Abstract
Natural Language inference refers to the problem of determining the relationships between a premise and a hypothesis, it is an emerging area of natural language processing. The paper uses deep learning methods to complete natural language inference task. The dataset includes 3GPP dataset and SNLI dataset. Gensim library is used to get the word embeddings, there are 2 methods which are word2vec and doc2vec to map the sentence to array. 2 deep learning models DNNClassifier and Attention are implemented separately to classify the relationship between the proposals from the telecommunication area dataset. The highest accuracy of the experiment is 88% and we found that the quality of the dataset decided the upper bound of the accuracy.
Highlights
Deep learning which has multiple layers processing structure has blossomed in different areas such as computer vision, speech recognition and bioinformatics
Natural language inference (NLI) — characterizing and using the relations in computational systems is essential in tasks ranging from information retrieval, semantic parsing to commonsense reasoning [3]
Natural language inference is the new increasing area of natural language processing, which infer the relationship of 2 sentence, one is premise and the other one is hypothesis
Summary
Deep learning which has multiple layers processing structure has blossomed in different areas such as computer vision, speech recognition and bioinformatics. Natural language processing is an area of using technical methods to deal with human natural language. Natural language processing method change human language to numeral vectors for machine to calculate. With these word embeddings, researchers can do different task such as sentiment analysis, machine translation and natural language inference. Natural language inference is the new increasing area of natural language processing, which infer the relationship of 2 sentence, one is premise and the other one is hypothesis. It’s sunny outside The premise “If you help the needy, God will get reward.”, the hypothesis “Giving money to the poor has good consequences.”, the premise will entail the hypothesis. If the hypothesis changes to “Giving money to the poor has unfortunate consequences.”, they have contradictory statement. If the hypothesis is “it is sunny outside”, the relationship between them is neutral
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have