How deeply does Building LLM Applications with DSPy cover extractive summarization?

Defines passage selection and discusses coherence, relevance, and readability, but gives no extraction algorithm.

Extractive summarization

As explained in Building LLM Applications with DSPy

An extractive summary is a shortened text composed of passages selected from a source.

Extractive summarization builds a shorter text by selecting passages from the source and joining them. The passages should be relevant, concise, coherent out of context, and the finished summary readable. section 8.1.1

Its central trade-offs are:

Joined passages may jump between topics or fail to flow smoothly. section 8.1.1
Compared with abstractive summaries, extractive summaries retain source wording, while abstractive summaries can be more readable but may introduce inaccuracies. section 8.1.1

How Building LLM Applications with DSPy covers it

Cover of Building LLM Applications with DSPy

liveBook manning.com

Read Building LLM Applications with DSPy on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Starting Data Analytics with Generative AI and PythonExtractive summarization creates a summary by selecting and combining important sentences, terms, or other passages from the source text.
liveBook manning.com

Natural Language Processing in Action, Second EditionExtractive summarization creates a summary by selecting and arranging passages or sentences from the source document.
liveBook manning.com

Effective Conversational AIExtractive summarization is a summarization technique that constructs a shorter representation by selecting or extracting information from source content.

Compare how 4 books explain extractive summarization →

Related concepts

summarizationkind of · Summarization is the process of condensing source content into a shorter representation that preserves its important information or meaning.
abstractive summarizationcontrasts with · Abstractive summarization produces a concise account of source information using newly composed wording rather than only selecting text from the source.
generationkind of · Generation is the computational production of outputs from supplied inputs or context, often by applying a model to produce predictions or new content.
retrieved documentproduces · A retrieved document is information selected by an information-retrieval process from a source and supplied as context or evidence for a query or task.

This explainer was generated by Manning's knowledge graph from the text of Building LLM Applications with DSPy. The section links point to the parts of the book it draws on.