テキスト要約
長文をより短く、かつ正確な形に縮める
本ページの本文は英語で提供されています。タイトルと導入は日本語化されています。
この能力とは何か
Takes a long document and returns a shorter version that keeps the key information. It splits into extractive (selecting sentences) and abstractive (rewriting in new words) styles, the latter now dominant. Unlike free generation it has an explicit compression target, and unlike question answering it is not aimed at one query but should cover the whole thread.
技術的にどう実現するか
The classic approach is a sequence-to-sequence attention model producing abstractive summaries, with rewriting ability coming from large-scale pre-training. Long documents are usually handled hierarchically or by a map-reduce scheme that summarises chunks and then combines them. Controlled summarisation passes length, angle or audience constraints through the prompt or light fine-tuning to steer style.
代表的な製品
8GPT-4o
2024ネイティブにマルチモーダルな汎用モデル。テキスト・画像・音声をひとつの入口で扱う
Claude
2023長い文脈と安全性の調整で知られる汎用対話モデル
Gemini
2024検索・オフィス・マルチモーダルモデルを一つの対話入口に集約
NotebookLM
2023与えた資料だけを根拠に答え、出典を逐一示す
Kimi
2023長い文脈の処理を得意とする中国語の対話アシスタント
Apple Intelligence
2024端末とプライベートクラウドで分担する OS 級の AI 機能
Microsoft Copilot
2023対話型 AI を OS とオフィスソフトに組み込む
Perplexity
2022検索しながら答え、どの答えにも出典が付く
関連する組織
代表的な用途
- Quick reads of news and reports
- Meeting and call minutes
- Literature triage and paper skims
- Rolling summaries of tickets and email
どう評価するか
- ROUGE
- N-gram overlap with reference summaries
- BERTScore
- Semantic-embedding similarity, more tolerant than literal overlap
- Factual consistency
- Share of statements conflicting with the source, as in FactCC-style evaluation
限界と難しさ
- Middle sections of long documents are often dropped; models favour the start and end
- Abstractive models splice facts from different sentences into claims the source never made
- On ambiguous or multi-sided texts, minority views are often reported as the majority