Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Introduction to NLP : How to improve accessibil...

Avatar for Victoria Ubaldo Victoria Ubaldo
June 11, 2021
Technology
220
1

Introduction to NLP : How to improve accessibility with Machine Learning

WWCode CONNECT REIMAGINE 2021

Avatar for Victoria Ubaldo

Victoria Ubaldo

June 11, 2021

More Decks by Victoria Ubaldo

See All by Victoria Ubaldo
Analizar Datos con Python y Google Colab
Avatar for Victoria Ubaldo vickyale
1
160
¿Cómo estar al día en Tecnología, como profesional tech?
Avatar for Victoria Ubaldo vickyale
1
480
Primeros pasos en AI/ML
Avatar for Victoria Ubaldo vickyale
0
120
ML Zero to Hero in GCP
Avatar for Victoria Ubaldo vickyale
0
90
Agile & Big Data
Avatar for Victoria Ubaldo vickyale
1
57
Clean Data with Python
Avatar for Victoria Ubaldo vickyale
0
260
AoG Workshop for IWD19
Avatar for Victoria Ubaldo vickyale
0
170
Introducción a Actions for Google Assistant
Avatar for Victoria Ubaldo vickyale
0
83
Kit para crear un sitio web móvil asombroso!
Avatar for Victoria Ubaldo vickyale
0
50

Other Decks in Technology

See All in Technology
long-running-tasks
Avatar for cipepser cipepser
2
450
OpenClawとHermesAgentでAI新入社員を作った話
Avatar for yanada takanoriyanada
0
150
Databricks 月刊サービスアップデート 2026年05月号
Avatar for ちょし tyosi1212
0
130
ITエンジニアを取り巻く環境とキャリアパス / A career path for Japanese IT engineers
Avatar for 高玉 広和 / TAKATAMA Hirokazu takatama
4
1.8k
電子辞書Brainをネットに繋げてみた(自力編)
Avatar for らすぴー raspython3
0
400
Gradle×GitHub_ActionsでCI時間を約50%短縮 ジョブ分割の設計と落とし穴 / Cutting CI Time by ~50% with Gradle and GitHub Actions: Job-Splitting Design and Pitfalls
Avatar for 冨澤宝斗 takatty
0
560
大規模災害時でも高い信頼性を維持するアプリケーション基盤の実現/nikkei-tech-talk46
Avatar for 日本経済新聞社 エンジニア採用事務局 nikkei_engineer_recruiting
0
130
エンジニアは生成AIと どのように向き合うべきか？ ことばの意味という観点から
Avatar for Hitomi Yanaka verypluming
3
310
チームで実践する AI-DLC 思考の軌跡を残すチェックポイント設計
Avatar for Belong inc. belongadmin
0
350
もりもり新機能を一挙紹介！ AgentCoreに入門して、AWS上にAIエージェントを構築しよう
Avatar for みのるん minorun365
PRO
6
530
脅威をエンジニアリングの糧にして：恐怖を乗り越えた先にあったもの / Turn threats into fuel for engineering: what lay beyond overcoming fear
Avatar for nrs nrslib
1
360
ChatworkとBPaaS 異なる特性で学んだAI機能開発の ベストプラクティス
Avatar for kubell kubell_hr
2
470

Featured

See All Featured
Bioeconomy Workshop: Dr. Julius Ecuru, Opportunities for a Bioeconomy in West Africa
Avatar for AKADEMIYA2063 akademiya2063
PRO
1
130
Efficient Content Optimization with Google Search Console & Apps Script
Avatar for Katarina Dahlin katarinadahlin
PRO
1
580
Mind Mapping
Avatar for Hélio Medeiros helmedeiros
PRO
1
220
WENDY [Excerpt]
Avatar for Tessa Abrams tessaabrams
11
38k
Documentation Writing (for coders)
Avatar for Carmen Chung carmenintech
77
5.4k
ラッコキーワード サービス紹介資料
Avatar for ラッコ株式会社 rakko
1
3.5M
sira's awesome portfolio website redesign presentation
Avatar for ElsiraPls elsirapls
0
270
First, design no harm
Avatar for Per Axbom axbom
PRO
2
1.2k
Automating Front-end Workflow
Avatar for Addy Osmani addyosmani
1370
210k
Designing for Performance
Avatar for Lara Hogan lara
611
70k
AI Search:
Where Are We & What Can We Do About It?
Avatar for Aleyda Solis aleyda
0
7.5k
The AI Revolution Will Not Be Monopolized: How open-source beats economies of scale, even for LLMs
Avatar for Ines Montani inesmontani
PRO
3
3.5k

Transcript

  1. None

  2. Victoria Ubaldo @Vikyale Introduction to NLP : How to improve

    accessibility with Machine Learning CONNECT REIMAGINE 2021

  3. Hello! Computer and System Engineer. Peruvian Data Analyst @Interbank Msc

    Candidate Computer Science, PUCP. Enjoy mentoring, illustration and dancing!

  4. Agenda • Machine Learning and Accessibility • Natural Language Processing

    • Tensorflow for NLP • Next steps
  5. None
  6. None
  7. None

  8. Machine Learning is programming with data

  9. None
  10. None

  11. Natural Language Process (NLP)

  12. None

  13. Where find NLP ? Chatbots Predictive text (autocomplete) Transcription Language

    translation Others: Text Analysis Email filters Search Result Sentiment Analysis

  14. Challenges in NLP

  15. None

  16. Challenges in NLP : Textual Accessibility Visual Auditory Speech

  17. Accessible = Comprehensible

  18. Challenges in NLP : Textual Accessibility Transcription Speech recognition Language

    Translation

  19. Case : Recognize sentiment in Text

  20. None

  21. Amazon and Yelp reviews 1 : Good 0: Bad

  22. Pre-processing data

  23. Text Processing

  24. Tokenization

  25. Out Of Vocabulary (OOV) EXTRA WORDS unknown tokens (UNK)

  26. Stop Words

  27. Stemming

  28. Lemmatization

  29. Padding

  30. Tools! • Python 3.+ • Jupyter Notebook or Google Colab

    • and using a framework for ML

  31. ¿Why Tensorflow? Whether you’re an expert or a beginner, TensorFlow

    is an end-to-end platform that makes it easy for you to build and deploy ML models.

  32. Trying in Google Colab bit.ly/2TU9MJz

  33. Challenges in NLP : Textual Accessibility Transcription Speech recognition

  34. None

  35. Challenges in NLP : Textual Accessibility Language Translation

  36. None

  37. Next steps Try new tools : - Recurrent Neural Network

    (RNN) - Long short-term memory (LSTM)

  38. Next steps Increase your corpus with diverse data. - PDFMiner

    - Tweepy API

  39. Next steps Datasets with native or indigenous language or code

    mixing

  40. “We can build a much brighter future where humans are

    relieved of menial work using AI capabilities” - Andrew Ng

  41. Thanks! @womenwhocode #WWCode Keep in touch! linkedin.com/in/victoriaubaldo @vikyale

  42. None