Let's now turn to the use of summarization
in question answering. The goal of
summarization is to produce an abridged
version of the text that contains
information that's important to or
relevant for a user, a particular user
need. And so that might mean abstracting
any kind of document or article,
summarizing email threads or meetings,
simplifying text, we'll talk about
compressing sentences. And we can talk
about summarization in two ways. Single
document summarization. Given a single
document, we're gonna produce an abstract
or an outline, perhaps a headline, a very
short summary of a document. In multiple
document summarization, we're given a
group of documents, presumably related
documents, and our job is to produce the
gist of these documents. So if we have
some news stories on the same event, we
might summarize the event by picking
information from different documents. And
that could be true also for any kind of
set of web pages that are focused on some
topic or question. Now we distinguish
between generic summarization and
query-focused summarization. Generic
summarization is what I've talked about so
far. We have some document, or some set of
documents, and our job is just to build a
summary. Query-focused summarization is
summarizing a document with respect to the
information need the user expresses by
their query. So you can think of
query-focused summarization as just
another kind of complex question
answering. We're answering a question by
summarizing a document that has the
information in it to construct the answer
that the user needs. Now we've all seen
query focused summaries, because that's
what search engines use to show you
information about a page. So for example,
Google will give you 156 characters about
26 words for each page as a summary of the
page. So if I've asked a question to
Google, what is die brücke, I get,
let's say these three URLs back. We have
that title of the URL, the URL, and then
some text. And that text, that snippet, is
some kind of summary of the page that
helps the user understand what's in the
page. So we can think of summarization in
general, of single documents, as
generating things like snippets. And we're
going to talk about the more general task
other than specifically just snippets for
web search, but you can think of these
snippets as a characteristic example.
Now where a snippet is the answer to a
question by taking information from a
single document, we often want the answer
from multiple documents. So creating
answers to complex questions that involves
summarizing from multiple documents, we're
gonna create a cohesive answer that
combines information from each of these
documents. That's multiple document
question answering. Now we can think of two
ways of doing summarization. In
extractive summarization we create a
summary by taking particular words or
phrases that are in the document and
building a summary just out of those words
or phrases. And a snippet from a search
engine like Google is an extractive
summary in this way. By contrast an
abstractive summary is one in which we
create our own words, different words than
are in the text, to summarize the content
of the text. And, we're going to be talking
completely about extractive summarization
today. Abstractive summarization is an
important research goal, but very
difficult. And one thing to think about
whenever we're talking about summarizing
from a document, whether it's a web page
or anything else, is what our baselines
are for summarization. And good writers
often put their ideas right at the
beginning, in the title or in the first
sentence. So a simple baseline, whenever
we're measuring any kind of summarization
algorithm is just taking the first
sentence. So, for example, in this Google
query: what is Die Brücke, if we take
the output from this first hit and we
look at this sentence Die Brücke was a
group of German expressionist artists
formed in Dresden and so on. Let's look at
this page where the snippet comes from.
And we can see that this snippet is really
just the first 156 characters of this
page. So sometimes the best snippet is
really just the beginning. And so we're
going to use that not only as a baseline
but later we'll see that that's a feature
we could use in different kinds of
summarization algorithms. We've
introduced the task of natural language
generation, producing shorter abstracts or
summaries or even headlines from a
document. And we've talked about query
focused summarization, where we use
summarization to answer a particular
question. We build a summary of a document
that is specifically designed to answer a
question posed by the user. And we've
talked about single and multiple document
summarization. And now we'll see the
details of how to do each of these tasks
in the further lectures.