Automatic Summarization using Deep Learning | Abstractive Summarization with Pegasus

แชร์
ฝัง
  • เผยแพร่เมื่อ 18 ม.ค. 2025

ความคิดเห็น • 100

  • @naitikshah7969
    @naitikshah7969 3 ปีที่แล้ว +24

    Whoever is getting an error while creating the tokenizer in step 1, run this command on your terminal:
    pip install sentencepiece
    Great video Nicholas, thanks mate!

    • @satoshinakamoto5710
      @satoshinakamoto5710 3 ปีที่แล้ว +3

      Also restart kernel and run all cells if you get "None type error". Sometimes the cell that downloads the pegasus model fails.

    • @ashikurrahman-ai8227
      @ashikurrahman-ai8227 3 ปีที่แล้ว

      @@satoshinakamoto5710 Thanks mate

    • @vaishnavimore754
      @vaishnavimore754 2 ปีที่แล้ว

      Thanks

  • @priyamkakati4427
    @priyamkakati4427 3 ปีที่แล้ว +3

    Amazng content as usual!

  • @henkhbit5748
    @henkhbit5748 3 ปีที่แล้ว +1

    Samenvattend, wederom een mooie introductie in NLP met de "vliegende paard" 👍

  • @alexandregagne4151
    @alexandregagne4151 3 ปีที่แล้ว +2

    Like always, thank you. This channel is soooo good

    • @NicholasRenotte
      @NicholasRenotte  3 ปีที่แล้ว

      Cheers @Alexandre!

    • @shreevinayaka8219
      @shreevinayaka8219 6 หลายเดือนก่อน

      @@NicholasRenotte sir how to increase the number of words or how to keep it variable

  • @VladimirSkultetyOfficial
    @VladimirSkultetyOfficial 3 ปีที่แล้ว +1

    Very good channel and videos. Thank you Nicholas!

  • @TKollaKid
    @TKollaKid 2 ปีที่แล้ว

    I learned so much from this video. Liked and subscribed. Thank you, Nicholas!

  • @hilariouzclips1235
    @hilariouzclips1235 3 ปีที่แล้ว +1

    Great video, Nicholas.

  • @soumyadeepnag6300
    @soumyadeepnag6300 2 ปีที่แล้ว +6

    Thanks for explaining the video nicely. But, does the pegasus model always generate one line of summary? Is there any way we can increase the number of summary lines?

    • @user-og2cw5yv2m
      @user-og2cw5yv2m ปีที่แล้ว

      hey have you found how to generate multiple lines

  • @erfansthought
    @erfansthought 2 ปีที่แล้ว +1

    How to make more than 1 sentence summary? It is possible to configure it to generate a summary of specified sentences like 10 sentence summary?

  • @litttlemooncream5049
    @litttlemooncream5049 10 หลายเดือนก่อน

    mark! gonna take a try. many thanks

  • @mdrahatislamkhan9966
    @mdrahatislamkhan9966 2 ปีที่แล้ว +1

    cant install the torch. searched a lot but can't find the solution tried lots of things but got this error "No matching distribution found for torch" Please help me fix this problem.

  • @AutumnRainWish
    @AutumnRainWish 2 ปีที่แล้ว +1

    6:18 pip install transformers==4.11.3
    if you are getting an error ImportError: cannot import name 'PegasusForConditionalGeneration' from 'transformers'

    • @sanchitafusiondance
      @sanchitafusiondance ปีที่แล้ว

      thank u so much.. u have no idea how much u saved me..

  • @arshdeepsingh5950
    @arshdeepsingh5950 3 ปีที่แล้ว +2

    love you sir must say your brain is awesome.

  • @rohankherath
    @rohankherath 3 ปีที่แล้ว +1

    Thank You Nicho...

  • @Manideep.
    @Manideep. 3 ปีที่แล้ว +1

    when i import the model i am getting AttributeError: 'Version' object has no attribute 'major'

  • @Powercube7
    @Powercube7 3 ปีที่แล้ว +2

    Pegasus? More like Pega SUS 😳
    For real tho, this is actually really helpful, now i don't have to read anymore thanks fam 😂

    • @NicholasRenotte
      @NicholasRenotte  3 ปีที่แล้ว +2

      I think you mean....Mega SUS?!
      Hahaha, hell yeah, bail on all that reading rubbish!

    • @Powercube7
      @Powercube7 3 ปีที่แล้ว

      @@NicholasRenotte sussy baka 😳😳😳

  • @pradhansomu4100
    @pradhansomu4100 3 ปีที่แล้ว +2

    Bro please make a video on creating custom dataset for pose estimation and which architecture will be best to train

  • @BS-ob3hp
    @BS-ob3hp 3 ปีที่แล้ว +3

    Hi Nicholas, thank you for your content here on youtube :)! I was just wondering if I can also use Preview or Stable, since LTS is not supported on a mac. Thanks!

  • @asprakmantab
    @asprakmantab ปีที่แล้ว +1

    can we set the length of summary?

  • @Brian5094
    @Brian5094 2 ปีที่แล้ว

    Really dope! I was looking for the turtorial to guide me through the summarization model and your video has extremely high quality and super practical!
    I have a question that is abstractive summarization need to be fine-tuned? If so, how can we do it? :D

  • @swishrsplitr
    @swishrsplitr 11 หลายเดือนก่อน

    great video, thanks - are there any summarization models that accept more than 1k tokens as input?

  • @deepakkumarjha
    @deepakkumarjha 3 ปีที่แล้ว +8

    Hey, would you mind making a video on how the model could be fine tuned for a custom text dataset, because I read the paper and couldn't do it. It would also be a good continuation to this video.

    • @rudreshmehta6510
      @rudreshmehta6510 2 ปีที่แล้ว +1

      Hey, Did you find the way to do that?

  • @shreevinayaka8219
    @shreevinayaka8219 6 หลายเดือนก่อน

    sir how to increase the number of words or how to keep it variable

  • @aliffnabil5542
    @aliffnabil5542 3 ปีที่แล้ว +1

    yooooo this is sick!

  • @ryanw8765
    @ryanw8765 ปีที่แล้ว

    When companies build text summarization models like this one, do they create their own model and launch it for their app or do they generally use pre-existing models?

  • @e_souhil
    @e_souhil 3 ปีที่แล้ว +3

    thanks, it was so helpful can you do a video on how we can fine-tune the pegasus model on a different dataset?

    • @rudreshmehta6510
      @rudreshmehta6510 2 ปีที่แล้ว

      Hey, Did you find the way to do that?

    • @vent_srikar7360
      @vent_srikar7360 2 ปีที่แล้ว

      @@rudreshmehta6510 did you find it ?

  • @alexandregagne4151
    @alexandregagne4151 3 ปีที่แล้ว +1

    I have a little question. I would like to create a model to recognize a person, but everything I find online and on youtube uses Face-recognition.
    However, I would like my model to be able to recognize a person, not necessarily by their face but also by a tattoo or a feature of their body and etc. What do you think would be the best technique to accomplish this task? Would a simple image classifier do the trick?

    • @NicholasRenotte
      @NicholasRenotte  3 ปีที่แล้ว +1

      Aside from the ethical implications, you could look at using a siamese network. Keep in mind it requires a ton of data if you're to do it on more than just faces!

    • @alexandregagne4151
      @alexandregagne4151 3 ปีที่แล้ว

      @@NicholasRenotte That's what I understood, I need a lot of data. To practice a little, is it possible to use the landmarks (face) to detect and recognize a person with mediapipe? I'm trying to use your method on the sign languages video, but I get an accuracy of around 27% after 4000 epochs, no good :(

    • @NicholasRenotte
      @NicholasRenotte  3 ปีที่แล้ว

      @@alexandregagne4151 might be a bit late to this, have you checked out the facial rec tutorial?

  • @rahil1575
    @rahil1575 3 ปีที่แล้ว +1

    Is there any way to specify the length of summary

  • @shreeshaaithal-
    @shreeshaaithal- 3 ปีที่แล้ว +2

    First I thought that you are talking the Pegasus virus then ooh ok summarize Pegasus 😂

  • @trinitaroy5084
    @trinitaroy5084 2 ปีที่แล้ว +1

    Can you also show how do you fine tune the Pegasus model with a custom dataset for text summarization?

  • @akshay3361
    @akshay3361 3 ปีที่แล้ว +2

    Can you make a text summarizer using gpt 3 or 2?

  • @srishtigureja6534
    @srishtigureja6534 3 ปีที่แล้ว +1

    Great video! thanks 🎉
    I was unable to understand the last part, what fine tuning can be done exactly for the model to perform better?

    • @NicholasRenotte
      @NicholasRenotte  3 ปีที่แล้ว +1

      Can fine tune the underlying model on a dataset of your choice! Google did it on a bunch of different text corpuses, e.g. for Journals you could use this model: huggingface.co/google/pegasus-pubmed

    • @srishtigureja6534
      @srishtigureja6534 3 ปีที่แล้ว

      @@NicholasRenotte Thanks!

  • @ahmedalameldien765
    @ahmedalameldien765 3 ปีที่แล้ว +1

    hi nicholas, i really appreciate your video. thank you for this very informative video.
    could you make another one of how to fine tuning a custom text dataset ?

  • @vishnureddy7543
    @vishnureddy7543 3 ปีที่แล้ว +1

    Thanks Nick! Also how do I add a dataset to it instead of a piece of text?

    • @NicholasRenotte
      @NicholasRenotte  3 ปีที่แล้ว

      For summarization? This is very much focused on NLP. For structured data I would be focused on using Pandas, got a crash course on the channel!

  • @guimaraesalysson
    @guimaraesalysson ปีที่แล้ว

    Great video

  • @davidzhang4825
    @davidzhang4825 2 ปีที่แล้ว

    Is Pegasus the best model for text summarization? if not which model is the best?

  • @detour1055
    @detour1055 3 ปีที่แล้ว

    Just found you today...absolutely love your content and wide range of projects. I'm not a programmer but I'm looking to complete some projects very similar to what you've showcased in your videos. Are you available to hire?

  • @utkar1
    @utkar1 2 ปีที่แล้ว

    Hey thanks man! I'm wondering is there is way we can create book summaries as well with one of these transformers?

  • @mohammadabdulkadir8799
    @mohammadabdulkadir8799 ปีที่แล้ว +1

    Am getting this error when am trying to load the tokkenizer how can i resolve it
    TypeError Traceback (most recent call last)
    Cell In[25], line 2
    1 # Load tokenize
    ----> 2 tokenizer = PegasusTokenizer.from_pretrained("google/pegasus-large")
    TypeError: 'NoneType' object is not callable

  • @anonymousking2053
    @anonymousking2053 3 ปีที่แล้ว +2

    Nicholas why don't you start reinforcement learning for gaming, everybody wants it.
    by the way love your videos

    • @NicholasRenotte
      @NicholasRenotte  3 ปีที่แล้ว +2

      Ik ik, just gotta get back to it.

    • @Powercube7
      @Powercube7 3 ปีที่แล้ว +1

      He is doing his best, we should have some patience. Quality over quantity!

  • @debatradas9268
    @debatradas9268 2 ปีที่แล้ว +1

    thank you so much

  • @lahiruneranjanrathnayaka3665
    @lahiruneranjanrathnayaka3665 3 ปีที่แล้ว +1

    great video :D. How can we implement this for another language ?

    • @NicholasRenotte
      @NicholasRenotte  3 ปีที่แล้ว +2

      Would probably look at converting to english first, summarizing then converting back. One of the other subscribers mentioned the summarization in other languages sucks, would try that approach instead!

    • @lahiruneranjanrathnayaka3665
      @lahiruneranjanrathnayaka3665 3 ปีที่แล้ว

      @@NicholasRenotte Thanks. I'll give a try :D

  • @TejrajParab
    @TejrajParab 3 ปีที่แล้ว +1

    I remember that nightmarish novel.

    • @NicholasRenotte
      @NicholasRenotte  3 ปีที่แล้ว +1

      Don't even get me started. Honestly I hated every minute of that class and I definitely made it known. What a complete waste of time....if only i knew back then I'd end up coding, would've bailed completely!

  • @idkidk1774
    @idkidk1774 3 ปีที่แล้ว +2

    love it

  • @hosdvz1
    @hosdvz1 ปีที่แล้ว

    hi there. why do we bother ourselves to summarize just 512 tokens :)

  • @erfansthought
    @erfansthought 3 ปีที่แล้ว +1

    I am getting 'NoneType' object is not callable after this code in colab
    tokens = tokenizer(text, truncation=True, padding="longest", return_tensors="pt")
    Solution please.
    Great Videos. Keep it up.

    • @NicholasRenotte
      @NicholasRenotte  3 ปีที่แล้ว

      What's in the text?

    • @erfansthought
      @erfansthought 3 ปีที่แล้ว +3

      @@NicholasRenotte
      TypeError Traceback (most recent call last)
      in ()
      ----> 1 tokens = tokenizer(text, truncation=True, padding="longest", return_tensors="pt")
      TypeError: 'NoneType' object is not callable

    • @qwertl99
      @qwertl99 3 ปีที่แล้ว

      running into same problem

    • @qwertl99
      @qwertl99 3 ปีที่แล้ว

      reloading jupyter fixed my issue :)

    • @erfansthought
      @erfansthought 3 ปีที่แล้ว +1

      @@qwertl99 Didn't work for me in colab

  • @satvikmanchanda7090
    @satvikmanchanda7090 9 หลายเดือนก่อน

    reading research papers can really be hard, wish there was some trick

  • @mahdimahdavi1341
    @mahdimahdavi1341 ปีที่แล้ว

    thank's

  • @idkidk1774
    @idkidk1774 3 ปีที่แล้ว +5

    Bro pls make a python chat bot with deep learning and actions like: join school class answer ok sir and join the class

    • @NicholasRenotte
      @NicholasRenotte  3 ปีที่แล้ว +3

      Alrighty, will build it into the plan!

    • @idkidk1774
      @idkidk1774 3 ปีที่แล้ว +2

      You are insane bro

  • @ashleysami1640
    @ashleysami1640 3 ปีที่แล้ว +1

    Don't lie. Bet you love Jane Austin.

  • @mannatsiddiqui5499
    @mannatsiddiqui5499 2 ปีที่แล้ว

    Getting error
    TypeError Traceback (most recent call last)
    in ()
    4 model = PegasusForConditionalGeneration.from_pretrained("google/pegasus-xsum")
    5 # Load tokenizer
    ----> 6 tokenizer = PegasusTokenizer.from_pretrained("google/pegasus-xsum")
    TypeError: 'NoneType' object is not callable
    Please tell how should I resolve it

  • @laurentprea7746
    @laurentprea7746 3 ปีที่แล้ว

    Who else is having issues installing pytorch? The error is shown below
    ERROR: No matching distribution found for torch==1.8.2+cu111

    • @NicholasRenotte
      @NicholasRenotte  3 ปีที่แล้ว

      If copied directly from the PT site, you should be good to go. Possibly another version of Python required? I used 3.7.3 in the video with no issues.

  • @vent_srikar7360
    @vent_srikar7360 2 ปีที่แล้ว

    hey iam getting this error of -: tokenizer = PegasusTokenizer.from_pretrained("google/pegasus-xsum")
    TypeError: 'NoneType' object is not callable
    any idea whats the mistake ?

  • @jaymie-001
    @jaymie-001 2 ปีที่แล้ว

    I really hope you reply to this. Thanks so much for.this project. It worked before.. now for the autotokenizer.from_pretrained(google/pegasus-xsum) .. it's giving an error that filenotfound

  • @jetakota
    @jetakota 2 ปีที่แล้ว

    PegasusTokenizer.from_pretrained('google/pegasus-xsum') returns None. PegasusTokenizer also returns None for 'google/pegasus-large'