Methods Lab / NLP001

NLP: from language to research applications

Natural language processing (NLP) uses computational methods to work with human language. Systems use explicit rules or learn patterns from data to analyze, extract, predict, and generate information.

Large language models are one family of technologies within this field. [1]

The big picture

Visual notes
NLP study diagram covering language features, models, common tasks, speech analysis, and interview applications
NLP: from language to research applications

01Information in language

PerspectiveWhat to look forExample
Word structure and meaningHow words are formed and what they meanhappy → unhappy; “satisfied” versus “not satisfied”
Sentence structure and meaningRoles, evaluation targets, and contrasts“The explanation was clear, but the wait was too long” evaluates two things differently
Context and intentReferences across sentences and the purpose of an utterance“These instructions are confusing” may be a request for clarification

These perspectives help explain language; they are not mandatory sequential stages in every model. [1][2]

Conceptual illustration of morphology, syntax, semantics, and pragmatics
Language structure and context

A conceptual illustration, not a fixed architecture inside a model. NLU and NLG need not follow strictly inverse pipelines, and context matters across perspectives.

02Speech analysis: how something is said

CueWhat it captures
LoudnessHow loud or soft the voice is, and how it changes
Speaking rateHow quickly or slowly someone speaks
DeliveryIntonation, stress, pauses, and related patterns

Interpret acoustic and prosodic cues alongside the words and the situation. A plain transcript usually does not preserve all of them; analysis needs audio or the relevant acoustic features. Speech and text analysis can be combined, but measuring vocal features is different from interpreting linguistic content. [3]

03Common tasks

TaskThe question it addresses
Sentiment analysisWhat is being evaluated positively, negatively, or in mixed terms?
Emotion cue recognitionWhat feelings are expressed or implied? A cue is not a clinical diagnosis
Information extractionWhich themes, entities, or events should become fields or labels linked to the source?
SummarizationWhat are the main points of an interview, meeting, or body of material? Preserve important contrasts and uncertainty
Translation and question answeringHow can information be expressed in another language, or used to answer a question?

One passage can support several tasks.

“The explanation was clear, but the wait was too long.”

Sentiment analysis

Praise for the explanation; frustration with the wait

Information extraction

Explanation quality and waiting experience

Summarization

Preserve both judgments

Summarization concerns the key content, while speech analysis examines vocal cues. A workflow can use both.

04My perspective & use case

My starting point

Language itself makes NLP more approachable. Connecting words, sentences, and context to specific tasks helps me understand the broader framework.

My research direction

I have worked with interviews by manually marking passages and extracting keywords. I want to explore NLP-assisted organization and summaries of participants’ main points.

  1. Research question
  2. Information needed
  3. Fields or labels
  4. Source check

Usefulness depends on omissions, label quality, and time saved after corrections.

05Handwritten notes

A working note on language features, common tasks, and vocal expression.

Original bilingual handwritten NLP notes on models, language, sentiment, speech, and text tasks
Handwritten notes on NLP

06References

  1. Jurafsky & Martin — Speech and Language Processing
  2. Words and Tokens
  3. audEERING — Prosody & speech features
Further readingTang et al. (2023), evaluating medical evidence summarization ↗

Its findings concern particular models and a specific task; they do not validate an interview-analysis workflow.

Open original ↗