Recently Updated Pages
Horbach et al., 2019
The influence of variance in learner answers on automatic content scoring Andrea Horbach and Tor...
Riordan et al., 2019
How to account for mispellings: Quantifying the benefit of character representations in neural c...
CLINGDING Fall 2019
9-4: Coffee (crumble 10th and college) 9-11: Internship: noor, josephine, ken, hai 9-18: Coffe...
Notes
If you're running pytest and you have your own modules, sometimes it's necessary to run pytest as...
August 2019
New gtx 1070 blower in Mwanfunzi. With both GPUs under 99% load the power consumption is 415 watt...
Server refresh
I would like to get away from my dl380 g7 as it is somewhat loud and quite energy inefficient. C...
July 2019
July 19 2019 Mwanafunzi is listing nvidia-docker, docker-ce, and nvidia-docker-runtime as upgrad...
Notes on Screen
It is a good idea to use screen sessions On super computers like those at IU, it is essential to...
Docstring example
class Albatross(object): """A bird with a flight speed exceeding that of an unladen swallow....
Datasets
Guarani BABEL is stored at /nas/data/lorelei/ldc_downloads/LDC2016E19__IARPA_Babel_Guarani_Langua...
Building mozilla with deepspeech integration
https://treeherder.mozilla.org/#/jobs?repo=try&revision=5266680e9e43df3dd2a922b334ce9b33df73a...
Potentially using tensorflow api in python instead of c++
the tensorflow api in c++ is a bear to use. no one really uses it much and it has some noteworthy...
Crow res
After setting alpha and beta parameters for language model to 0 (effectively negating the languag...
Deep Speech Scorer Refactor
I have successfully renamed all variables dealing with the scorer and reran everything. The next...
Deep speech build
These instructions are for those of us who wish to have a version of Mozilla's DeepSpeech where t...
Generate trie
This issues a call to scorer::setup()?
Deep Speech import
Loading TSV file: /home/kenneth/Projects/JSALT_NPLM_data/Speech/Deep_Speech/cro/train.tsv Savin...
Text conversion command
for file in `ls ../Inuit-Yupik/ess/monolingual_corpus/sivuqam_nangaghnegha/sivuqam_volume2/volume...
Querying word embeddings for word similarity and relatdness
Word relatedness is sometimes asymmetrical e.g. stork may elicit associations with baby but baby...
Catastrophic Interference in Neural Embedding Models (Dachapally & Jones)
Catastrophic forgetting is the tendancy of neural models to have a strong recency bias e.g. more ...