Zhanliang Liu — technologist, founder & CEO of FuSearch, focused on self-improving superintelligence (ASI), large language models, and intelligent information processing.https://zliu.org/https://zliu.org/post/chatgpt-the-dawn-of-a-new-era/https://zliu.org/post/chatgpt-the-dawn-of-a-new-era/On November 30, 2022, OpenAI released ChatGPT. In hindsight, that day may mark the beginning of the Fourth Industrial Revolution.Mon, 15 Jun 2026 00:00:00 GMThttps://zliu.org/post/universal-information-extraction/https://zliu.org/post/universal-information-extraction/UIE - a unified text-to-structure generation framework, which can universally model different IE tasks, adaptively generate targeted structures, and unfiedly learn general IE abilities from different knowledge sources.Wed, 03 Aug 2022 00:00:00 GMThttps://zliu.org/post/vector-search-engine/https://zliu.org/post/vector-search-engine/Vector search engines or vector databases are a core piece of infrastracture that fuels every big deep learning deployment in industry.Tue, 01 Mar 2022 00:00:00 GMThttps://zliu.org/post/qanlu-language-model-is-all-you-need/https://zliu.org/post/qanlu-language-model-is-all-you-need/One Amazon Alexa AI's new paper *Language Model Is All You Need* explores NLU problem as a QA problem. The original paper is on [arXiv](https://arxiv.org/abs/2011.03023).Tue, 12 Jan 2021 00:00:00 GMThttps://zliu.org/post/semantic-meaning/https://zliu.org/post/semantic-meaning/I found a very worthwhile article while surfing medium.com days ago. The article is a summary of a twitter thread which talked about meaning, semantics, language models, learning Thai and Java, entailment, co-reference — all in one fascinating thread. The original article is [here](https://medium.com/huggingface/learning-meaning-in-natural-language-processing-the-semantics-mega-thread-9c0332dfe28e).Thu, 15 Nov 2018 00:00:00 GMThttps://zliu.org/post/topk-in-stream/https://zliu.org/post/topk-in-stream/[Filtered-Space Saving](http://www.l2f.inesc-id.pt/~fmmb/wiki/uploads/Work/dict.refd.pdf) (FSS) is a data structure and algorithm combination useful for accurately estimating the top k most frequent values appearing in a stream while using a constant, minimal memory footprint.Mon, 25 Jun 2018 00:00:00 GMThttps://zliu.org/projects/pullword/https://zliu.org/projects/pullword/Pullword would be used in settings where only unlabelled text data is available.Sat, 16 Jun 2018 00:00:00 GMThttps://zliu.org/post/godels-first-incompleteness-theorem/https://zliu.org/post/godels-first-incompleteness-theorem/Gödel's incompleteness theorems are two theorems of mathematical logic that demonstrate the inherent limitations of every formal axiomatic system containing basic arithmetic. These results, published by [Kurt Gödel](https://en.wikipedia.org/wiki/Kurt_G%C3%B6del) in 1931, are important both in mathematical logic and in the philosophy of mathematics.Sun, 08 Apr 2018 00:00:00 GMThttps://zliu.org/post/weighted-random/https://zliu.org/post/weighted-random/The optimal solution for weighted random should be the [Alias Method](https://en.wikipedia.org/wiki/Alias_method). It requires $O(n)$ time to initialize, $O(1)$ time to make a selection, and $O(n)$ memory.Thu, 05 Apr 2018 00:00:00 GMThttps://zliu.org/projects/fmr/https://zliu.org/projects/fmr/A formal language for representing meaning and a system for semantic parsing.Fri, 16 Feb 2018 00:00:00 GMThttps://zliu.org/projects/gocc/https://zliu.org/projects/gocc/gocc is a golang port of OpenCC([Open Chinese Convert 開放中文轉換](https://github.com/BYVoid/OpenCC/)) which is a project for conversion between Traditional and Simplified Chinese developed by [BYVoid](https://www.byvoid.com/).Fri, 16 Feb 2018 00:00:00 GMThttps://zliu.org/post/logistic-map/https://zliu.org/post/logistic-map/A Python implementation for illustrating the behavior of logistic map.Thu, 15 Jun 2017 00:00:00 GMThttps://zliu.org/projects/ling/https://zliu.org/projects/ling/Toknization, Normalization, Lemmatization, Tagging etc.Thu, 27 Apr 2017 00:00:00 GMThttps://zliu.org/projects/goobot/https://zliu.org/projects/goobot/Goobot is a general multilingual web article extractor. It works without rules or training just as diffbot.com, and it is more than 10 times faster than diffbot.Wed, 27 Apr 2016 00:00:00 GMThttps://zliu.org/projects/knowledge-extraction/https://zliu.org/projects/knowledge-extraction/基于网页库的全球电话号码信息抽取Wed, 27 Apr 2016 00:00:00 GMThttps://zliu.org/post/linux-process-and-thread/https://zliu.org/post/linux-process-and-thread/Linux Threads vs Light Weight Processes.Sat, 11 Jul 2015 00:00:00 GMThttps://zliu.org/projects/web-crawling/https://zliu.org/projects/web-crawling/A flexible and high performance distributed crawler framework.Sat, 27 Apr 2013 00:00:00 GMT