Krabi, Thailand by Mo Baghdadi

⛵ Learning Meaning in Natural Language Processing — The Semantics Mega-Thread

In which Twitter talked about meaning, semantics, language models, learning Thai and Java, entailment, co-reference — all in one fascinating thread.

Thomas Wolf
Aug 7, 2018 · 7 min read
Full size image here

🏎 A crash course on Lexical Meaning & Semantics

Meaning is the information that a sender intends to convey, or does convey, to a receiver.

Meaning representation: 𝑚𝑎𝑥(𝚙𝚛𝚒𝚖𝚎𝚜 ∩(−∞; 𝟣𝟢))

🔥 Triggering a debate on Meaning

Can a model trained only on raw text learn meaning?

The Thai and Java Experiments

Investigating Programming Language Semantic

Language Models

Textual Entailment

An Inductive Bias Language Model

The Big Open Question



A word on Searle’s Chinese Room

HuggingFace

Stories @ Hugging Face

1.5K

1.5K claps
Thomas Wolf

Written by

Natural Language Processing, Deep learning and Computational Linguistics – Science Lead @Huggingface | thomwolf.io

HuggingFace

Stories @ Hugging Face