Stanford CS224n Project: Reading Comprehension
نویسندگان
چکیده
In this paper we explore Machine Comprehension, a subset of Natural Language Processing, using data from SQuAD. We take an iterative approach to designing our prediction model, starting with a very basic foundation, extending it and replacing components piece by piece while testing for effectiveness. Our model achieves a 62.3 F1 score on the SQuAD test set.
منابع مشابه
CS224N Project: Let Computers Do Reading Comprehension
In this work, we want to teach the computers to do reading comprehension. More specifically, the task is to let computers read a short passage and then answer some simple questions based on the passage.[1] proposes an end-to-end, RNN-like approach which, according to them, needs significantly less supervision but performs comparatively good to benchmarks for many applications. However, we found...
متن کاملCS224N Assignment 4: Reading Comprehension
Building question answering systems with deep learning is a significant application of solving the complex natural language problem of reading comprehension. In our approach, we have analyzed literature on previous work, implemented and improved on specific models described, and compared the various models to analyze the effects of certain aspects of models on performance on the question answer...
متن کاملReconstructing, Investigating the Reliability and Validity and Scoring the Stanford Diagnostic Reading Test
Objectives: The aim of the present study was to reconstruct determining validity, and score The Stanford Diagnostic Reading Test fourth edition (SDRT4) in the sixth grade students. Methods: The population of the study was all sixth grades of the 19 educational districts from Tehran, 571 students (255 boys and 316 girls) were selected by using a random multi-cluster sampling. The data were an...
متن کاملCS224N: Assignment 4 Reading Comprehension
The Dynamic Coattention Network [1] is an end-to-end neural network model for question answering. The model consists of a coattentive encoder that captures the interactions between the question and the context paragraph, as well as a dynamic pointing decoder that alternates between estimating the start and end of the answer span. Due to the extensive training time needed by the complex decoder ...
متن کاملContext Encoding LSTM CS224N Course Project
This project uses ideas from greedy transition based parsing to build neural network models that can jointly learn to parse sentences and use those parses to guide semantic composition. The model is used for sentence encoding for tasks like Sentiment classification and Entailment. The performance is evaluated on Stanford Sentiment Treebank(SST) and Stanford Natural Language Inference (SNLI) cor...
متن کامل