Papers by Samuel Mensah
ExStrucTiny: A Benchmark for Schema-Variable Structured Information Extraction from Document Images (2026.eacl-long)
Copied to clipboard
Mathieu Sibue, Andrés Muñoz Garza, Samuel Mensah, Pranav Shetty, Zhiqiang Ma, Xiaomo Liu, Manuela Veloso
| Challenge: | Existing models for structured information extraction are limited by narrow entity ontologies, simple queries, or homogeneous document types. |
| Approach: | They propose a benchmark dataset for structured Information Extraction (IE) from document images . they analyze open and closed VLMs on this benchmark . |
| Outcome: | The proposed model can perform fine-grained structured extraction across document types and schemas. |
DropMix: A Textual Data Augmentation Combining Dropout with Mixup (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to overcome overfitting in text learning do not consider dimensionality . dimensionalization is important for deep neural networks to overcome the problem . |
| Approach: | They propose a saliency map-based approach to overcome overfitting in text learning . they propose augmentation regularization methods such as Dropout and Mixup to improve regularization . |
| Outcome: | Empirical results show that the proposed approach overcomes overfitting in text learning . dropout and mixup methods are effective in enhancing regularization . |
An Empirical Study on Leveraging Position Embeddings for Target-oriented Opinion Words Extraction (2021.emnlp-main)
Copied to clipboard
| Challenge: | Current methods for extracting opinion words for an aspect in text leverage position embeddings to capture relative position of word to the target. |
| Approach: | They propose to use pretrained word embeddings to extract opinion words for a given aspect in text. |
| Outcome: | The proposed methods outperform current methods on a task based on pre-trained word embeddings and position embedders. |
A Hierarchical N-Gram Framework for Zero-Shot Link Prediction (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to zero-shot link prediction use textual features of relations as auxiliary information to improve the encoded representation. |
| Approach: | They propose a Hierarchical N-gram framework for Zero-Shot Link Prediction that leverages character n-gram information for ZSLP. |
| Outcome: | The proposed method achieves state-of-the-art on two standard ZSLP datasets. |
Contrastive Learning with Expectation-Maximization for Weakly Supervised Phrase Grounding (2022.emnlp-main)
Copied to clipboard
| Challenge: | Weakly supervised phrase grounding aims to learn an alignment between phrases in a caption and objects in an image using only caption-image annotations. |
| Approach: | They propose a novel contrastive learning framework that adaptively refines the target prediction by using only caption-image annotations. |
| Outcome: | The proposed framework outperforms existing methods on two widely used benchmarks, Flickr30K Entities and RefCOCO+. |
FinNLI: Novel Dataset for Multi-Genre Financial Natural Language Inference Benchmarking (2025.findings-naacl)
Copied to clipboard
| Challenge: | FinNLI is a benchmark dataset for Financial Natural Language Inference (NLI) across diverse financial texts like SEC Filings, Annual Reports, and Earnings Call transcripts. |
| Approach: | They propose to use FinNLI to evaluate financial natural language inference models across diverse financial texts like SEC Filings, Annual Reports, and Earnings Call transcripts. |
| Outcome: | The proposed dataset is based on a high-quality test set of 3,304 instances annotated by finance experts. |
Trading Syntax Trees for Wordpieces: Target-oriented Opinion Words Extraction with Wordpieces and Aspect Enhancement (2023.acl-short)
Copied to clipboard
| Challenge: | State-of-the-art target-oriented opinion word extraction methods use pre-trained BERT wordpieces and graph convolutional networks (GCNs) to encode inputs. |
| Approach: | They trade syntax trees for BERT wordpieces to eliminate the GCN component from the methods’ architectures to improve TOWE performance. |
| Outcome: | The proposed approach achieves state-of-the-art results on benchmark datasets and should serve as a strong baseline for further research. |
Explicit Role Interaction Network for Event Argument Extraction (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods extract arguments of each role independently, ignoring the relationship between different roles. |
| Approach: | They propose a neural model that captures the correlations between different argument roles within an event. |
| Outcome: | Extensive experiments on the benchmark dataset ACE2005 show the superiority of the proposed model over existing methods. |
Distill and Align Decomposition for Enhanced Claim Verification (2026.findings-eacl)
Copied to clipboard
Jabez Magomere, Elena Kochkina, Samuel Mensah, Simerjot Kaur, Fernando Acero, Arturo Oncevay, Charese Smiley, Xiaomo Liu, Manuela Veloso
| Challenge: | Existing methods for complex claim verification struggle to align decomposition quality with verification performance. |
| Approach: | They propose a reinforcement learning approach that optimizes decomposition quality and verifier alignment using Group Relative Policy Optimization. |
| Outcome: | The proposed method outperforms prompt-based approaches and existing methods in six evaluation settings. |
A Transformational Biencoder with In-Domain Negative Sampling for Zero-Shot Entity Linking (2022.findings-acl)
Copied to clipboard
| Challenge: | Recent work on entity linking has focused on the zero-shot scenario where at test time the entity mention to be labelled is never seen during training. |
| Approach: | They propose a transformational biencoder that integrates a transform into BERT to perform a zero-shot transfer from the source domain to the target domain. |
| Outcome: | The proposed model performs a zero-shot transfer from the source domain to the target domain on a benchmark dataset and achieves new state-of-the-art. |
Aspect-Level Sentiment Analysis Via Convolution over Dependency Tree (D19-1)
Copied to clipboard
| Challenge: | Existing methods to identify sentiment polarity of opinion words are cumbersome due to the amount of opinionated material on the internet. |
| Approach: | They propose a method to identify sentiment polarity of opinion words on a specific aspect of a sentence using neural networks. |
| Outcome: | The proposed method is the state-of-the-art in aspect-based sentiment classification. |
A Variational Approach for Mitigating Entity Bias in Relation Extraction (2025.acl-short)
Copied to clipboard
| Challenge: | Relation Extraction (RE) models often rely excessively on entities, resulting in poor generalization. |
| Approach: | They propose a Variational Information Bottleneck (VIB) framework to reduce entity bias in Relation Extraction (RE) . their method extracts relational information from unstructured data to improve generalization . |
| Outcome: | The proposed method achieves state-of-the-art on general and financial domain RE datasets, excelling in in-domain settings and out-of domain. |
Advanced Messaging Platform (AMP): Pipeline for Automated Enterprise Email Processing (2025.acl-industry)
Copied to clipboard
Simerjot Kaur, Charese Smiley, Keshav Ramani, Elena Kochkina, Mathieu Sibue, Samuel Mensah, Pietro Totis, Cecilia Tilli, Toyin Aguda, Daniel Borrajo, Manuela Veloso
| Challenge: | a lack of publicly available datasets for training and benchmarking limits current AI techniques' effectiveness in industry-specific applications. |
| Approach: | They propose an email automation pipeline that automates email response generation at scale in real-world enterprise settings. |
| Outcome: | The proposed pipeline automates email response generation at scale in real-world environments. |
Recurrent Interaction Network for Jointly Extracting Entities and Classifying Relations (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to solve the extraction problem learn interactions between the two tasks through a shared network . |
| Approach: | They propose to use multi-task learning to address the joint extraction of entity and relation . they exploit correlation between ER and relation classification tasks to improve performance . |
| Outcome: | Empirical results show that the proposed model improves on two real-world datasets. |