Real Time Transcript Summarisation
According to an aspect there is provided a computer-implemented method for determining summaries of text over multiple batches of text. The method comprises: for each of a plurality of batches of text, each batch comprising text for addition to a cumulative document: adding the batch of text to the cumulative document to produce an updated cumulative document; encoding the updated cumulative document using an encoder neural network to obtain one or more encoder hidden states; inputting the one or more encoder hidden states and a cumulative summary that summarises each preceding batch of text into a decoder neural network to generate a summary for the batch of text; and updating the cumulative summary by adding the summary to the cumulative summary. The method further comprises outputting each summary.
1 . A computer-implemented method for determining summaries of text over multiple batches of text, the method comprising:
for each of a plurality of batches of text, each batch comprising text for addition to a cumulative document:
adding the batch of text to the cumulative document to produce an updated cumulative document;
encoding the updated cumulative document using an encoder neural network to obtain one or more encoder hidden states;
inputting the one or more encoder hidden states and a cumulative summary that summarises each preceding batch of text into a decoder neural network to generate a summary for the batch of text; and
updating the cumulative summary by adding the summary to the cumulative summary; and
outputting each summary.
2 . The method of claim 1 wherein the batches are obtained separately over time and each summary is generated in response to the obtaining of the corresponding batch.
3 . The method of claim 2 wherein, in response to each batch being obtained, the batch is immediately processed to determine a summary.
4 . The method of claim 1 further comprising generating each batch by receiving a sequence of text and grouping the sequence of text into batches.
5 . The method of claim 4 wherein each batch comprises:
a predetermined number of words;
a predetermined number of sentences;
a predetermined number of statements; or
a predetermined number of phrases.
6 . The method of claim 4 wherein the sequence of text is a transcript of a conversation between multiple people and each batch relates to a predetermined number of turns in conversation.
7 . The method of claim 1 wherein outputting each summary comprises one or more of:
outputting each summary separately;
outputting each cumulative summary separately; and
outputting each summary as part of a final cumulative summary comprising every summary for every batch of the plurality of batches.
8 . The method of claim 1 wherein, for a first batch of the plurality of batches, inputting the one or more encoder hidden states and a cumulative summary that summarises each preceding batch of text into a decoder neural network comprises inputting the context vector and a start of sequence token.
9 . The method of claim 1 wherein, for a first batch of the plurality of batches, adding the batch of text to the cumulative document to produce an updated cumulative document comprises setting the cumulative document to consist only of the first batch.
10 . The method of claim 1 wherein each generated summary ends with an end of sequence token, and wherein the end of sequence token is removed from the cumulative summary before the cumulative summary is input into the decoder.
11 . The method of claim 1 wherein each generated summary ends with an end of sequence token, and wherein the end of sequence token is removed from the cumulative summary before the cumulative summary is updated.
12 . A system for determining summaries of text over multiple batches of text, the system comprising one or more processors configured to:
for each of a plurality of batches of text, each batch comprising text for addition to a cumulative document:
add the batch of text to the cumulative document to produce an updated cumulative document;
encode the updated cumulative document using an encoder neural network to obtain one or more encoder hidden states;
input the one or more encoder hidden states and a cumulative summary that summarises each preceding batch of text into a decoder neural network to generate a summary for the batch of text; and
update the cumulative summary by adding the summary to the cumulative summary; and
output each summary.
13 . A non-transitory computer readable medium comprising computer executable instructions that, when executed by one or more processors, cause the one or more processors to perform a method comprising:
for each of a plurality of batches of text, each batch comprising text for addition to a cumulative document:
adding the batch of text to the cumulative document to produce an updated cumulative document;
encoding the updated cumulative document using an encoder neural network to obtain one or more encoder hidden states;
inputting the one or more encoder hidden states and a cumulative summary that summarises each preceding batch of text into a decoder neural network to generate a summary for the batch of text; and
updating the cumulative summary by adding the summary to the cumulative summary; and
outputting each summary.