Neural Probabilistic Language Model (NPLM) introduced

Yoshua Bengio and colleagues published 'A Neural Probabilistic Language Model,' proposing a feed-forward neural network to learn distributed word representations (embeddings) and a joint probability function over sequences of words.

Significance

This paper was a foundational step, demonstrating that neural networks could learn continuous representations of words, capturing semantic and syntactic similarities, laying the groundwork for future embedding techniques like Word2Vec and ultimately the inputs to LLMs.