ITERATED DECOMPOSITION: IMPROVING SCIENCE Q&A
Type: Paper
Posts by Year
2023
Decoder Inference Optimization
Introduction
1 Year of a Challenging Big-Bench Task
In 2021 I contributed to the Big-Bench suite of NLP tasks, aiming to probe the abilities of large language models. Inspired by sports, I developed a task aim...
2022
Relation Extraction as Open-book Examination:
Introduction
Trial2Vec
Trial2Vec
TeKo: Text-Rich Graph Neural Networks
Introduction
PolyDPR
Introduction
PALM
Introduction
CDLM: Cross-Document Language Model
Introduction
SPANBERT
What is the name of the SpanBERT paper? SpanBERT: Improving Pre-training by Representing and Predicting Spans Mandar Joshi, ...
Condenser
Introduction
Adaptable Adapters
Introduction
Improving Multi-task Generalization Ability for Neural Text
What is the name of the MatchPrompt paper? Improving Multi-task Generalization Ability for Neural Text Matching via Prompt Learning ...
Introducing Neural Bag of Whole-Words with ColBERTer
Introduction
ARE NEURAL NETS MODULAR? INSPECTING FUNCTIONAL MODULARITY THROUGH DIFFERENTIABLE
machinelearning::papers::AreNeuralNetworksModular
Hyperlink-induced Pre-training
Introduction
Compressing Sentence Representation for Semantic Retrieval via Homomorphic Projective Distillation
Introduction
Token Dropping for Efficient BERT Pretraining
Introduction
Memorizing Transformers
Introduction
Mar 20 Research Wrapup
Paper Summaries:
Mar 18 Research Wrapup
Quick hit thoughts on trending papers?
Visualizing and Measuring the Geometry of BERT
What is the name of the BERT geometry paper? Visualizing and Measuring the Geometry of BERT Hewitt and Manning Hewitt (20...
GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models
Introduction
Neural reality of argument structure constructions
Introduction
NoisyTune: A Little Noise Can Help You Finetune
Type: Paper
TransformerXL
Introduction Transformer models typically have a fixed context window that is hard to scale due to the $O(n^2)$ cost of the attention mechanism. Extending th...
Compacter
Intro
2021
Wav2Vec part 1: Wav2Vec and VQwav2vec
What is Wav2Vec?
Parallelizing OpenCV For Real Time Object Detection
Introduction
2020
XGboost Part 1: Gradient Boosting
Introduction Xgboost is a powerful yet simple algorithm that has achieved state of the art results on tabular datasets. The Xgboost algorithm uses an ensembl...
Training an AI to play Incan Gold
Introduction