List view
In this chapter, we train a neural machine translation (NMT) model by using IWSLT'14 English to German translation dataset. For the actual implementation of an NMT model, use the off-the-shelf toolkits such as [fairseq](https://github.com/pytorch/fairseq), [Hugging Face Transformers](https://github.com/huggingface/transformers) and [OpenNMT-py](https://github.com/OpenNMT/OpenNMT-py).
No due date•0/10 issues closed- No due date•0/10 issues closed
In this chapter, we implement a neural network model for the text classification task. We then apply the model to the news classification dataset that we used in the chapter 6. You might want to use the deep learning frameworks such as PyTorch, TensorFlow, Chainer.
No due date•0/10 issues closedThis chapter introduces the concept of the word vectors (i.e., word embeddings). Create the following problems.
No due date•0/10 issues closedIn this chapter, we tackle the task of news classification. The task is to classify a given news headline to one of the following categories: "Business", "Science", "Entertainment" and "Health". [News Aggregator Data Set](https://archive.ics.uci.edu/ml/datasets/News+Aggregator) provided by Fabio Gasparetti, is the dataset we use in this chapter.
No due date•0/10 issues closedThe zip archive [ai.en.zip](https://nlp100.github.io/data/ai.en.zip) contains the text of the Wikipedia article, "[Artificial Intelligence](https://en.wikipedia.org/wiki/Artificial_intelligence)". Apply a dependency parser to the text, and store the result in a file. Implement programs that read the dependency trees and perform the jobs. For your convenience, the zip archive also includes `ai.en.txt.json`, the text with dependency trees predicted by [Stanford CoreNLP](https://stanfordnlp.github.io/CoreNLP/) and stored in JSON format.
No due date•0/10 issues closed