Meet Musio

Deep Reinforcement Learning

Goal In this week’s summary we introduce the basic concepts behind reinforcement learning and some ways it is applied in very controlled environments. Motivation Reinforcement learning methods recently experienced a hype through AlphaGo ranking next to the best human Go players. Furthermore the complexity of Go might ease the transfer of reinforcement learning to very large NLP tasks like dialog handling. Ingredients Markov Decision Process, exploration and exploitation, policy, Monte Carlo Tree Search, Q-Learning Steps Reinforcement Learning is usually applied to tasks, where an environment is partially observable and a certain action has to be taken. The influence on the state of the environment results in a backreaction in form of some reward. Any kind of game basically fits the […]

Seminar on Research related to NLP

For more info: Research-presentation-related-in-NLP This seminar was presented by Ash. The summary of this seminar is as follows.   ***Peeking Into The Seminar***   This seminar was about large Corpus-based automatic grammar rules and export methods for information. There are two types.   1. Edit : A broad-coverage grammar checker using grammar pattern recognition.   example)     2. Information extraction from Web-scale N-gram data example) is(Laden, terrorist) – two words are connected with ‘is’ partOf(Laden,zihard) – a word connotes another word in two words hasProperty(Laden,cruelty) – a word modifies the other word in two words.     For editing purposes, as the real purpose of this is editing sentences, it is used to edit a user’s sentences by exporting accurate […]