Papers by Thamar Solorio

Let Me Choose: From Verbal Context to Font Selection (2020.acl-main)

Challenge:	Existing rating systems only provide simple age restrictions and do not include suitability level on a specific aspect of the content.
Approach:	They propose to categorize ordinal severity of movies on 5 aspects using dialogue script data . they propose to use a siamese network-based multitask framework to improve interpretability .
Outcome:	The proposed method outperforms the state-of-the-art model and provides useful information to interpret predictions.

Copied to clipboard

Amirreza Shirani, Franck Dernoncourt, Jose Echevarria, Paul Asente, Nedim Lipka, Thamar Solorio

Question-Instructed Visual Descriptions for Zero-Shot Video Answering (2024.findings-acl)

Challenge:	Current font selection interfaces do not consider verbal context of the input text.
Approach:	They propose a dataset containing examples of different topics in social media posts and ads, labeled through crowd-sourcing.
Outcome:	The proposed model captures inter-subjectivity across annotations on a dataset of social media posts and ads labeled through crowd-sourcing.

Copied to clipboard

David Mogrovejo, Thamar Solorio

Beyond Understanding: Evaluating the Pragmatic Gap in LLMs’ Cultural Processing of Figurative Language (2026.eacl-long)

Challenge:	Existing models for video QA rely on complex architectures, expensive pipelines or closed models like GPTs.
Approach:	They propose a single instruction-aware open vision-language model to tackle videoQA using frame descriptions.
Outcome:	The proposed framework achieves higher performance than current state-of-the-art models on videoQA benchmarks.

Copied to clipboard

Mena Attia, Aashiq Muhamed, Mai Alkhamissi, Thamar Solorio, Mona T. Diab

Sentiment Analysis

Challenge:	Using figurative language as a proxy for cultural nuance and local knowledge, large language models struggle with connotative meaning.
Approach:	They evaluate large language models' ability to process culturally grounded language . they use figurative language as a proxy for cultural nuance and local knowledge .
Outcome:	The proposed models can understand and use figurative expressions that encode local knowledge and social nuance.

Modeling Noisiness to Recognize Named Entities using Multitask Neural Networks on Social Media (N18-1)

Copied to clipboard

Gustavo Aguilar, Adrian Pastor López-Monroy, Fabio González, Thamar Solorio

Information Retrieval

Challenge:	Current approaches to Named Entity Recognition (NER) are effective in formal text, but they fail on informal text, where improper grammatical structures, spelling inconsistencies, and slang vocabulary prevail.
Approach:	They propose a multitask end-to-end bidirectional long short-term memory (BLSTM)-Conditional Random Field (CRF) network with two CRF classifiers and a feature extractor that transfers learning to a CRF for prediction.
Outcome:	The proposed models outperform the current state-of-the-art on the Workshop on Noisy User-generated Text 2017 dataset by 2.45% and 3.69%, establishing a more suitable approach for social media environments.

Distillation of encoder-decoder transformers for sequence labelling (2023.findings-eacl)

Copied to clipboard

Marco Farina, Duccio Pappadopulo, Anant Gupta, Leslie Huang, Ozan Irsoy, Thamar Solorio

Language Models

Challenge:	despite the strong trend in NLP to explore the use of large language models, there is still limited work evaluating prompting and decoding mechanisms for SL tasks.
Approach:	They propose a hallucination-free framework for sequence tagging that is especially suited for distillation.
Outcome:	The proposed framework performs well across multiple sequence labelling datasets and in a few-shot learning scenario.

Folksonomication: Predicting Tags for Movies from Plot Synopses using Emotion Flow Encoded Neural Network (C18-1)

Copied to clipboard

Sudipta Kar, Suraj Maharjan, Thamar Solorio

Challenge:	Existing systems that generate tags for movies can help users better retrieve movies based on their personal preferences and user profiles.
Approach:	They propose a neural network model that merges synopses and emotion flows to predict a set of movies' tags.
Outcome:	The proposed model outperforms a machine learning system by learning 18% more tags than the previous one.

From English to Code-Switching: Transfer Learning with Strong Morphological Clues (2020.acl-main)

Copied to clipboard

Gustavo Aguilar, Thamar Solorio

Syntactic Text Processing

Challenge:	Linguistic code-switching (CS) is an understudied area in natural language processing . lack of resources and annotated data makes it difficult to strive for progress in CS-related tasks.
Approach:	They propose a method to adapt monolingual models to code-switched text in various tasks . they transfer English knowledge from a pre-trained ELMo model to different code-paired languages .
Outcome:	The proposed method outperforms multilingual BERT and homologous CS-unaware models and provides state-of-the-art in CS tasks.

SemRel2024: A Collection of Semantic Textual Relatedness Datasets for 13 Languages (2024.findings-acl)

Copied to clipboard

Nedjma Ousidhoum, Shamsuddeen Muhammad, Mohamed Abdalla, Idris Abdulmumin, Ibrahim Ahmad, Sanchit Ahuja, Alham Aji, Vladimir Araujo, Abinew Ayele, Pavan Baswani, Meriem Beloucif, Chris Biemann, Sofia Bourhim, Christine Kock, Genet Dekebo, Oumaima Hourrane, Gopichand Kanumolu, Lokesh Madasu, Samuel Rutunda, Manish Shrivastava, Thamar Solorio, Nirmal Surange, Hailegnaw Tilaye, Krishnapriya Vishnubhotla, Genta Winata, Seid Yimam, Saif Mohammad

Semantic Similarity

Challenge:	SemRel datasets are annotated by native speakers across 13 languages . they are used to characterise the relationship between two units of text .
Approach:	They propose to use a semantic relatedness dataset to measure the degree of semantic textual relatedness between sentences in Afrikaans, Algerian Arabic, Amharic, English, Hausa, Hindi, Indonesian, Kinyarwanda, Marathi, Moroccan Arabic, Modern Standard Arabic, Spanish, and Telugu.
Outcome:	The proposed datasets are annotated by native speakers across 13 languages and represent the semantic relatedness of 13 languages.

A Scalable Framework for Automated NER Annotation Correction in Low-Resource Languages (2026.findings-eacl)

Copied to clipboard

Toqeer Ehsan, Thamar Solorio

Information Extraction & Text Mining

Challenge:	Existing NER benchmarks lack quality annotations, resulting in poor performance.
Approach:	They propose a frequency-based iterative approach that leverages self-training and a dual-threshold mechanism to enhance inference confidence.
Outcome:	The proposed approach improves NER performance on three datasets with a high number of missing annotations.

MoMentS: A Comprehensive Multimodal Benchmark for Theory of Mind (2025.findings-emnlp)

Copied to clipboard

Emilio Villa-Cueva, S M Masrur Ahmed, Rendi Chevi, Jan Christian Blaise Cruz, Kareem Elzeky, Fermin Cristobal, Alham Fikri Aji, Skyler Wang, Rada Mihalcea, Thamar Solorio

Learning Emphasis Selection for Written Text in Visual Media from Crowd-Sourced Label Distributions (P19-1)

Challenge:	MoMentS is a benchmark designed to assess the ToM capabilities of multimodal large language models (LLMs) in short films.
Approach:	They introduce a benchmark to assess the ToM capabilities of multimodal large language models (LLMs) through realistic, narrative-rich scenarios presented in short films.
Outcome:	The proposed benchmark features long video context windows and realistic social interactions that provide deeper insight into characters’ mental states.

Copied to clipboard

Amirreza Shirani, Franck Dernoncourt, Paul Asente, Nedim Lipka, Seokhwan Kim, Jose Echevarria, Thamar Solorio

The Zeno’s Paradox of ‘Low-Resource’ Languages (2024.emnlp-main)

Challenge:	Visual communication relies heavily on images and short texts to grab a viewer's attention and convey a message in the most efficient way.
Approach:	They propose a model that employs end-to-end label distribution learning on crowd-sourced data and predicts a selection distribution, capturing the inter-subjectivity and ambiguity of the input.
Outcome:	The proposed model captures the inter-subjectivity and ambiguity of the input and can be transformed to single-label learning by mapping labels to absolute labels via majority voting.

Copied to clipboard

Hellina Hailu Nigatu, Atnafu Tonja, Benjamin Rosman, Thamar Solorio, Monojit Choudhury

Afri-MCQA: Multimodal Cultural Question Answering for African Languages (2026.acl-long)

Challenge:	'low resource' languages are understudied by the NLP community, while 'high resource' is referred to as 'achieved', while high-resource languages are referred .
Approach:	They qualitatively analyzed 150 papers from the ACL Anthology and popular speech-processing conferences that mention the keyword ‘low-resource.
Outcome:	The proposed analysis reveals that several interacting axes contribute to ‘low-resourceness’ of a language and why that makes it difficult to track progress for each individual language.

Copied to clipboard

Atnafu Lambebo Tonja, Srija Anand, Emilio Villa-Cueva, Israel Abebe Azime, Jesujoba Oluwadara Alabi, Muhidin A. Mohamed, Debela Desalegn Yadeta, Negasi Haile Abadi, Abigail Oppong, Nnaemeka Casmir Obiefuna, Idris Abdulmumin, Naome A Etori, Eric Peter Wairagala, Kanda Patrick Tshinu, Imanigirimbabazi Emmanuel, Gabofetswe Malema, Alham Fikri Aji, David Ifeoluwa Adelani, Thamar Solorio

LinCE: A Centralized Benchmark for Linguistic Code-switching Evaluation (2020.lrec-1)

Challenge:	Afri-MCQA is the first multilingual cultural question-answering benchmark containing 7.5k Q A pairs across 15 African languages from 12 countries.
Approach:	They introduce Afri-MCQA, the first multilingual cultural question-answering benchmark containing 7.5k Q A pairs across 15 African languages from 12 countries.
Outcome:	The proposed model shows poor performance across cultures, with near zero accuracy on open-ended VQA when queried through native language or speech.

Copied to clipboard

Gustavo Aguilar, Sudipta Kar, Thamar Solorio

Code-Switching

Challenge:	Recent trends in NLP research have raised an interest in linguistic code-switching . however, many of these approaches are limited to a few language pairs and a specific domain .
Approach:	They propose a centralized benchmark for Linguistic Code-switching Evaluation that combines eleven corpora covering four different code-switch languages and four tasks.
Outcome:	The proposed benchmark provides a centralized benchmark and compares with other benchmarks in real-time.

A Survey of Code-switched Arabic NLP: Progress, Challenges, and Future Directions (2025.coling-main)

Copied to clipboard

Injy Hamed, Caroline Sabty, Slim Abdennadher, Ngoc Thang Vu, Thamar Solorio, Nizar Habash

Positive and Risky Message Assessment for Music Products (2024.lrec-main)

Challenge:	Code-switching (CSW) is a common linguistic phenomenon in multilingual societies . current literature on CSW in the arab world is limited to the Arabic language .
Approach:	They present a review of the literature in the field of code-switched Arabic NLP . they propose recommendations for future research .
Outcome:	This review provides a broad perspective on the current literature in the field of code-switched Arabic NLP . it also provides recommendations for future research .

Copied to clipboard

Yigeng Zhang, Mahsa Shafaei, Fabio Gonzalez, Thamar Solorio

Early Text Classification Using Multi-Resolution Concept Representations (N18-1)

Challenge:	a new approach to content assessment is needed to assess positive and potentially harmful messages in music.
Approach:	They propose a multi-task predictive model fortified with ordinality-enforcement to assess positive and potentially harmful messages within music products.
Outcome:	The proposed method outperforms task-specific alternatives and can assess multiple aspects simultaneously.

Copied to clipboard

Adrian Pastor López-Monroy, Fabio A. González, Manuel Montes, Hugo Jair Escalante, Thamar Solorio

Representation Learning

Challenge:	e-communications have been misused by cyber-criminals, who hide in the depths of the web.
Approach:	They propose a document representation which allows us to generate multiple "views" of the analyzed text.
Outcome:	The proposed representation outperforms existing models in two tasks where anticipation is critical: sexual predator detection and depression detection.

OATS: A Challenge Dataset for Opinion Aspect Target Sentiment Joint Detection for Aspect-Based Sentiment Analysis (2024.lrec-main)

Copied to clipboard

Siva Uday Sampreeth Chebolu, Franck Dernoncourt, Nedim Lipka, Thamar Solorio

Sentiment Analysis

Challenge:	Aspect-based sentiment analysis (ABSA) focuses on understanding sentiments specific to distinct elements within a user-generated review.
Approach:	They propose to use Aspect-based sentiment analysis to understand specific aspects of a user-generated review to identify the target entity being reviewed, the aspect to which it belongs, the opinion phrase, and the sentiment expressed toward the aspects.
Outcome:	The proposed dataset bridges the gaps observed in existing datasets and sheds light on various ABSA subtasks.

CaMMT: Benchmarking Culturally Aware Multimodal Machine Translation (2025.findings-emnlp)

Copied to clipboard

Emilio Villa-Cueva, Sholpan Bolatzhanova, Diana Turmakhan, Kareem Elzeky, Henok Biadglign Ademtew, Alham Fikri Aji, Vladimir Araujo, Israel Abebe Azime, Jinheon Baek, Frederico Belcavello, Fermin Cristobal, Jan Christian Blaise Cruz, Mary Dabre, Raj Dabre, Toqeer Ehsan, Naome A Etori, Fauzan Farooqui, Jiahui Geng, Guido Ivetta, Thanmay Jayakumar, Soyeong Jeong, Zheng Wei Lim, Aishik Mandal, Sofía Martinelli, Mihail Minkov Mihaylov, Daniil Orel, Aniket Pramanick, Sukannya Purkayastha, Israfel Salazar, Haiyue Song, Tiago Timponi Torrent, Debela Desalegn Yadeta, Injy Hamed, Atnafu Lambebo Tonja, Thamar Solorio

Labeling Comic Mischief Content in Online Videos with a Multimodal Hierarchical-Cross-Attention Model (2024.lrec-main)

Challenge:	a human-curated benchmark of over 5,800 triples of images is used to evaluate multimodal translation systems.
Approach:	They introduce a human-curated benchmark of over 5,800 triples of images along with parallel captions in English and regional languages.
Outcome:	The results show that visual context improves translation quality in culturally-specific items .

Copied to clipboard

Elaheh Baharlouei, Mahsa Shafaei, Yigeng Zhang, Hugo Jair Escalante, Thamar Solorio

A Genre-Aware Attention Model to Improve the Likability Prediction of Books (D18-1)

Challenge:	Existing systems for detecting questionable content in online media are limited by age, life experiences, socio-cultural values, and cognitive skills.
Approach:	They propose a multimodal system for comic mischief detection using video, text, and audio.
Outcome:	The proposed system improves existing models and baselines for comic mischief detection and its type classification.

Copied to clipboard

Suraj Maharjan, Manuel Montes, Fabio A. González, Thamar Solorio

Cross-lingual Few-Shot Learning on Unseen Languages (2022.aacl-main)

Challenge:	Existing methods for likability prediction are time-consuming and too rigid.
Approach:	They propose a novel neural architecture that incorporates genre supervision to assign weights to individual feature types based on the characteristics of each book.
Outcome:	The proposed method outperforms state-of-the-art methods and achieves competitive results.

Copied to clipboard

Genta Winata, Shijie Wu, Mayank Kulkarni, Thamar Solorio, Daniel Preotiuc-Pietro

Low-Resource NLP

Challenge:	Large pre-trained language models have demonstrated the ability to obtain good performance on downstream tasks with limited examples in resource-rich languages.
Approach:	They propose to use a downstream sentiment analysis task to analyze the effectiveness of several few-shot learning strategies across 12 languages, including 8 unseen languages, to compare results.
Outcome:	The proposed model, XLM-R, gives the best performance on a task with few examples in resource-rich languages.

Towards Fast and Accurate Modeling for Cross-Lingual Label Projection (2026.acl-long)

Copied to clipboard

Thang Le, Huy Huu Nguyen, Anh Tuan Luu, Thamar Solorio, Thien Huu Nguyen

Data Augmentation for Cross-Domain Named Entity Recognition (2021.emnlp-main)

Challenge:	Existing methods for label projection are inaccurate or slow for large-scale use.
Approach:	They propose to synthesize alignment sequence pairs and fine-tune an encoder model with span alignment objective while controlling data influence during training.
Outcome:	The proposed method outperforms state-of-the-art methods while maintaining fast inference speed across 50+ languages.

Copied to clipboard

Shuguang Chen, Gustavo Aguilar, Leonardo Neves, Thamar Solorio

Adaptive Cross-lingual Text Classification through In-Context One-Shot Demonstrations (2024.naacl-long)

Challenge:	Existing methods for named entity recognition focus on augmenting in-domain data in low-resource scenarios where annotated data is limited.
Approach:	They propose a neural architecture to transform data from high-resource to low-resourced domains by learning the patterns in the text that differentiate them.
Outcome:	The proposed approach improves on high-resource domain representations over high- and low-resourced domains.

Copied to clipboard

Emilio Cueva, Adrian Lopez Monroy, Fernando Sánchez-Vega, Thamar Solorio

Cross-Lingual Transfer

Challenge:	Zero-Shot Cross-lingual transfer (ZS-XLT) uses a model trained in a source language to make predictions in another language, often with a performance loss.
Approach:	They propose a new approach that uses In-Context Tuning to train a model to learn from context examples and adapt it to a target language by prepending a One-Shot context demonstration.
Outcome:	The proposed approach outperforms prompt-based models in Zero-Shot and Few-shot scenarios with target-language examples.

Letting Emotions Flow: Success Prediction by Modeling the Flow of Emotions in Books (N18-2)

Copied to clipboard

Suraj Maharjan, Sudipta Kar, Manuel Montes, Fabio A. González, Thamar Solorio

Sentiment Analysis

Challenge:	We obtained the best weighted F1-score of 69% for predicting books’ success in a multitask setting.
Approach:	They propose to model the flow of emotions over a book using recurrent neural networks and quantify its usefulness in predicting success in books.
Outcome:	The proposed model obtained the best weighted F1-score of 69% for predicting books’ success in a multitask setting.

NLP Progress in Indigenous Latin American Languages (2024.naacl-long)

Copied to clipboard

Atnafu Tonja, Fazlourrahman Balouchzahi, Sabur Butt, Olga Kolesnikova, Hector Ceballos, Alexander Gelbukh, Thamar Solorio

Multi-view Story Characterization from Movie Plot Synopses and Reviews (2020.emnlp-main)

Challenge:	a new study examines the marginalization of indigenous languages in the face of rapid technological advancements.
Approach:	They highlight the cultural richness of indigenous languages and the risk they face of being overlooked in the realm of natural language processing.
Outcome:	The authors highlight the cultural richness of indigenous languages and their risk of being overlooked in the realm of natural language processing.

Copied to clipboard

Sudipta Kar, Gustavo Aguilar, Mirella Lapata, Thamar Solorio

Challenge:	Existing methods for characterizing stories by generating tags from synopses suffer from coverage issues.
Approach:	They propose to use synopses and reviews to characterize stories by inferring attributes such as theme and style from written synopsis and reviews.
Outcome:	The proposed model improves over methods that only use synopses and reviews . it can extract a complementary set of story attributes from reviews without supervision .

ProverbEval: Exploring LLM Evaluation Challenges for Low-resource Language Understanding (2025.findings-naacl)

Copied to clipboard

Israel Abebe Azime, Atnafu Lambebo Tonja, Tadesse Destaw Belay, Yonas Chanie, Bontu Fufa Balcha, Negasi Haile Abadi, Henok Biadglign Ademtew, Mulubrhan Abebe Nerea, Debela Desalegn Yadeta, Derartu Dagne Geremew, Assefa Atsbiha Tesfu, Philipp Slusallek, Thamar Solorio, Dietrich Klakow

Interpreting Themes from Educational Stories (2024.lrec-main)

Challenge:	Large language models (LLMs) evaluation is gaining increasing attention as they are typically trained on general-domain datasets while demonstrating notable performance on tasks out of their training domains.
Approach:	They propose an LLM evaluation benchmark for low-resource languages that focuses on low-rsource language understanding in culture-specific scenarios.
Outcome:	The proposed benchmarks outperform monolingual evaluations on proverb generation tasks and native language proverb descriptions on multiple choice tasks.

Copied to clipboard

Yigeng Zhang, Fabio Gonzalez, Thamar Solorio

Explainability & Interpretability in NLP

Challenge:	Recent advances in machine reading comprehension (MRC) have centered on literal comprehension, referring to the surface-level understanding of content.
Approach:	They propose a dataset specifically designed for interpretive comprehension of educational narratives, providing corresponding well-edited theme texts.
Outcome:	The proposed dataset spans genres and cultural origins and includes human-annotated theme keywords with varying levels of granularity.

The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challenges (2023.findings-acl)

Copied to clipboard

Genta Winata, Alham Fikri Aji, Zheng Xin Yong, Thamar Solorio