Sebastian Ruder

FEBRUARY 23, 2023

As discrete decisions cannot be learned directly with gradient descent, methods learn hard routing via reinforcement learning, evolutionary algorithms, or stochastic re-parametrisation.  Hard learned routing models the choice of whether a module is active as a binary decision. Soft learned routing.  Soft

Deep Learning 52

Deep Learning NLP Computer Vision Metadata 52

AWS Machine Learning Blog

MAY 22, 2023

Amazon EBS is well suited to both database-style applications that rely on random reads and writes, and to throughput-intensive applications that perform long, continuous reads and writes. """, """ Amazon Comprehend uses natural language processing (NLP) to extract insights about the content of documents.

Natural Language Processing 89

Natural Language Processing Machine Learning Computational Linguistics NLP 89

Sebastian Ruder

NOVEMBER 14, 2022

Developing models that work for more languages is important in order to offset the existing language divide and to ensure that speakers of non-English languages are not left behind, among many other reasons. In Findings of the Association for Computational Linguistics: ACL 2022 (pp. 2340–2354). Winata, G.

Natural Language Processing 52

Natural Language Processing NLP Computational Linguistics AI 52

Sebastian Ruder

JUNE 6, 2022

The initiative focuses on making Computational Linguistics (CL) research accessible in 60 languages and across all modalities, including text/speech/sign language translation, closed captioning, and dubbing. propose a method that prefers subwords that are shared across multiple languages. Similarly, Hofmann et al.

NLP 52

NLP Natural Language Processing Computational Linguistics Neural Network 52

Explosion

MAY 8, 2016

German is like English but different On the evolutionary tree of languages, German and English are close cousins, on the Germanic branch of the Indo-European family. The algorithmic changes needed to process German are an important step towards processing many other languages. It’s a simplifying assumption.

Convolutional Neural Networks 40

Convolutional Neural Networks NLP Algorithm Neural Network 40

Topbots

JUNE 15, 2023

Language Disparity in Natural Language Processing This digital divide in natural language processing (NLP) is an active area of research. 70% of research papers published in a computational linguistics conference only evaluated English.[ Association for Computational Linguistics.

Natural Language Processing 59

Natural Language Processing Computational Linguistics NLP ChatGPT 59

Topbots

JANUARY 30, 2023

In the last couple of years, Large Language Models (LLMs) such as ChatGPT, T5 and LaMDA have developed amazing skills to produce human language. We are quick to attribute intelligence to models and algorithms, but how much of this is emulation, and how much is really reminiscent of the rich language capability of humans?

Large Language Models 52

Large Language Models LLM Computational Linguistics Natural Language Processing 52

NLP People

SEPTEMBER 12, 2017

This job brought me in close contact with a large number of IT researchers, and some of them happened to work in computational linguistics and machine learning. This was when I realized I might try to pursue this path too, as it would allow me to combine my passion for languages and interest in technologies.

Computational Linguistics 52

Computational Linguistics Data Mining Machine Learning Natural Language Processing 52

Sebastian Ruder

JANUARY 24, 2022

2021) 2021 saw many exciting advances in machine learning (ML) and natural language processing (NLP). In mathematics, ML was shown to be able to guide the intuition of mathematicians in order to discover new connections and algorithms [77]. Transactions of the Association for Computational Linguistics, 9, 978–994.

NLP 52

NLP ML BERT Computational Linguistics 52

AWS Machine Learning Blog

MARCH 2, 2023

He spent 10 years as Head of Morgan Stanley’s Algorithmic Trading Division in San Francisco. Ana has had several leadership roles at startups and large corporations such as Intel and eBay, leading ML inference and linguistics related products. She has a technical background in AI and Natural Language Processing.

BERT 75

BERT Deep Learning Metadata Auto-complete 75

Explosion

DECEMBER 17, 2013

I wrote this blog post in 2013, describing an exciting advance in natural language understanding technology. Today, almost all high-performance parsers are using a variant of the algorithm described below (including spaCy). This doesn’t just give us a likely advantage in learnability; it can have deep algorithmic implications.

Python 45

Python Algorithm NLP Computational Linguistics 45

ODSC - Open Data Science

MARCH 6, 2024

Artificial Intelligence has made significant strides since its inception, evolving from simple algorithms to highly advanced Neural Networks capable of performing sophisticated tasks such as generating completely new content, including images, audio, and video. She is currently part of the Artificial Intelligence Practice at Avanade.

Responsible AI 52

Responsible AI Generative AI Natural Language Processing Artificial Intelligence 52

NLP People

JULY 24, 2019

The 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019) is starting this week in Florence, Italy. The analysis is based on ACL papers published since 1998 which were processed using a domain-specific ontology for the fields of NLP and Machine Learning. For a mathematical introduction, Young et al.

NLP 52

NLP Neural Network Deep Learning Natural Language Processing 52