David S. Batista

Annotated-Semantic-Relationships-Datasets. A collections of public and free annotated datasets of relationships between entities/nominals (Portuguese and English)

NER-datasets. Datasets to train supervised classifiers for Named-Entity Recognition in different languages (Portuguese, German, Dutch, French, English)

NER-Evaluation. An implementation of a full named-entity evaluation metrics based on SemEval'13 Task 9 - not at tag/token level but considering all the tokens that are part of the named-entity

Snowball. Implementation with some extensions of the paper "Snowball: Extracting Relations from Large Plain-Text Collections" (Agichtein and Gravano, 2000)

BREDS. "Bootstrapping Relationship Extractors with Distributional Semantics" (Batista et al., 2015) in EMNLP'15 - Python implementation

Aspect-Based-Sentiment-Analysis. Aspect-Based Sentiment Analysis Experiments

text-classification. An example on how to train supervised classifiers for multi-label text classification using sklearn pipelines

ConvNets-for-Sentence-Classification. "Convolutional Neural Networks for Sentence Classification" (Kim 2014) - https://www.aclweb.org/anthology/D14-1181

machine-learning-notebooks. Assorted exercises and proof-of-concepts to understand and study machine learning and statistical learning theory

lexicons. Dictionaries of names, surnames, acronyms and it's extensions, stop-words, etc., which I gathered for different experiments.

TAC-Entity-Linking. An entity linking prototype, developed using the datasets from the TAC-KBP sub-task.

awesome-Portuguese-NLP. A list of libraries and NLP projects for Portuguese

information-extraction-PT. An example of triples extraction with PoS-tags using ReVerb

REACTION-resources. Resources developed by and for the project REACTION (Retrieval, Extraction and Aggregation Computing Technology for Integrating and Organizing News) an initiative for developing a computational journalism platform (mostly) for Portuguese.

StanfordNER-experiments. Python

haystack-retrieval. Different retrieval techniques implemented in Haystack - presented at PyCon Lithuania 2025 🇱🇹

Toponym-Disambiguation-Using-Ontology-Based-Semantic-Similarity. Toponym Disambiguation using Ontology-based Semantic Similarity.

SLANG-Sequence-LAbeliNG. Sequence LAbeliNG with Neural Networks: "Neural Architectures for Named Entity Recognition" (Lample et al., 2016) and "End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF" (Ma, 2016)

MuSICo. A Minwise Hashing Method for Addressing Relationship Extraction from Text

coding-exercises. A repository of coding interview questions and solutions

NER-English-Gigaword-LDC. Python scripts to parse the Gigaword collection and perform NER tagging with StanfordNER

bash-shell-utils. bash scripts, sed examples, and other stuff that I need from time to time

ml-report-kit. A plug-in to generate various evaluation metrics and reports ( PR-curves, classifications reports, confusion matrix) for supervised machine learning models using only two lines of code.

dbpedia-webapps. Simple webapps, relying on DBpedia as a data-source.

Temporal-Information-Datasets.

GermEval-2019-Task_1. GermEval 2019 Task 1 - Shared Task on Hierarchical Classification of Blurbs

minhash-classifier. supervised relationship extraction based on min-hash and locality sensitive hashing

Awesome-CV. :page_facing_up: Awesome CV is LaTeX template for your outstanding job application

Snowball-Java. Snowball: Extracting Relations from Large Plain-Text Collections

nostalgia. Old projects of mine, done during high-school or university and found in old hard-drives

davidsbatista.net. my personal homepage and blog

GermEval-2017-Aspect-Based-Sentiment-Analysis. Python

politiquices. Explore relações de apoio e oposição, entre personalidades políticas, expressas em títulos de notícias preservadas no arquivo.pt