吴国华 wugh

PPDB: The Paraphrase Database

The paper presents a database of ranked English and Spanish paraphrases derived by:
- Extracting lexical, phrasal, and syntactic paraphrases from large bilingual parallel corpora.
- Computing the similarity scores for the pair of paraphrases using Google ngrams and the Annotated Gigaword corpus.
Link to the paper

brew install mysql

Set up launchctl to auto start mysql

$ ln -sfv /usr/local/opt/mysql/*.plist ~/Library/LaunchAgents

/usr/local/opt/mysql/ is a symlink to /usr/local/Cellar/mysql/x.y.z (e.g., 5.6.16)

start new:

tmux

start new with session name:

tmux new -s myname

	# 21 世纪最伟大的发明是什么，那必然是 AI
	# 所以如果你遇到什么问题，也许问 AI 比问人更快哦

	# AFF
	# 如果你想支持我，可以通过我的邀请链接购买机场
	# 感谢支持
	# 1. ssLinks 邀请码: fSo2OhzH https://98a6251b6cd7471da86cca993b6dbe6f.36d.biz/#/register?code=fSo2OhzH 贵快
	# 2. 一元机场邀请码: r3f1duds https://xn--4gq62f52gdss.top/#/register?code=r3f1duds 垃圾但是便宜
	# 3. Kitty 邀请码: MSOOG0Q0 https://kitty.fo/register?invite=MSOOG0Q0
	# 4. BiuBiu 邀请码: fACfjKC8 https://biubiux.online/#/register?code=fACfjKC8 有年周期套餐

	#! /usr/bin/env python

	import tensorflow as tf

	def inference_fn(x, training=False):
	net = x

	net = tf.layers.flatten(net)
	net = tf.layers.dense(net, 512, activation=tf.nn.relu)
	net = tf.layers.dropout(net, 0.2, training=training)

	''' Script for downloading all GLUE data.

	Note: for legal reasons, we are unable to host MRPC.
	You can either use the version hosted by the SentEval team, which is already tokenized,
	or you can download the original data from (https://download.microsoft.com/download/D/4/6/D46FF87A-F6B9-4252-AA8B-3604ED519838/MSRParaphraseCorpus.msi) and extract the data from it manually.
	For Windows users, you can run the .msi file. For Mac and Linux users, consider an external library such as 'cabextract' (see below for an example).
	You should then rename and place specific files in a folder (see below for an example).

	mkdir MRPC
	cabextract MSRParaphraseCorpus.msi -d MRPC

	var waitForEl = function(selector, callback) {
	if (jQuery(selector).length) {
	callback();
	} else {
	setTimeout(function() {
	waitForEl(selector, callback);
	}, 100);
	}
	};