Google Semantic Reactor - Revision history

BPeat: Text replacement - "* Conversational AI ... ChatGPT | OpenAI ... Bing | Microsoft ... Bard | Google ... Claude | Anthropic ... Perplexity ... You ... Ernie | Baidu" to "* Conversational AI ... [[C...

2024-03-16T15:49:24Z

BPeat at 03:04, 6 December 2023

2023-12-06T03:04:30Z

BPeat at 15:33, 9 October 2023

2023-10-09T15:33:49Z

BPeat at 23:11, 3 September 2023

2023-09-03T23:11:04Z

BPeat at 00:56, 3 September 2023

2023-09-03T00:56:09Z

BPeat at 20:11, 28 April 2023

2023-04-28T20:11:54Z

BPeat: Text replacement - "http:" to "https:"

2023-03-28T20:44:29Z

Text replacement - "http:" to "https:"

BPeat at 13:16, 17 March 2023

2023-03-17T13:16:53Z

BPeat at 01:47, 7 February 2023

2023-02-07T01:47:47Z

BPeat at 16:21, 19 March 2022

2022-03-19T16:21:19Z

@@ Line 19: / Line 19: @@
 * [[Google]] offerings
 * [[Large Language Model (LLM)]] ... [[Natural Language Processing (NLP)]]  ...[[Natural Language Generation (NLG)|Generation]] ... [[Natural Language Classification (NLC)|Classification]] ...  [[Natural Language Processing (NLP)#Natural Language Understanding (NLU)|Understanding]] ... [[Language Translation|Translation]] ... [[Natural Language Tools & Services|Tools & Services]]
-* [[Conversational AI]] ... [[ChatGPT]] | [[OpenAI]] ... [[Bing]] | [[Microsoft]] ... [[Bard]] | [[Google]] ... [[Claude]] | [[Anthropic]] ... [[Perplexity]] ... [[You]] ... [[Ernie]] | [[Baidu]]
+* [[Conversational AI]] ... [[ChatGPT]] | [[OpenAI]] ... [[Bing/Copilot]] | [[Microsoft]] ... [[Gemini]] | [[Google]] ... [[Claude]] | [[Anthropic]] ... [[Perplexity]] ... [[You]] ... [[phind]] ... [[Ernie]] | [[Baidu]]
 * [[Semantic Search]]
 * [[Papers Search]]

@@ Line 80: / Line 80: @@
 * Chef
-The game is built as an [https://angular.io/ Angular] app in [https://www.typescriptlang.org/ TypeScript]. The machine learning model uses a [[Javascript]] implementation of the [https://github.com/tensorflow/tfjs-models/tree/master/universal-sentence-encoder Universal Sentence Encoder lite], which it preloads using [https://www.json.org/ JSON] files that were generated from comma-separated values (CSV) files (butler.csv, maid.csv, chef.csv) for each of the characters (see generate_models.js).
+The game is built as an [https://angular.io/ Angular] app in [https://www.typescriptlang.org/ TypeScript]. The machine learning model uses a [[JavaScript]] implementation of the [https://github.com/tensorflow/tfjs-models/tree/master/universal-sentence-encoder Universal Sentence Encoder lite], which it preloads using [https://www.json.org/ JSON] files that were generated from comma-separated values (CSV) files (butler.csv, maid.csv, chef.csv) for each of the characters (see generate_models.js).
 The game works by matching a representation of the player's input to precomputed representations of candidate strings and calculates a similarity score. For example, if the player types "Where'd the diamond go?", the game might determine that it has a similarity of 0.86 to "Where is the diamond?", and if that's a greater score than the other candidates, the game will use that as the question to the bot and return the corresponding response.

@@ Line 20: / Line 20: @@
 * [[Large Language Model (LLM)]] ... [[Natural Language Processing (NLP)]]  ...[[Natural Language Generation (NLG)|Generation]] ... [[Natural Language Classification (NLC)|Classification]] ...  [[Natural Language Processing (NLP)#Natural Language Understanding (NLU)|Understanding]] ... [[Language Translation|Translation]] ... [[Natural Language Tools & Services|Tools & Services]]
 * [[Conversational AI]] ... [[ChatGPT]] | [[OpenAI]] ... [[Bing]] | [[Microsoft]] ... [[Bard]] | [[Google]] ... [[Claude]] | [[Anthropic]] ... [[Perplexity]] ... [[You]] ... [[Ernie]] | [[Baidu]]
 * [[Papers Search]]
 * [https://opensource.googleblog.com/ Semantic Reactor: A tool for experimenting with NLU models | B. Pietrzak, S. Pucci, & A. Cohen — Google AI]

@@ Line 2: / Line 2: @@
 |title=PRIMO.ai
 |titlemode=append
-|keywords=artificial, intelligence, machine, learning, models, algorithms, data, singularity, moonshot, Tensorflow, Google, Nvidia, Microsoft, Azure, Amazon, AWS
+|keywords=ChatGPT, artificial, intelligence, machine, learning, GPT-4, GPT-5, NLP, NLG, NLC, NLU, models, data, singularity, moonshot, Sentience, AGI, Emergence, Moonshot, Explainable, TensorFlow, Google, Nvidia, Microsoft, Azure, Amazon, AWS, Hugging Face, OpenAI, Tensorflow, OpenAI, Google, Nvidia, Microsoft, Azure, Amazon, AWS, Meta, LLM, metaverse, assistants, agents, digital twin, IoT, Transhumanism, Immersive Reality, Generative AI, Conversational AI, Perplexity, Bing, You, Bard, Ernie, prompt Engineering LangChain, Video/Image, Vision, End-to-End Speech, Synthesize Speech, Speech Recognition, Stanford, MIT |description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools
 |description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools
 }}
 [https://www.youtube.com/results?search_query=Google+Semantic+Reactor Youtube search...]

@@ Line 10: / Line 10: @@
 * [[Google]] offerings
 * [[Large Language Model (LLM)]] ... [[Natural Language Processing (NLP)]]  ...[[Natural Language Generation (NLG)|Generation]] ... [[Natural Language Classification (NLC)|Classification]] ...  [[Natural Language Processing (NLP)#Natural Language Understanding (NLU)|Understanding]] ... [[Language Translation|Translation]] ... [[Natural Language Tools & Services|Tools & Services]]
 * [[Papers Search]]
 * [https://opensource.googleblog.com/ Semantic Reactor: A tool for experimenting with NLU models | B. Pietrzak, S. Pucci, & A. Cohen — Google AI]

@@ Line 5: / Line 5: @@
 |description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools
 }}
-[http://www.youtube.com/results?search_query=Google+Semantic+Reactor Youtube search...]
+[https://www.youtube.com/results?search_query=Google+Semantic+Reactor Youtube search...]
-[http://www.google.com/search?q=Google+Semantic+Reactor ...Google search]
+[https://www.google.com/search?q=Google+Semantic+Reactor ...Google search]
 * [[Google]] offerings
 * [[Natural Language Tools & Services]]
 * [[Papers Search]]
-* [http://opensource.googleblog.com/ Semantic Reactor: A tool for experimenting with NLU models | B. Pietrzak, S. Pucci, & A. Cohen — Google AI]
+* [https://opensource.googleblog.com/ Semantic Reactor: A tool for experimenting with NLU models | B. Pietrzak, S. Pucci, & A. Cohen — Google AI]
-* [http://venturebeat.com/2020/03/27/google-releases-semantic-reactor-for-natural-language-understanding-experimentation/ Google releases Semantic Reactor for natural language understanding experimentation | Kyle Wiggers - VentureBeat]
+* [https://venturebeat.com/2020/03/27/google-releases-semantic-reactor-for-natural-language-understanding-experimentation/ Google releases Semantic Reactor for natural language understanding experimentation | Kyle Wiggers - VentureBeat]
-* [http://research.google.com/semanticexperiences/for-developers.html Semantic Experiences for Developers] based on fully learned end-to-end models that can be used for a wide variety of natural language understanding applications.
+* [https://research.google.com/semanticexperiences/for-developers.html Semantic Experiences for Developers] based on fully learned end-to-end models that can be used for a wide variety of natural language understanding applications.
-* [http://github.com/tensorflow/tfjs-models/tree/master/universal-sentence-encoder Universal Sentence Encoder lite] a model that encodes text into 512-dimensional embeddings. These embeddings can then be used as inputs to natural language processing tasks such as sentiment classification and textual similarity analysis. This module is a [[TensorFlow.js]]
+* [https://github.com/tensorflow/tfjs-models/tree/master/universal-sentence-encoder Universal Sentence Encoder lite] a model that encodes text into 512-dimensional embeddings. These embeddings can then be used as inputs to natural language processing tasks such as sentiment classification and textual similarity analysis. This module is a [[TensorFlow.js]]
 A tool for experimenting with [[Natural Language Processing (NLP) | natural language understanding (NLU)]] models via a [[Google Sheets]] add-on that allows the user to sort lines of text in a sheet using a variety of machine-learning models.  Beyond ranking lists, Semantic Reactor can help write dialog for a [[Assistants#Chatbot | Chatbot]], such as a customer service [[Assistants#Chatbot | Chatbot]], using semantic similarity. Specifically, it can quickly add new question/answer pairs and test different phrasings, enabling developers to see how the model reacts to them. Semantic Reactor can also search through text using input-response, meaning it can examine a list of potential responses and rank each according to which the model thinks is the most likely. In input-response mode, the model predicts the most conversational response to an input, and in semantic similarity mode, it returns the answer that’s semantically closest to the input.
-http://venturebeat.com/wp-content/uploads/2020/03/pasted-image-0-2.png
+https://venturebeat.com/wp-content/uploads/2020/03/pasted-image-0-2.png
 === Why use the Semantic Reactor? ===
@@ Line 55: / Line 55: @@
 = Mystery of the Three Bots =
-* [http://github.com/google/mysteryofthreebots Mystery of the Three Bots GitHub]
+* [https://github.com/google/mysteryofthreebots Mystery of the Three Bots GitHub]
-To dispel some of the intimidation of using [[Natural Language Processing (NLP) | natural language understanding (NLU)]], and to demonstrate how it can be easily used with pre-trained, generic models, [[Google]] has released a tool for creating dialog-based games, the Semantic Reactor, and open-sourced example code, [http://github.com/google/mysteryofthreebots The Mystery of the Three Bots] that allows you to experiment with machine-learned language models...
+To dispel some of the intimidation of using [[Natural Language Processing (NLP) | natural language understanding (NLU)]], and to demonstrate how it can be easily used with pre-trained, generic models, [[Google]] has released a tool for creating dialog-based games, the Semantic Reactor, and open-sourced example code, [https://github.com/google/mysteryofthreebots The Mystery of the Three Bots] that allows you to experiment with machine-learned language models...
-This simple dialog-based game is an example of using a machine-learning model inside of a web application. The model it uses is called [http://github.com/tensorflow/tfjs-models/tree/master/universal-sentence-encoder Universal Sentence Encoder lite] and is available at [[Tensorflow Hub]].  To learn more, go to the [http://cloud.google.com/ai-workshop Google Cloud AI Workshop] Page.
+This simple dialog-based game is an example of using a machine-learning model inside of a web application. The model it uses is called [https://github.com/tensorflow/tfjs-models/tree/master/universal-sentence-encoder Universal Sentence Encoder lite] and is available at [[Tensorflow Hub]].  To learn more, go to the [https://cloud.google.com/ai-workshop Google Cloud AI Workshop] Page.
-* [http://google.github.io/mysteryofthreebots/ Play Here] <<<<<<<<
+* [https://google.github.io/mysteryofthreebots/ Play Here] <<<<<<<<
-[http://google.github.io/mysteryofthreebots/ Mystery of the Three Bots] is a simple dialog-based game utilizing machine learning to enable you to communicate with three characters. The goal is to determine which of several guests stole the precious MacGuffin Diamond. You interrogate three robot servants who were present during the crime:
+[https://google.github.io/mysteryofthreebots/ Mystery of the Three Bots] is a simple dialog-based game utilizing machine learning to enable you to communicate with three characters. The goal is to determine which of several guests stole the precious MacGuffin Diamond. You interrogate three robot servants who were present during the crime:
 * Butler
@@ Line 69: / Line 69: @@
 * Chef
-The game is built as an [http://angular.io/ Angular] app in [http://www.typescriptlang.org/ TypeScript]. The machine learning model uses a [[Javascript]] implementation of the [http://github.com/tensorflow/tfjs-models/tree/master/universal-sentence-encoder Universal Sentence Encoder lite], which it preloads using [http://www.json.org/ JSON] files that were generated from comma-separated values (CSV) files (butler.csv, maid.csv, chef.csv) for each of the characters (see generate_models.js).
+The game is built as an [https://angular.io/ Angular] app in [https://www.typescriptlang.org/ TypeScript]. The machine learning model uses a [[Javascript]] implementation of the [https://github.com/tensorflow/tfjs-models/tree/master/universal-sentence-encoder Universal Sentence Encoder lite], which it preloads using [https://www.json.org/ JSON] files that were generated from comma-separated values (CSV) files (butler.csv, maid.csv, chef.csv) for each of the characters (see generate_models.js).
 The game works by matching a representation of the player's input to precomputed representations of candidate strings and calculates a similarity score. For example, if the player types "Where'd the diamond go?", the game might determine that it has a similarity of 0.86 to "Where is the diamond?", and if that's a greater score than the other candidates, the game will use that as the question to the bot and return the corresponding response.
 === How it Works ===
-[http://google.github.io/mysteryofthreebots/ The Mystery of the Three Bots] was created using machine learning and natural language understanding.
+[https://google.github.io/mysteryofthreebots/ The Mystery of the Three Bots] was created using machine learning and natural language understanding.
 A deep-learning model, trained on billions of lines of conversation, enables players to talk to the robots through a technique called "semantic matching," sometimes called "fuzzy matching."

@@ Line 16: / Line 16: @@
 * [http://github.com/tensorflow/tfjs-models/tree/master/universal-sentence-encoder Universal Sentence Encoder lite] a model that encodes text into 512-dimensional embeddings. These embeddings can then be used as inputs to natural language processing tasks such as sentiment classification and textual similarity analysis. This module is a [[TensorFlow.js]]
-A tool for experimenting with [[Natural Language Processing (NLP) | natural language understanding (NLU)]] models via a [[Google Sheets]] add-on that allows the user to sort lines of text in a sheet using a variety of machine-learning models.  Beyond ranking lists, Semantic Reactor can help write dialog for a chatbot, such as a customer service chatbot, using semantic similarity. Specifically, it can quickly add new question/answer pairs and test different phrasings, enabling developers to see how the model reacts to them. Semantic Reactor can also search through text using input-response, meaning it can examine a list of potential responses and rank each according to which the model thinks is the most likely. In input-response mode, the model predicts the most conversational response to an input, and in semantic similarity mode, it returns the answer that’s semantically closest to the input.
+A tool for experimenting with [[Natural Language Processing (NLP) | natural language understanding (NLU)]] models via a [[Google Sheets]] add-on that allows the user to sort lines of text in a sheet using a variety of machine-learning models.  Beyond ranking lists, Semantic Reactor can help write dialog for a [[Assistants|chatbot]], such as a customer service [[Assistants|chatbot]], using semantic similarity. Specifically, it can quickly add new question/answer pairs and test different phrasings, enabling developers to see how the model reacts to them. Semantic Reactor can also search through text using input-response, meaning it can examine a list of potential responses and rank each according to which the model thinks is the most likely. In input-response mode, the model predicts the most conversational response to an input, and in semantic similarity mode, it returns the answer that’s semantically closest to the input.
 http://venturebeat.com/wp-content/uploads/2020/03/pasted-image-0-2.png