Systems and methods for neural clinical paraphrase generation
The present disclosure pertains to a paraphrase generation system. The system comprises one or more hardware processors and/or other components. The system is configured to obtain a training corpus. The training corpus comprises language and known paraphrases of the language. The system is configured to generate, based on the training corpus, a word-level attention-based model and a character-level attention-based model. The system is configured to provide one or more candidate paraphrases of a natural language input based on both the word-level and character-level attention-based models. The word-level attention-based model is a word-level bidirectional long short term memory (LSTM) network and the character-level attention-based model is a character-level bidirectional LSTM network. The word-level and character level LSTM networks are generated based on words and characters in the training corpus. In some embodiments, the LSTM networks are stacked residual LSTM networks comprising residual connections between stacked layers of a given LSTM network.
1. A paraphrase generation system comprising one or more hardware processors configured by machine-readable instructions to:
obtain a training corpus, the training corpus comprising language and paraphrases of the language;
determine word-level and character-level embeddings using the training corpus;
update the word-level and character-level embeddings based on semantic relationships known from existing knowledge bases;
generate, based on the training corpus and the word-level and character-level embeddings, a word-level attention-based model and a character-level attention-based model; and
provide one or more candidate paraphrases of a natural language input based on both the word-level and character-level attention-based models.
2. The system of claim 1 , wherein the one or more hardware processors are configured such that the word-level attention-based model is a word-level bidirectional long short term memory (LSTM) network and the character-level attention-based model is a character-level bidirectional LSTM network, and wherein the word-level and character level LSTM networks are generated based on words and characters in the training corpus.
3. The system of claim 1 , wherein the one or more hardware processors are configured to generate a sentence-level attention-based model based on the training corpus, wherein the one or more hardware processors are configured to provide the one or more candidate paraphrases of the natural language input based on the sentence-level, word-level, and character-level attention-based models.
4. The system of claim 1 , wherein the one or more hardware processors are further configured to determine a sentence-level embedding using the training corpus; update the sentence-level embedding based on semantic relationships known from existing knowledge bases; and provide the one or more candidate paraphrases further based on the sentence-level embedding.
5. The system of claim 4 , wherein the one or more hardware processors are configured to determine the sentence-level, word-level, and character level embeddings using recurrent neural networks (RNN) and/or convolutional neural networks (CNN).
6. The system of claim 1 , wherein the one or more hardware processors are configured such that the providing the one or more candidate paraphrases comprises determining a reward function reinforcement learning model configured to compare a semantic similarity and novelty of candidate paraphrase word choices to a target sentence, and outputting a candidate paraphrase based on the comparison.
7. The system of claim 1 , wherein the one or more hardware processors are configured such that the word-level attention-based model is a stacked residual word-level bidirectional long short term memory (LSTM) network and the character-level attention-based model is a stacked residual character-level bidirectional LSTM network, the stacked residual LSTM networks comprising residual connections between stacked layers of a given LSTM network.
8. A method for generating paraphrases with a paraphrase generation system, the system comprising one or more hardware processors configured by machine-readable instructions, the method comprising:
obtaining a training corpus, the training corpus comprising language and paraphrases of the language;
determining word-level and character-level embeddings based on semantic relationships known from existing knowledge bases;
updating the word-level and character-level embeddings based on semantic relationships known from existing knowledge bases;
generating, based on the training corpus and on the updated word-level and character-level embeddings, a word-level attention-based model and a character-level attention-based model; and
providing one or more candidate paraphrases of a natural language input based on both the word-level and character-level attention-based models.
9. The method of claim 8 , wherein the word-level attention-based model is a word-level bidirectional long short term memory (LSTM) network and the character-level attention-based model is a character-level bidirectional LSTM network, and wherein the word-level and character level LSTM networks are generated based on words and characters in the training corpus.
10. The method of claim 8 , further comprising generating a sentence-level attention-based model based on the training corpus, and providing the one or more candidate paraphrases of the natural language input based on the sentence-level, word-level, and character-level attention-based models.
11. The method of claim 8 , further comprising determining a sentence-level embedding using the training corpus; updating the sentence-level embeddings based on semantic relationships known from existing knowledge bases; and providing the one or more candidate paraphrases based on the updated sentence-level embedding.
12. The method of claim 11 , wherein the sentence-level, word-level, and character level embeddings are determined using recurrent neural networks (RNN) and/or convolutional neural networks (CNN).
13. The method of claim 8 , wherein providing the one or more candidate paraphrases comprises determining a reward function reinforcement learning model configured to compare a semantic similarity and novelty of candidate paraphrase word choices to a target sentence, and outputting a candidate paraphrase based on the comparison.
14. The method of claim 8 , wherein the word-level attention-based model is a stacked residual word-level bidirectional long short term memory (LSTM) network and the character-level attention-based model is a stacked residual character-level bidirectional LSTM network, the stacked residual LSTM networks comprising residual connections between stacked layers of a given LSTM network.
15. A system for generating paraphrases, the system comprising:
means for obtaining a training corpus, the training corpus comprising language and paraphrases of the language;
means for determining word-level and character-level embeddings using the training corpus;
means for updating the word-level and character-level embeddings based on semantic relationships known from existing knowledge bases;
means for generating, based on the training corpus and the updated word-level and character-level embeddings, a word-level attention-based model and a character-level attention-based model; and
means for providing one or more candidate paraphrases of a natural language input based on both the word-level and character-level attention-based models.
16. The system of claim 15 , wherein the word-level attention-based model is a word-level bidirectional long short term memory (LSTM) network and the character-level attention based model is a character-level bidirectional LSTM network, and wherein the word-level and character level LSTM networks are generated based on words and characters in the training corpus.
17. The system of claim 15 , further comprising means for generating a sentence-level attention-based model based on the training corpus, and providing the one or more candidate paraphrases of the natural language input based on the sentence-level, word-level, and character-level attention-based models.
18. The system of claim 15 , further comprising means for determining sentence-level embeddings using the training corpus; means for updating sentence-level embeddings based on semantic relationships known from existing knowledge bases; and means for providing the one or more candidate paraphrases based on the updated sentence-level embeddings.
19. The system of claim 18 , wherein the sentence-level, word-level, and character level embeddings are determined using recurrent neural networks (RNN) and/or convolutional neural networks (CNN).
20. The system of claim 15 , wherein providing the one or more candidate paraphrases comprises determining a reward function reinforcement learning model configured to compare a semantic similarity and novelty of candidate paraphrase word choices to a target sentence, and outputting a candidate paraphrase based on the comparison.
21. The system of claim 15 , wherein the word-level attention-based model is a stacked residual word-level bidirectional long short term memory (LSTM) network and the character-level attention-based model is a stacked residual character-level bidirectional LSTM network, the stacked residual LSTM networks comprising residual connections between stacked layers of a given LSTM network.