Code for Massive-scale Decoding for Text Generation using Lattices

Last update: Dec 18, 2022

Related tags

Overview

Massive-scale Decoding for Text Generation using Lattices

TL;DR: a new search algorithm to construct lattices encoding many generation options; two key technical contributions: (1) best-first search, (2) path recombination.

Visualization

We provide a few examples in the vis folder and on my homepage. You need to download the html files to view and interact with the model outputs.

The complete set of outputs are available on Box.

Getting started

model contains all of the methods, including baselines like beam search, nucleus sampling, and our methods.
evaluation contains scripts for evaluation.
command are the prompts and shells we use to run the experiment.

Beam Search:

PYTHONPATH=./ python src/recom_search/command/run_pipeline.py -nexample 100  -ngram_suffix 4  -beam_size 16 -min_len 10 -max_len 35   -model bs

Best-first Search:

PYTHONPATH=./ python src/recom_search/command/run_pipeline.py -nexample 100  -ngram_suffix 4  -beam_size 16 -min_len 10 -max_len 35   -model astar_baseline

Best-first Search with Recomb:

PYTHONPATH=./ python src/recom_search/command/run_pipeline.py -nexample 100  -ngram_suffix 4 -beam_size 16 -min_len 10 -max_len 35 -model astar -merge imp  -avg_score 0.75  -adhoc

Best-first Search with Zip:

PYTHONPATH=./ python src/recom_search/command/run_pipeline.py -nexample 100  -ngram_suffix 4 -beam_size 16 -min_len 10 -max_len 35 -model astar -merge zip  -avg_score 0.75  -adhoc

More detailed instructions coming soon!

Citation

@misc{xu-durrett-2021-massive,
    title={Massive-scale Decoding for Text Generation using Lattices},
    author={Jiacheng Xu and Greg Durrett},
    year={2021},
    eprint={2112.07660},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

Contact

[email protected]

Code for Massive-scale Decoding for Text Generation using Lattices

Related tags

Overview

Massive-scale Decoding for Text Generation using Lattices

Visualization

Getting started

Citation

Contact

Owner

Jiacheng Xu

Context Axial Reverse Attention Network for Small Medical Objects Segmentation

Fedlearn支持前沿算法研发的Python工具库 | Fedlearn algorithm toolkit for researchers

TraSw for FairMOT - A Single-Target Attack example (Attack ID: 19; Screener ID: 24):

Density-aware Single Image De-raining using a Multi-stream Dense Network (CVPR 2018)

Face Recognize System on camera AI OAK1

A benchmark for the task of translation suggestion

The fastai book, published as Jupyter Notebooks

Source code, data, and evaluation details for “Cross-Lingual Citations in English Papers: A Large-Scale Analysis of Prevalence, Formation, and Ramifications”

High-Resolution 3D Human Digitization from A Single Image.

Implementation of Neonatal Seizure Detection using EEG signals for deploying on edge devices including Raspberry Pi.

Inferring Lexicographically-Ordered Rewards from Preferences

Worktory is a python library created with the single purpose of simplifying the inventory management of network automation scripts.

The 2nd Version Of Slothybot

Fre-GAN: Adversarial Frequency-consistent Audio Synthesis

Pytorch implementation of the AAAI 2022 paper "Cross-Domain Empirical Risk Minimization for Unbiased Long-tailed Classification"

Decoding the Protein-ligand Interactions Using Parallel Graph Neural Networks

StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks

N-gram models- Unsmoothed, Laplace, Deleted Interpolation

Migration of Edge-based Distributed Federated Learning

A Partition Filter Network for Joint Entity and Relation Extraction EMNLP 2021