob Van Der Goot, Lanwenn ar C’horr, Karan Dua, Andrew Yates, Mithil Bangera, Yeshil Bangera, Hitesh Laxmichand Patel, Shu Okabe, Fenal Ashokbhai Ilasariya, Dmitry Gaynullin, Genta Indra Winata, Yiyuan Li, Juan Pablo Martínez, Amit Agarwal, Ikhlasul Akmal Hanif, Raia Abu Ahmad, Esther Adenuga, Filbert Aurelian Tjiaranata, Weerayut Buaphet, Michael Anugraha, Sowmya Vajjala, Benjamin L Rice, Azril Hafizi Amirudin, Jesujoba Oluwadara Alabi, Srikant Panda, Yassine Toughrai, Bruhan Kyomuhendo, Daniel Ruffinelli, null Akshata, Manuel Goulão, Ej Zhou, Ingrid Gabriela Franco Ramirez, Cristina Aggazzotti, Konstantin Dobler, Jun Kevin, Quentin Pagès, Nicholas Andrews, Nuhu Ibrahim, Mattes Ruckdeschel, Amr Keleg, Mike Zhang, Casper Rufaro Muziri, Saron Samuel, Sotaro Takeshita, Kun Kerdthaisong, Luca Foppiano, Rasul Dent, Tommaso Green, Ahmad Mustapha Wali, Kamohelo Makaaka, Vicky Feliren, Inshirah Idris, Hande Celikkanat, Abdulhamid Abubakar, Jean Maillard, Benoît Sagot, Thibault Clérice, Kenton Murray, Sarah K. K. Luger
| Challenge: | Language identification (LID) is a fundamental step in curating multilingual corpora. |
| Approach: | They introduce CommonLID, a community-driven, human-annotated LID benchmark for the web domain, covering 109 languages. |
| Outcome: | The proposed benchmark covers 109 languages and shows that existing evaluations overestimate accuracy for many languages in the web domain. |
Trends, Limitations and Open Challenges in Automatic Readability Assessment Research (2022.lrec-1)
Copied to clipboard
| Challenge: | Readability assessment is the task of evaluating the reading difficulty of a given piece of text. |
| Approach: | They examine the common approaches used for automatic readability assessment and identify their shortcomings and some challenges for the future. |
| Outcome: | The proposed models are compared with existing models and are based on existing ones. |
What do we really know about State of the Art NER? (2022.lrec-1)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) is a well researched task and widely used in real world NLP scenarios. |
| Approach: | They perform a broad evaluation of Named Entity Recognition using a popular dataset that takes into consideration various text genres and sources constituting the dataset at hand. |
| Outcome: | The proposed models perform on a popular dataset and generate six new adversarial test sets through small perturbations in the original test set, replacing select entities while retaining the context. |
Keyphrase Generation: Lessons from a Reproducibility Study (2024.lrec-main)
Copied to clipboard
| Challenge: | Reproducibility studies are used to verify the validity of a scientific method, but what else can we learn from such experiments? |
| Approach: | They use Keyphrase Generation to examine reproducibility under different conditions . they draw conclusions on state of the art in KPG and provide guidelines for researchers . |
| Outcome: | The proposed models are compared under the same or varied conditions and provide guidelines for reporting results in a more comprehensive manner. |
Improving Absent Keyphrase Generation with Diversity Heads (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing approaches to generating keyphrases for a given text are limited to extracting only the keyphrase that is directly seen in the document. |
| Approach: | They propose to treat present keyphrase extraction as a sequence labeling problem and treat absent keyphrases together in a text-to-text generation framework during training. |
| Outcome: | The proposed model improves on the state-of-the-art for present keyphrase extraction and five datasets for absent keyphrase generation among the six English datasets. |
Methods, Applications, and Directions of Learning-to-Rank in NLP Research (2024.findings-naacl)
Copied to clipboard
| Challenge: | Learning-to-rank (LTR) algorithms aim to order items according to some criteria. |
| Approach: | They focus on the formal background of LTR and the most widely-used supervised methods . they also discuss how large language models are changing the LTR landscape . |
| Outcome: | The proposed methods are used in natural language processing and information retrieval tasks. |
UniversalCEFR: Enabling Open Multilingual Research on Language Proficiency Assessment (2025.emnlp-main)
Copied to clipboard
Joseph Marvin Imperial, Abdullah Barayan, Regina Stodden, Rodrigo Wilkens, Ricardo Muñoz Sánchez, Lingyun Gao, Melissa Torgbi, Dawn Knight, Gail Forey, Reka R. Jablonkai, Ekaterina Kochmar, Robert Joshua Reynolds, Eugénio Ribeiro, Horacio Saggion, Elena Volodina, Sowmya Vajjala, Thomas François, Fernando Alva-Manchego, Harish Tayyar Madabushi
| Challenge: | Language proficiency research plays a central role in education and often intersects with advances in linguistics and AI. |
| Approach: | They propose a multilingual multidimensional dataset of texts annotated according to the CEFR scale in 13 languages. |
| Outcome: | The proposed dataset supports linguistic features and pretrained models in multilingual CEFR level assessment. |