Duygu ALTINOK – Medium

Mar 1

Neden yasaklandı? Depremle ilgili Ekşi Sözlük yorumlarına NLP gözüyle bakış

Ekşi Sözlük yazarları gerçekten hükümeti karalama kampanyası yürüttü mü? Depremle ortaya çıkan duyguların politik hararete dönmesiyle başlayan, sitenin yasaklanmasıyla biten yolun sayılarla incelenmesi. — Malumunuz kısa bir süre önce deprem sırasında ve sonrasında yazılan yorumlardan dolayı Ekşi Sözlük’ün başı derde girdi. BTK bu karara sebep olarak hükümeti ve kurumlarını küçük düşürme, yetersiz gösterme ve toplumda kaos ortamı yaratmayı göstermiş.

NLP

10 min read

Neden yasaklandı? Depremle ilgili Ekşi Sözlük yorumlarına NLP gözüyle bakış

NLP

10 min read

Published in Towards Data Science

·Sep 24, 2021

Zero-Shot Intent Classification with Siamese Networks

Locate out-of-domain intents effectively with zero-shot intent classification — Intent recognition is an essential task for goal-oriented dialogue systems. Intent recognition (sometimes also called intent detection) is the task of classifying each user utterance with a label, which comes from a predefined set of labels. Classifiers train on labelled data and learns to discriminate which utterance belongs to which…

NLP

8 min read

Zero-shot Intent Classification with Siamese Networks

NLP

8 min read

Published in Towards Data Science

·Sep 7, 2021

Siamese NN Recipes with Keras

Practical Siamese neural network recipes with Keras and BERT for semantic similarity tasks — I have been enjoying Siamese networks for different NLU tasks at my work for quite some time. In this article, I’ll share quick recipes with Keras, featuring Glove vectors or BERT as the text vectorizer. We’ll focus on semantic similarity calculations. Semantic similarity is basically the task of determining if…

NLP

4 min read

NLP

4 min read

Published in Towards Data Science

·Mar 8, 2021

Context Theory II: Semantic Frames

Semantic Framing for Dialogue Management — In the previous articles of context theory series, first we discovered some linguistic concepts related to context. Next, we dived into conversation structure; what makes a conversation meaningful and coherent. In this article, we’ll focus on a structured way of dialogue management, called Semantic Framing. As understood from the name…

Dialogue Management

9 min read

Dialogue Management

9 min read

Published in Towards Data Science

·Jul 19, 2020

Mood & Modality and Dialogue Sentiment

Verbal Features and Dialogue Sentiment with spaCy — In this article, we will see how verbal functional categories used in customer dialogue text and how these categories contribute to the semantics, especially the text sentiment. Verb phrase in a sentence sometimes can carry huge semantics, sometimes hint the sentiment only by itself even though if one does not…

NLP

12 min read

NLP

12 min read

Published in Towards Data Science

·May 16, 2020

Turkish Phonetics: A Quick Intro

A Practical Turkish Articulatory Phonetics Intro — In this article, we will explore some details of the Turkish phonetic system, including tips for better quality Turkish ASR development 😉 Before shifting to Conversational AI, I worked in a speech team. In this article, I will share the tips I found out during developing a Turkish speech recognition…

Speech Recognition

9 min read

Speech Recognition

9 min read

Published in Towards Data Science

·Feb 24, 2020

Neo4j vs GRAKN Part II: Semantics

Battle of Semantics: Who models the data better? — Dear readers, in this part I will take you to the semantics land. In the first part, we compared Grakn and Neo4j worlds in general to see how the paradigm difference lead to different ways of doing things. …

Neo4j

9 min read

Neo4j

9 min read

Published in Towards Data Science

·Feb 24, 2020

Neo4j vs GRAKN Part I: Basics

An exhaustive comparison between two most popular knowledge bases — Dear readers, in this series of articles I compared two popular knowledge bases: Neo4j and Grakn. I decided to write this comparison long time ago upon your requests, however kismet is for now 😊 This is a detailed comparison in 3 parts: first part is devoted to technical details, the…

Knowledge Graph

13 min read

Knowledge Graph

13 min read

Published in Towards Data Science

·Jun 10, 2019

Context Theory I: Conversation Structure

"Must a name mean something?" Alice asked doubtfully. "Of course it must," Humpty Dumpty said with a short laugh; "my name means the shape I am - and a good handsome shape it is, too. With a name like yours, you might be any shape, almost." …

Artificial Intelligence

7 min read

Context Theory I: Conversation Structure

Artificial Intelligence

7 min read

Published in Towards Data Science

·Mar 28, 2019

Context Theory I: Introduction

An intro to linguistic foundations of computational pragmatics — "That's a great deal to make one word mean", Alice said in a thoughtful tone. "When I make a word do a lot of work like that", said Humpty Dumpty, "I always pay it extra". Through the Looking Glass, Lewis Carroll Conversational AI has come a long way since the…

NLP

9 min read

NLP

9 min read