natural language processing
A field of machine learning focused on enabling computers to understand and analyze human language text, used here to reconstruct sentences and extract sentiment from digitized documents
As defined in Melissa Dell
Where it comes up · 12
- 151 | Jordan Ellenberg on the Mathematics of Political Boundaries3 claims
- The Three Body Portfolio2 claims
- The Long Game: A Conversation with Robert Waldinger (Episode #308)1 claim
- Stephen Wolfram's Take on Artificial Intelligence & The Future of Humanity1 claim
- Melissa Dell1 claim
- Melanie Mitchell on Artificial Intelligence1 claim
- 308 - The Long Game1 claim
- Amjad Masad - The Future of Software Creation - [Invest Like the Best, EP.310]1 claim
and 4 more
Most important claims · 10 of 15Search all claims for “natural language processing” →
- Self-report is limited both by what people can tell us—because we are blind to so much about ourselves—and by what they are willing to tell us, since we present ourselves in flattering lights; this can be partly circumvented by reading non-explicit signals like tone of voice and word choice via natural language processing.308 - The Long Game
- Longitudinal text analysis of the Stormfront neo-Nazi forum shows that as users interact over time, their language shifts from individual self-reference ('I', 'my') to collective identity markers ('we', 'us'/'Stormfront'), evidencing that the community reshapes individual identity into a collective one.330 | Petter Törnberg on the Dynamics of (Mis)Information
- Beyond literal self-report content, researchers can use natural language processing and AI to analyze tone of voice and word choice to infer aspects of mental state that subjects may not consciously articulate.The Long Game: A Conversation with Robert Waldinger (Episode #308)
- Watson did not 'know' a lot of things so much as it could rapidly look up information on Wikipedia and large databases plus use some natural-language processing to parse Jeopardy questions; its abilities did not transfer to medicine as IBM marketed, and the Jeopardy-winning Watson effectively no longer exists, replaced by a rebranded platform of standard deep-learning tools.Melanie Mitchell on Artificial Intelligence
- The 2017 invention of the transformer architecture was a key breakthrough because it proved remarkably efficient and scalable; since then most progress has come not from better architectures but from sheer engineering scaling of transformer-based networks trained on large text corpora.230 | Raphaël Millière on How Artificial Intelligence Thinks
- Artificial intelligence and machine learning will not make regressions on structured price and volume data run faster or find arbitrage that is vanishing in time and price, because historical structured data does not reveal stable patterns.The Three Body Portfolio
- Markov demonstrated his chains by treating Pushkin's Eugene Onegin as a string of consonants and vowels and computing transition probabilities, a modern computational-style reduction to bits that distinguished it from a different Russian author's text—a precursor to today's natural language processing.151 | Jordan Ellenberg on the Mathematics of Political Boundaries
- Early machine learning for code was primitive because researchers missed that code is very similar to natural language, so applying advanced natural language processing methods to programming was the key insight that unlocked AI for code.Amjad Masad - The Future of Software Creation - [Invest Like the Best, EP.310]
- A memoryless Markov chain can incorporate memory by enlarging the definition of a state—for example, running the chain on three-letter strings rather than single letters, where each step lops off the first letter and appends a new one—which underlies how language-prediction systems extend basic Markov models.151 | Jordan Ellenberg on the Mathematics of Political Boundaries
- The most promising source of public-market alpha is capturing behavioral patterns through natural language processing applied to unstructured text, because AI cannot speed up regressions on structured price data but can reveal how narratives shape investor behavior.The Three Body Portfolio