1. NLP 2020: What Works and What's Next
Recent Advances in Natural Language Processing
Seth Grimes
Alta Plana Corporation
@SethGrimes
November 20, 2020
4. Disclaimer
I use A LOT of commercial product materials in the
slides that follow. These are illustrations and not
recommendations.
5. Natural Language Processing
Natural Language Understanding (NLU)
• OCR, language detection, tokenization, parsing
• Information extraction: parts of speech, chunks , entities,
aspects, topics/themes, relations, attributes, events, …
• Speech processing
Natural Language Generation (NLG)
NLU + NLG together, for example:
• Summarization
• Machine translation
• Conversational interfaces
• Question answering
10. “Statistical information
derived from word frequency
and distribution is used by the
machine to compute a relative
measure of significance, first
for individual words and then
for sentences. Sentences scoring
highest in significance are
extracted and printed out to
become the auto-abstract.”
-- H.P. Luhn, The Automatic
Creation of Literature Abstracts,
IBM Journal, 1958.
15. Word2Vec: Key Concepts
Continuous bag-of-
words (CBOW)
predicts a word from
a window of
surrounding words.
Skip-gram uses a
word to predict a
window of
surrounding words.
36. Amazon Comprehend Medical
https://aws.amazon.com/comprehend/medical/
“Amazon Comprehend Medical is a natural language processing service that
makes it easy to use machine learning to extract relevant medical information from
unstructured text. Using Amazon Comprehend Medical, you can quickly and
accurately gather information, such as medical condition, medication, dosage,
strength, and frequency from a variety of sources like doctors’ notes, clinical trial
reports, and patient health records. Amazon Comprehend Medical can also link the
detected information to medical ontologies such as ICD-10-CM or RxNorm so it
can be used easily by downstream healthcare applications.”
46. “If we want computers to be genuinely
intelligent, to adapt to us and to interact
naturally with us, then they will need to ability
to recognize and express emotions, and to
have what has come to be called ‘emotional
intelligence.’”
-- Rosalind Picard, Affective Computing, 1997
Affective Computing
50. What about Sentiment Analysis? Text sourced…
https://dl.acm.org/doi/10.1145/945645.945658,
October 2003
https://dl.acm.org/doi/10.1561/1500000011,
January 2008
53. Emotion AI
“Emotion mining is the science of detecting, analyzing, and
evaluating humans' feelings towards different events, issues,
services, or any other interest.”
Emotion synthesis enhances the ability of a machine to provide
meaningful, contextual responses, by conveying an appropriate
emotional state through words, voice, and expression.
Emotion induction aims to evoke a certain emotional response or
affective state.
56. “Parsing Text for Emotion Terms:
Analysis & Visualization Using R”
Emotion in
Text: Parsing,
Stats
https://datascienceplus.com/parsing-text-for-emotion-terms-analysis-visualization-using-r/
64. Speech https://www.phon.ucl.ac.uk/courses/spsci/iss/week9.php
“Voice cues are commonly divided into those related to: (a) fundamental
frequency (F0, a correlate of the perceived pitch), (b) vocal perturbation (short-
term variability in sound production), (c) voice quality (a correlate of the
perceived ‘timbre’), (d) intensity (a correlate of the perceived loudness), and (e)
temporal aspects of speech (e.g., speech rate), as well as various combinations of
these aspects (e.g., prosodic features).”
http://www.scholarpedia.org/article/Speech_emotion_analysis
68. “Conversational Intelligence & Behavioral Prediction Insights from
Voice: Our Oliver engine offers ASR+ with a sophisticated layer of
emotion recognition metrics & behavioral KPIs, not only from what is
being said but also from the how it is said.”
69. NLP 2020: What Works and What's Next
Recent Advances in Natural Language Processing
Seth Grimes
Alta Plana Corporation
@SethGrimes
November 20, 2020