保留正文与补采附件。源页面当前未重新核验；具体限制见交付清单。

Revisit consent button We value your privacy We use cookies to enhance your browsing experience, serve personalised ads or content, and analyse our traffic. By clicking "Accept All", you consent to our use of cookies. Customise Reject All Accept All Customise Consent Preferences We use cookies to help you navigate efficiently and perform certain functions. You will find detailed information about all cookies under each consent category below. The cookies that are categorised as "Necessary" are stored on your browser as they are essential for enabling the basic functionalities of the site. ... Show more NecessaryAlways Active Necessary cookies are required to enable the basic features of this site, such as providing secure log-in or adjusting your consent preferences. These cookies do not store any personally identifiable data.

Functional Functional cookies help perform certain functionalities like sharing the content of the website on social media platforms, collecting feedback, and other third-party features.

Analytics Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics such as the number of visitors, bounce rate, traffic source, etc.

Performance Performance cookies are used to understand and analyse the key performance indexes of the website which helps in delivering a better user experience for the visitors.

Advertisement Advertisement cookies are used to provide visitors with customised advertisements based on the pages you visited previously and to analyse the effectiveness of the ad campaigns.

Uncategorised Other uncategorised cookies are those that are being analysed and have not been classified into a category as yet. No cookies to display. Reject All Save My Preferences Accept All Toggle SearchToggle Mobile Navigation Publish AI, ML & data-science insights to a global community of data professionals. Sign inSubmit an Article LatestEditor's PicksNewsletterShipAI

Write For TDS LinkedInXToggle Search Data Science

Practical NLP: Summarising Short and Long Speeches With Hugging Face's Pipeline

Compared to sentiment analysis or classification, text summarisation is a far less ubiquitous NLP task due to the time and resources... Chua Chin Hon July 27, 20206 min read

Compared to sentiment analysis or classification, text summarisation is a far less ubiquitous NLP task due to the time and resources needed to execute it well. Hugging Face's transformers pipeline has changed that. Here's a quick demo of how you can summarise short and long speeches easily.

Screen grabs from PAP.org.sg left and WP.sg right. Screen grabs from PAP.org.sg (left) and WP.sg (right). Summarising a speech is more art than science, some might argue. But recent advances in NLP could well test the validity of that argument. In particular, Hugging Face's (HF) transformers summarisation pipeline has made the task easier, faster and more efficient to execute. Admittedly, there's still a hit-and-miss quality to current results. But there are also flashes of brilliance that hint at the possibilities to come as language models become more sophisticated. This post will demonstrate how you can easily use HF's pipeline to summarise both short and long speeches. A minor work-around is needed for long speeches due to the maximum sequence limit for models used in the pipeline. I've also included the code for a simple text summarisation web app that you can run on your local machine.

Learn this step by step with the interactive AI and Data Scientist, Machine Learning and Computer Science roadmaps.

1. DATA, NOTEBOOK AND CAVEATS

Here's the Github repo for this post. The toy dataset used in this post is based on a small collection of political speeches/statements made during Singapore's General Election in July 2020. The word-count for the speeches, by politicians from the ruling People's Action Party (PAP) as well as the Opposition, range from 236 words to 3,746 words. The simple workflow outlined in my notebook should work for any other collection of speeches you care to put together in a CSV file. The HF summarisation pipeline doesn't work for non-English speeches as far as I know. I'm using the pipeline out of the box, meaning the results stem from the default bart-large-cnn model. Feel free to test with other models tuned for this task.

2. SUMMARISING SHORT SPEECHES

It is unlikely that anyone needs to batch run summaries of dozens or hundreds of short speeches in one go. But in the off-chance that you do, the HF pipeline's ease of use is a lifesaver. Here, I ran the pipeline on seven speeches under 800 words. Results and time taken may vary according to the computer and version of the transformers library you are using. This was run on a 2018 Mac Mini with 64Gb of RAM on version 2.11.0 of the transformers library. You can download the results here and compare the summaries with the original text: Download this CSV file here. Download this CSV file here. Some of the summaries are so-so. There's a clear tendency for the model to use the first and second sentences in a speech. This could work well for summaries of news stories, but less so for those involving political/corporate speeches. But the model turned up one brilliant summary, the fifth one where Workers' Party (WP) leader Pritam Singh laid out his party's main pitch to voters. See the original statement here, and here's a side-by-side comparison with the summary by the Bart model. Image on left: Screen grab from WP.sg. Image on left: Screen grab from WP.sg. In just 59 words, the Bart model perfectly distilled the essence of the WP's campaign message from a 627-word statement. Those who are familiar with Singapore politics would appreciate how sharp this summary is, particularly given that the model was not tuned on data involving Singapore news or politics. It is not unreasonable to ask whether this summary is a fluke or happy coincidence. I ran the same set of speeches through the latest version of transformers (version 3.0.2) and got a less impressive translation: "The workers party offers singaporeans a choice and an alternative voice in parliament . The wp has contributed significantly to the democratic processes in our country . Former pap mps who wrote their memoirs after have helped to expose the limitations of a parliament dominated by the pap". Consistency of quality appears to be a problem at this point. A fuller test, unfortunately, is outside the scope of this post.

3. SUMMARISING A LONG SPEECH

This is likely the use case for most people: Summarising a long speech running into thousands of words. To get around the sequence length limits in the pipeline/models, I used a function to break up the text into a number of chunks of fixed-character length. To keep this post concise, I decided to run the HF pipeline on the longest speech - 3,746 words - in the toy dataset. I broke up the speech into 9 chunks of 2,500 characters each. The function allows you to easily set the character length that you prefer. This approach is admittedly clumsy, but I find it useful for a closer inspection of the results. Details are in my notebook. Here's the link to the original speech, and a CSV file comparing the original text with the mini-summaries can be dowloaded [here](http://A CSV file comparing the original text with the mini-summaries can be dowloaded here). This is a side-by-side comparison of how the model summarised it : Image on left: Screen grab from Pap.org.sg. Download the CSV results file of the long-speech summarisation here. Image on left: Screen grab from Pap.org.sg. Download the CSV results file of the long-speech summarisation here. The 536-word "combined summary" is not as brilliant as the WP example I highlighted above, but it's pretty decent (except for the section highlighted in red, which I'll discuss in a bit) for a first draft. If I'm in a crunch, this is something I can quickly edit into a more useable form. Singaporean users will easily pick out an obvious mistake in the summary of the sixth section: "Pap Lee Kuan Yew seeks not just your mandate but your strong mandate to lead singapore through this crisis." The original paragraph reads: "Investors will scrutinise the election results, and act on their conclusions. So will others, both friends and adversaries of Singapore. That is why in this election, the PAP seeks not just your mandate, but your strong mandate, to lead Singapore through this crisis." Lee Kuan Yew, Singapore's founding prime minister, died in March 2015. However, those with more than a passing knowledge of Singapore politics might flippantly argue that the model was in fact correct and not erroneous with the above summary mentioning Lee Kuan Yew. But that is a discussion for another day ;p.

4. WEB APP

I tried to deploy a simple web app to let non-notebook users try the summarisation pipeline, but discovered that free accounts on Pythonanywhere.com don't have enough storage space for the libraries required, particularly pytorch. So instead I uploaded a version that runs on local machines, if you are keen to let colleagues at the workplace try it out. The code for the web app was adapted from two sources: the main one from Github and a second one by Plotly using DistilBart. If the app returns an error, it means the text you've copied has exceeded the maximum number of tokens. Try summarising in smaller chunks or use the function in the notebook to break up the text. I'll try to deploy the app online in future if Pythonanywhere.com includes pytorch as part of their pre-installed packages.

5. CONCLUSION

With more language models being added by the week, there's ample scope for experimentation and more robust tests of the HF pipeline's summarisation output. My own experience so far is that using a different model doesn't necessarily translate into better results. Towards the end of my notebook, I switched to the T5 model for a trial but found that the summarisations for three short speeches weren't better than those churned out by the default Bart model. But we are certainly getting a good glimpse of the future possibilities as companies like Hugging Face and OpenAI continue to push the NLP envelope. I'm certainly curious to see how GPT-3 performs on this task, given the impressive results it has achieved on a diverse range of tasks so far. Meanwhile, those who want to experiment further by fine tuning a transformer model with their own dataset can check out these two notebooks [here](https://github.com/abhimishra91/transformers-tutorials/blob/master/transformers_summarization_wandb.ipynb) and here. Finding a good dataset for your use case, however, could be more challenging than you think. If you spot errors in this post or the notebook, ping me at: Twitter: Chua Chin Hon LinkedIn: www.linkedin.com/in/chuachinhon

Register Now to Continue Reading

Unlock Towards Data Science with a Free Account

All articles on Towards Data Science are available to registered users. Create a free account today to access this article and thousands more. Register for freeSign in to your account

Written By

Chua Chin Hon

See all from Chua Chin Hon Data ScienceHugging FaceNLPScienceSingapore Share This Article

Towards Data Science is a community publication. Submit your insights to reach our global audience and earn through the TDS Author Payment Program. Write for TDS

Related Articles

Exploratory Data Analysis with Python - Part 2

Data Science A template to follow to get you started analyzing data with Python and Pandas. Gustavo Santos November 29, 20211 min read

Downscaling a Satellite Thermal Image from 1000 m to 10 m (Python)

Data Science Thermal Sharpening of Sentinel-3 Images: From 1 Km to 10 m Using Python in Google Colab Mahyar Aboutalebi March 6, 202413 min read

SQL Server's Secret Feature - Run Python and Add-Ons Natively In SQL Server.

Machine Learning Import Python libraries, manipulate and output SQL tables and more, all without leaving SQL server. Sasha Korovkina May 15, 20244 min read

Python Pandas Gives You Full Control Over Timestamps

Artificial Intelligence From years to nanoseconds. Soner Yıldırım January 15, 20226 min read

Five Rules for Designing Tables

Data Science Simple design elements to make your spreadsheets pop Alana Pirrone July 27, 20214 min read

How to Optimize your Switchback A/B Test Configuration

Data Science An algorithm that determines the most effective randomization points for a switchback experiment. Michael Berk June 8, 20219 min read

Simple Explanations of Basic Statistics Concepts (Part 1)

Data Science Simple and comprehensive explanations of different statistical concepts Chi Nguyen June 7, 20227 min read

A Guide to using h2o.ai in R

Machine Learning Learn how to work with the h2o library using the R Language Ivo Bernardo November 2, 202215 min read

Why You Shouldn't Hire More Data Scientists

Data Science Save money and frustration by considering the roles of analysts, data engineers, and software engineers... Adam Sroka April 26, 20217 min read

Your home for data science and AI. The world's leading publication for data science, data analytics, data engineering, machine learning, and artificial intelligence professionals. Subscribe to Our NewsletterWrite For TDS•About•Advertise•Privacy Policy•Terms of Use © Insight Media Group, LLC 2026•The New Stack•roadmap.sh•Creator Network

Recommended Articles

Close