Missing pipeline types in Chapter 1 / Section 3 ("Transformers, what can they do?")

The pipeline types "question-answering", "summarization" and "translation" (mentioned in #1284 ) are no longer available in the `transformers` module. Trying to execute the example code e.g. by [opening the notebook in Colab](https://colab.research.google.com/github/huggingface/notebooks/blob/master/course/en/chapter1/section3.ipynb) raises a KeyError:

```
KeyError: "Unknown task translation, available tasks are
['any-to-any', 'audio-classification', 'automatic-speech-recognition', 'depth-estimation', 'document-question-answering', 'feature-extraction', 'fill-mask', 'image-classification', 'image-feature-extraction', 'image-segmentation', 'image-text-to-text', 'keypoint-matching', 'mask-generation', 'ner', 'object-detection', 'sentiment-analysis', 'table-question-answering', 'text-classification', 'text-generation', 'text-to-audio', 'text-to-speech', 'token-classification', 'video-classification', 'zero-shot-audio-classification', 'zero-shot-classification', 'zero-shot-image-classification', 'zero-shot-object-detection']"
```

Start with course/en/chapter1/section3.ipynb and run the affected examples in Colab to reproduce the KeyError. Review the references to question-answering, summarization, and translation, then verify that the Chapter 1 Section 3 examples run successfully without unknown-task errors.

Written by the indexing model from the issue text.