GotAI.NET

Форум: Проблемы искусственного интеллекта

 

Регистрация | Вход

 Все темы | Новая тема Стр.1 (1)   Поиск:  
 Автор Тема: Salesforce
Ilya Geller
Сообщений: 4884
Salesforce
Добавлено: 25 фев 20 12:08
Salesforce’s AI navigates Wikipedia to find answers to complex questions

Wikipedia offers a wealth of knowledge on countless topics to those who know where to look, but therein lies the rub — navigating its database of over 6 billion articles requires some web-crawling finesse. In an effort to streamline the search, researchers at Salesforce developed what they call a graph-based trainable retriever-reader framework, which sequentially retrieves paragraphs from English Wikipedia articles to answer complex open-domain questions.
https://venturebeat.com/2020/02/25/salesforces-ai-navigates-wikipedia-to-find-answers-to-complex-questions/
[Ответ][Цитата]
Ilya Geller
Сообщений: 4884
На: Salesforce
Добавлено: 25 фев 20 12:15
Вообще-то такой подход не очень честен: Wiki это сорт словаря, хорошо проиндексированный. Найти там нужное не представляет труда...
[Ответ][Цитата]
Ilya Geller
Сообщений: 4884
На: Salesforce
Добавлено: 11 мар 20 18:34
Очень здорово! Параграфы и все такое! Но текстуальный поиск не работает без синонимов, надо понять что такое синонимы для аминокислот.
It’s a technique unlike that of DeepMind’s AlphaFold, which estimates the distances between amino acids pairs and their angles and uses the estimations to generate protein fragments, or MIT CSAIL’s system, which learns to predict how similar protein structures are likely to be from pairs of proteins and embeddings (i.e., mathematical representations) of their sequences. By contrast, ProGen approaches protein generation from a natural language perspective: It treats amino acids as words in a paragraph (in this case, a protein).
https://venturebeat.com/2020/03/11/salesforces-progen-trained-on-280-million-amino-acid-sequences-to-learn-to-generate-proteins/
[Ответ][Цитата]
Ilya Geller
Сообщений: 4884
На: Salesforce
Добавлено: 13 мар 20 13:35
Salesforce весьма серьезно:
https://trailhead.salesforce.com/en/content/learn/modules/einstein_intent_basics/einstein_intent_basics_prep
Take this sentence, for example: They are visiting relatives. That sentence could mean that they have gone to visit relatives or that they are relatives who are visiting. A human can read that sentence in context and understand what it means. Deep learning applied to NLP means that now computers can understand language subtlety that it was previously unable to. Given the context of a sentence, computers can now correctly interpret ambiguous grammar.

Осталось дождаться пока они поймут что нужно использовать подтексты, то есть словарные определения.
Также они не понимают что эмоции это в первую очередь синонимичные кластеры из других текстов и те же самые подтексты.
[Ответ][Цитата]
Ilya Geller
Сообщений: 4884
На: Salesforce
Добавлено: 08 май 20 17:08
Morphological analysis—Breaking down complex words into their components to better understand their meaning.
For example, you can break down “incomprehensible” into its component parts.
“in”—not
“comprehens”—to understand or comprehend
“ible”—indicates that this word is an adjective, describing whether something can be comprehended
Syntactic analysis—Trying to understand the structure of sentences by looking at how the words work together. This step is like diagramming a sentence, where you identify the role each word is playing in the sentence.
Semantic interpretation—Working out the meaning of a sentence by combining the meaning of individual words with their syntactic roles in the sentence.
Discourse processing—Understanding the context around a sentence to fully process what it means.
https://trailhead.salesforce.com/en/content/learn/modules/deep-learning-and-natural-language-processing/start-with-nlp
[Ответ][Цитата]
Ilya Geller
Сообщений: 4884
На: Salesforce
Добавлено: 08 май 20 17:11
Einstein Intent—The Einstein Intent API categorizes unstructured text into user-defined labels to better understand what users are trying to accomplish. Use this API to analyze text from emails, chats, or web forms to:
Determine which products prospects are interested in, and send customer inquiries to the appropriate sales person.
Route service cases to the correct agents or departments, or provide self-service options.
Understand customer posts to provide personalized self-service in your communities.
Einstein Sentiment—The Einstein Sentiment API classifies text into positive, negative, and neutral classes to understand what the words people use can tell us about how they’re feeling. Use this API to analyze emails, social media, and text from chat to:
Identify the sentiment or emotion in a prospect’s emails to trend a lead or opportunity up or down.
Provide proactive service by helping dissatisfied customers first or extending promotional offers to satisfied customers.
Monitor how people perceive your brand across social media channels, identify brand evangelists, and note customer satisfaction.
https://trailhead.salesforce.com/en/content/learn/modules/einstein_intent_basics/einstein_intent_basics_prep
[Ответ][Цитата]
Ilya Geller
Сообщений: 4884
На: Salesforce
Добавлено: 18 июн 20 18:12
Ну наконец! Salesfoce поняло где собака зарыта и что громкими лозунгами не проживешь:

Salesforce Research develops COVID-19 search engine
https://www.techrepublic.com/article/salesforce-research-develops-covid-19-search-engine/
[Ответ][Цитата]
Ilya Geller
Сообщений: 4884
На: Salesforce
Добавлено: 21 июн 20 17:54
With deep experience in natural language processing (NLP), Salesforce Research pulled together a team of experts to develop a search engine that would support research efforts as more information pours into public archives. Within a few months, Salesforce Research developed COVID-19 Search to help users search through rigorous scientific information in their efforts to stem the tide of the global pandemic.
[Ответ][Цитата]
Ilya Geller
Сообщений: 4884
На: Salesforce
Добавлено: 25 июн 20 9:05
Salesforce integrates chat, text and video collaboration into a desktop interface and a new mobile app, Salesforce Anywhere. It tracks and logs conversations and transcribes videos.
https://searchcustomerexperience.techtarget.com/news/252485170/Salesforce-collaboration-gets-mobile-boost-with-new-app
[Ответ][Цитата]
Ilya Geller
Сообщений: 4884
На: Salesforce
Добавлено: 26 июл 20 14:08
https://www.salesforce.com/blog/2019/09/introducing-einstein-search.html

Personalized results for every user


Salespeople and service agents rely on Salesforce as their single source of truth for customer information. This is why we made sure that Einstein Search had the ability to return personalized results for every user. Each search result is tailored to what matters at your company and how you work as an individual. For example, if a sales representative covers accounts in the Northeast in the Financial Services vertical, Einstein Search will learn that and show them more of what matters to them. Under the hood, Einstein Search leverages innovative data mining and machine learning techniques to personalize search results, all while keeping specific user information anonymized.

Говорил? Свобода! Скоро никакой слежки на Интернете!
[Ответ][Цитата]
 Стр.1 (1)