CS PAPERS DEEP-READ · PAPER 9

Jointly Learning to Align and Translate (Bahdanau Attention)

Bahdanau, Cho & Bengio · ICLR 2015

中文 →

What did this paper do?

In late 2014, three researchers — Bahdanau, Cho, and Bengio — gave machine translation a new organ: attention. It lets the model, while translating each word, glance back at the most relevant words in the source sentence. The "attention" you hear about every day in ChatGPT and large-model news traces its bloodline straight back here — this paper is attention's birth certificate.

First, a puzzle

The previous paper, Seq2Seq, translated by "first understand, then re-say": read the whole English sentence, compress it onto one small sticky note, then write out the French from that note alone. Fine for short sentences; the moment sentences got long, quality fell off a cliff. No wonder — take a 60-word passage, allow yourself one sticky note, and try to reproduce every detail from it. Impossible. The strange part: human translators never work this way. Nobody memorizes a whole paragraph before writing; everyone reads as they translate.

What's new

This paper says: stop memorizing — let the model read as it translates too. While producing each word, the source text lies open on the desk, free to be consulted at any moment. The sticky note's single-plank bridge is torn down and replaced by the original text, always at hand.

How it works

Before writing each output word, the model takes its current thought — "where am I in the translation?" — and makes eye contact with every word of the source, one by one: each gets a relevance score. High scorers get a long look; low scorers just peripheral vision. Its gaze works like a spotlight — a bright spot plus dimmer surroundings — and in exactly those proportions it blends information from across the source into one custom reference, then writes. The best part: nobody taught it where to look. The model picked that up on its own, as a by-product of learning to translate — after training, its gaze lands on the right corresponding words, and where English and French swap word order, the gaze visibly criss-crosses back and forth.

What it brought

The immediate win: long sentences stopped collapsing, and neural translation matched the old statistical systems that had ruled for twenty years, for the first time. The deeper win: it proved that "look things up as needed" beats "memorize once." Three years later, Google's Transformer paper declared "attention is all you need," threw away every other part and kept only this trick — and the large-model era began. One honest note: this version of attention still sat on the old word-by-word engine, and every output word required scanning the whole source again — slow and hard to parallelize. That bill was settled three years later, by the Transformer.

Remember one thing

Don't compress the whole sentence onto one sticky note and recite from it — let the translator glance back at the source for every word it writes, allocating its gaze by relevance. That gaze is where the attention mechanism began, and it's what beats inside the heart of every large model today.

Want the three-step formula, the architecture diagram, and the BLEU numbers? → switch to the deep read