Russel Ku

Model · Question answering

bert-base-cased-squad-extractive-qa

Russel Ku

This repository provides a fine-tuned bert-base-cased model adapted for the downstream task of Extractive Question Answering on the full SQuAD v1.1 dataset. Given a (Question, Context) pair, the model predicts the exact start and end character/token spans within the context passage that answer the question. The model was evaluated on the complete SQuAD v1.1 validation set (valdataset, 10,570 examples): Our final Epoch 3 checkpoint achieves 88.21% F1 and 80.75% EM, matching the original Google BERT benchmark (-0.29 F1 points) with complete reproducibility on modern GPU hardware and AMP FP16. - Sequence Length (maxlength): 384 tokens - Document Stride (docstride): 128 tokens To better…

Model · Sentence similarity

simcse-bert-uncased-unsup

Russel Ku

Unsupervised SimCSE sentence encoder trained from bert-base-uncased on a 100k-record subset of SNLI, as a course replication of Gao, Yao & Chen (EMNLP 2021). It maps an English sentence to a 768-dimensional vector; compare sentences with cosine similarity. Team (Universidad Politécnica de Yucatán, U2T02): Acosta Castellanos Bianca Alexandra, Canche Chuc Angel Rivaldo, Ku Aguilar Russel, Sanchez Novelo Damian, Velasco Martin Jonathan Abisai. 165,528 unique sentences (premises and hypotheses, whitespace-stripped) from snlitrain100k.jsonl, a 100k-record subset of the SNLI train split. Labels are not used: each sentence is its own positive, the two views differ only by dropout. The paper…