georgepar

{
	"Create Class": {
		"prefix": "cls",
		"body": [
		  "class ${1:MyClass}(${2:object}):",
		  "    def __init__(self, ${3:*args}, ${4:**kwargs}):",
		  "        super(${1:MyClass}, self).__init__(${5:*args}, ${6:**kwargs})"
		],
		"description": "Create Class"
	  },

georgepar

from typing import Dict, Optional

import torch
import torch.nn as nn
from torchcrf import CRF
from transformers import AutoModel


class TransformerSlidingWindower(nn.Module):
    """Apply model on a strided sliding window

georgepar

[[package]]
name = "absl-py"
version = "0.12.0"
description = "Abseil Python Common Libraries, see https://github.com/abseil/abseil-py."
category = "main"
optional = false
python-versions = "*"

[package.dependencies]
six = "*"

georgepar

#!/usr/bin/env bash

SPELL_CHECKER_COMPILED=${1}

python test.py | 
    fstcompile --isymbols=letter_syms.txt --osymbols=letter_syms.txt | 
    fstcompose - ${SPELL_CHECKER_COMPILED} | 
    fstshortestpath |
    fstrmepsilon |
    fsttopsort |

georgepar

#!/usr/bin/env bash

python create_fst.py | fstcompile --isymbols=chars.syms --osymbols=chars.syms - rosebud.bin.fst

georgepar

{"lastUpload":"2020-08-27T13:06:54.146Z","extensionVersion":"v3.4.3"}

georgepar

How to run

• Download this as a tab separated file
• Run python create_papers_csv.py --inp acl2020_accepted_papers.tsv --out out.csv --n-keywords 5

Create the embeddings and projection files

• python embeddings.py ../acl-2020-virtual-conference-sitedata/papers.csv
• python reduce.py ../acl-2020-virtual-conference-sitedata/papers.csv embeddings.torch > ../sitedata_acl2020/papers_projection.json --projection-method [tsne|umap]

georgepar

import numpy as np
import gzip
import copy
from sklearn.preprocessing import LabelEncoder
from torch.utils.data import Dataset
from torch.utils.data import SubsetRandomSampler, DataLoader


# Combine similar classes and remove underrepresented classes
class_mapping = {

georgepar

import numpy as np
import gzip
import copy
from sklearn.preprocessing import LabelEncoder
from torch.utils.data import Dataset
from torch.utils.data import SubsetRandomSampler, DataLoader


class_mapping = {
    'Rock': 'Rock',

georgepar

import numpy as np
import gzip
import copy
from sklearn.preprocessing import LabelEncoder
from torch.utils.data import Dataset
from torch.utils.data import SubsetRandomSampler, DataLoader


class_mapping = {
    'Rock': 'Rock',