aneesh-joshi

# Easy editing and sourcing of .bashrc
alias vbrc='vim ~/.bashrc ; source ~/.bashrc'

# Quick git commands
alias gs='git status'
alias gd='git diff';
alias gl='git log';
alias glol='git log --oneline'
alias gdno='git diff --name-only;'
alias gad='git add .'

aneesh-joshi

• broadly speaking there are three classes of multiple access protocols:

  • channel partitioning (including CDMA)
  • random access
  • taking turns

• This random access protocol is referred to as CSMA with collision avoidance, or more succinctly as CSMA/CA. As with Ethernet’s CSMA/CD, the “CSMA” in CSMA/CA stands for “carrier sense multiple access,” meaning that each station senses the channel before transmitting, and refrains from transmitting when the channel is sensed busy

• CSMA/CA(802.11) vs CDMA(Ethernet???)

  • Collision avoidance vs collision detection

• senses before transmitting vs transmits as soon as channel is sensed to be idle

aneesh-joshi

Basic file operations:

List the files in a directory

ls

List the files in a directory

• -l : more details per file
• -a : include hidden files (files starting with .) ls -la

Change directory

aneesh-joshi

Similarity Learning using Neural Networks

Index

1. Problem Statement
2. Similarity Learning Tasks
3. Evaluation Metrics
4. Establishing Baselines
5. About Datasets
6. The journey
7. Notes on Finetuning Models

aneesh-joshi

Resources on QA-Transfer Model

QA-Transfer Model uses:

• SQUAD-T dataset
• BiDAF model (with end layers changed)

BiDAF moedel has 3 open source implementations:

• AllenAI-keras
• Original-BiDAF-tf-0.11 and Original-QA-Transfer-tf-0.11 (QA-Transfer essentially forks the first repo and makes some changes to it.)
• PyTorch

aneesh-joshi

Resources on QA-Transfer Model

QA-Transfer Model uses:

• SQUAD-T dataset
• BiDAF model (with end layers changed)

BiDAF moedel has 3 open source implementations:

• AllenAI-keras
• Original-BiDAF-tf-0.11 / Original-QA-Transfer
• PyTorch

aneesh-joshi

WikiQA test set	w2v 300 dim	MP	FT 300 dim	DRMM_TKS	biMPM
map	0.6277	0.6515	0.5276	0.6259	0.3856
gm_map	0.4968	0.5147	0.3923	0.4966	0.269
Rprec	0.4667	0.5089	0.3429	0.4613	0.1965

Current Situation For the task of similarity learning, we are evaluating on the WikiQA Dataset

aneesh-joshi

import sys
import os
sys.path.append(os.path.join('..'))

import csv
import re
import gensim.downloader as api
from gensim.utils import simple_preprocess
import numpy as np

aneesh-joshi

How to reproduce your benchmark

This document will explain the newly introduced files, how they are to be used and how to reproduce my benchmarks.

Additional dependencies:

Unfortunately, the current state of the code needs the additional dependency of pandas, a module for hadnling .csv, .tsv, etc. I was using it for grouping the datapoints by the document id. There are ways to do it without it and will be pushed soon.

So, you will have to install pandas first by running the command: pip install pandas

aneesh-joshi

MZ : the Match Zoo evaluation run on my machine Mine: my evaluation script run on my machine

ANMM

MZ:
map=0.610744
ndcg@1=0.459916
ndcg@3=0.603051