Papers by Denilson Barbosa

8 papers
Cree Corpus: A Collection of nêhiyawêwin Resources (2022.acl-long)

Copied to clipboard

Challenge: Plains Cree is a low resource language with no corpus available for development . a lack of publicly available corpora hinders the development of such technologies .
Approach: They develop a corpus of Plains Cree (nêhiyawêwin) covering genres, time periods, and texts for a variety of intended audiences.
Outcome: The corpus covers genres, time periods, and texts for a variety of intended audiences.
Accurate and Nuanced Open-QA Evaluation Through Textual Entailment (2024.findings-acl)

Copied to clipboard

Challenge: Open-domain question answering (Open-QA) evaluations are criticized for the ambiguity in questions and the lack of semantic understanding in evaluators.
Approach: They propose to examine the entailment relations of answers to identify more informative and more general system answers.
Outcome: The proposed evaluations offer a much closer evaluation to human judgment on NaturalQuestions and TriviaQA while being learning-free.
WordTies: Measuring Word Associations in Language Models via Constrained Sampling (2022.findings-emnlp)

Copied to clipboard

Challenge: Word associations are widely used in psychology to provide insights on how humans perceive and understand concepts.
Approach: They propose an algorithm that allows an asymmetric measurement of associated words, given a cue word as input.
Outcome: The proposed algorithm shares more overlap with human associations and observes the asymmetric property of human associations.
Connecting Language and Knowledge with Heterogeneous Representations for Neural Relation Extraction (N19-1)

Copied to clipboard

Challenge: Knowledge Bases (KBs) require constant updating to reflect changes to the world they represent.
Approach: They propose a framework that unifies learning of RE and KBE models . the framework is based on a relation extraction task that uses a KB relation to a phrase .
Outcome: The proposed framework unifies learning of RE and KBE models, leading to significant improvements over the state-of-the-art RE framework.
NLP Workbench: Efficient and Extensible Integration of State-of-the-art Text Mining Tools (2023.eacl-demo)

Copied to clipboard

Challenge: NLP Workbench is a web-based text mining platform that allows non-expert users to obtain semantic understanding of large-scale corpora using state-of-the-art text mining models.
Approach: They propose to use a microservice architecture to replace existing models or integrate a new one.
Outcome: The proposed model is extensible and can be easily replaced or integrated with existing models.
KnowledgeNet: A Benchmark Dataset for Knowledge Base Population (D19-1)

Copied to clipboard

Challenge: KnowledgeNet provides text exhaustively annotated with facts . high-quality KBs still rely almost exclusively on human-curated structured or semi-structured data.
Approach: They propose five baseline approaches to populating a knowledge base with facts . the best approach achieves an F1 score of 0.50, significantly outperforming a traditional approach by 79% .
Outcome: The best approach achieves an F1 score of 0.50, outperforming a traditional approach by 79%, indicating the dataset is challenging.
Neural Fine-Grained Entity Type Classification with Hierarchy-Aware Loss (N18-1)

Copied to clipboard

Challenge: Existing methods for fine-grained type classification rely on distant supervision and are susceptible to noisy labels that can be out-of-context or overly-specific.
Approach: They propose a neural network model that uses cross-entropy loss function to handle out-of-context labels and hierarchical loss normalization to cope with overly-specific ones.
Outcome: The proposed model outperforms the state-of-the-art on established benchmarks for the task.
Improving Bengali and Hindi Large Language Models (2024.lrec-main)

Copied to clipboard

Challenge: Bengali and Hindi are low-resource languages, and the state-of-the-art tokenization methods fail to separate roots from affixes.
Approach: They used BERT and Wordpiece tokenizers to train a wordpiece tokenization system for Bengali and Hindi to model fine-grained character-level information.
Outcome: The proposed tokenizers outperform the state-of-the-art and Wordpiece tokenizer for modeling Bengali and Hindi.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations