Dialogue Summarization: A Deep Learning Approach

This article was published as a part of the Data Science Blogathon. Dialogue Summarization: Its types and methodology   Image cc: Aseem Srivastava Summarizing long pieces of text is a challenging problem. Summarization is done primarily in two ways: extractive approach and abstractive approach. In this work, we break down the problem of meeting summarization into extractive and abstractive components which further collectively generate a summary of the conversation.   What is Dialogue Summarization? Humans are social animals, we exchange […]

Read more

Python: Get Number of Days Between Dates

Introduction In this tutorial, we’ll take a look at how to get the number of days between two dates in Python. We’ll be using the built-in datetime package, that allows you to really easily work with datetime objects in Python. Creating a Datetime Object As datetime is a built-in module, you can access it right away by importing it at the top of your Python file. You can construct datetime objects in a few different ways: from datetime import datetime […]

Read more

Python: Check if Variable is a Dictionary

Introduction Variables act as a container to store data. A developer can use type hints when creating variables or passing arguments, however, that’s an optional feature in Python, and many codebases, old and new, are yet to have them. It’s more common for a variable in Python to have no information of the type being stored. If we had code that needed a dictionary but lacked type hints, how can we avoid errors if the variable used is not a […]

Read more

A Gentle Introduction to Stochastic Optimization Algorithms

Stochastic optimization refers to the use of randomness in the objective function or in the optimization algorithm. Challenging optimization algorithms, such as high-dimensional nonlinear objective problems, may contain multiple local optima in which deterministic optimization algorithms may get stuck. Stochastic optimization algorithms provide an alternative approach that permits less optimal local decisions to be made within the search procedure that may increase the probability of the procedure locating the global optima of the objective function. In this tutorial, you will […]

Read more

Machine Translation Weekly 68: Pre-editing of MT inputs

Today, I am going to comment on a paper that systematically explores something that probably many MT users do this is pre-editing (editing the source sentence) to get a better output of an MT that is treated as a black box. The title of the paper is Understanding Pre-Editing for Black-Box Neural Machine Translation by authors from Nagoya University and NICT in Japan and will appear at this year’s EACL. Pre-editing is something I often do when I use automatic […]

Read more

Python: How to Add Key to a Dictionary

Introduction A dictionary in Python is a collection of items that store data as key-value pairs. We can access and manipulate dictionary items based on their key. Dictionaries are mutable and allow us to add new items to them. The quickest way to add a single item to a dictionary is by using referencing a dictionary’s index with a new key and assigning a value. For example, we add a new key-value pair like this: snacks[‘chocolate’] = 5 Python allows […]

Read more

Python: How to Remove a Key from a Dictionary

Introduction In this article, we’ll take a look at how to remove keys from Python dictionaries. This can be done with the pop() function, the del keyword, and with dict comprehensions. Remove a Key Using pop(key,d) The pop(key, d) function removes a key from a dictionary and returns its value. It takes two arguments, the key is removed and the optional value to return if the key isn’t found. Here’s an example of popping an element with only the required […]

Read more

Customer Sentiments Analysis of Pepsi and Coca-Cola using Twitter Data in R

This article was published as a part of the Data Science Blogathon. Introduction Coca-Cola and PepsiCo are well-established names in the soft drink industry with both in the fortune 500. The companies that own a wide spectrum of product lines in a highly competitive market have a fierce rivalry with each other and constantly competing for market share in almost all subsequent product verticals. We will analyze the sentiment of customers of these two companies with the help of 5000 […]

Read more

How to Use Optimization Algorithms to Manually Fit Regression Models

Regression models are fit on training data using linear regression and local search optimization algorithms. Models like linear regression and logistic regression are trained by least squares optimization, and this is the most efficient approach to finding coefficients that minimize error for these models. Nevertheless, it is possible to use alternate optimization algorithms to fit a regression model to a training dataset. This can be a useful exercise to learn more about how regression functions and the central nature of […]

Read more
1 3 4 5 6 7 10