ject-of-Natural-Language-Processing-DATA130030
所属分类：自然语言处理
开发工具：HTML
文件大小：20967KB
下载次数：0
上传日期：2020-03-16 09:19:47
上 传 者：
sh-1993
说明： 自然语言处理项目-DATA130030.01，这是一份报告，包括我在学校2019年秋季自然语言处理课程（DATA130030.01）中的所有项目...
(This is a report including all projects in my 2019 Fall Natural Language Processing course (DATA130030.01) in School of Data Science of Fudan University .)
文件列表:
Final PJ (0, 2020-03-16)
Final PJ\Final PJ (0, 2020-03-16)
Final PJ\Final PJ\1-ABSA (0, 2020-03-16)
Final PJ\Final PJ\1-ABSA\eval.py (1579, 2020-03-16)
Final PJ\Final PJ\1-ABSA\laptop-test.txt (79270, 2020-03-16)
Final PJ\Final PJ\1-ABSA\laptop-train.txt (322856, 2020-03-16)
Final PJ\Final PJ\1-ABSA\reference (0, 2020-03-16)
Final PJ\Final PJ\1-ABSA\reference\Attention-based LSTM for Aspect-level Sentiment Classification.pdf (1462259, 2020-03-16)
Final PJ\Final PJ\1-ABSA\reference\Interactive Attention Networks for Aspect-Level Sentiment Classification.pdf (213864, 2020-03-16)
Final PJ\Final PJ\1-ABSA\reference\SemEval-2014 Task 4- Aspect Based Sentiment Analysis.pdf (415834, 2020-03-16)
Final PJ\Final PJ\1-ABSA\restaurants-test.txt (155958, 2020-03-16)
Final PJ\Final PJ\1-ABSA\restaurants-train.txt (470315, 2020-03-16)
Final PJ\Final PJ\2 & 3-Commonsense (0, 2020-03-16)
Final PJ\Final PJ\2 & 3-Commonsense\dataset (0, 2020-03-16)
Final PJ\Final PJ\2 & 3-Commonsense\dataset\taskA (0, 2020-03-16)
Final PJ\Final PJ\2 & 3-Commonsense\dataset\taskA\dev.tsv (172697, 2020-03-16)
Final PJ\Final PJ\2 & 3-Commonsense\dataset\taskA\test.tsv (186388, 2020-03-16)
Final PJ\Final PJ\2 & 3-Commonsense\dataset\taskA\train.tsv (691278, 2020-03-16)
Final PJ\Final PJ\2 & 3-Commonsense\dataset\taskB (0, 2020-03-16)
Final PJ\Final PJ\2 & 3-Commonsense\dataset\taskB\dev.tsv (352677, 2020-03-16)
Final PJ\Final PJ\2 & 3-Commonsense\dataset\taskB\test.tsv (354904, 2020-03-16)
Final PJ\Final PJ\2 & 3-Commonsense\dataset\taskB\train.tsv (1404011, 2020-03-16)
Final PJ\Final PJ\2 & 3-Commonsense\evaluation tools (0, 2020-03-16)
Final PJ\Final PJ\2 & 3-Commonsense\evaluation tools\taskA_answer.csv (15056, 2020-03-16)
Final PJ\Final PJ\2 & 3-Commonsense\evaluation tools\taskB_answer.csv (15056, 2020-03-16)
Final PJ\Final PJ\2 & 3-Commonsense\evaluation tools\task_scorer.py (1449, 2020-03-16)
Final PJ\Final PJ\2 & 3-Commonsense\reference (0, 2020-03-16)
Final PJ\Final PJ\2 & 3-Commonsense\reference\Are Elephants Bigger than Butterflies_ Reasoning about Sizes of Objects.pdf (3944006, 2020-03-16)
Final PJ\Final PJ\2 & 3-Commonsense\reference\Does It Make Sense_ACL2019.pdf (319867, 2020-03-16)
Final PJ\Final PJ\2 & 3-Commonsense\reference\KagNet- Knowledge-Aware Graph Networks for Commonsense Reasoning.pdf (1003111, 2020-03-16)
Final PJ\Final PJ\2 & 3-Commonsense\result samples (0, 2020-03-16)
Final PJ\Final PJ\2 & 3-Commonsense\result samples\taskA_prediction_sample.csv (49, 2020-03-16)
Final PJ\Final PJ\2 & 3-Commonsense\result samples\taskB_prediction_sample.csv (49, 2020-03-16)
Final PJ\Final PJ\4-FNC (0, 2020-03-16)
Final PJ\Final PJ\4-FNC\note (173, 2020-03-16)
Final PJ\Final PJ\ACL format (232, 2020-03-16)
Final PJ\Final PJ\Final PJ.pptx (193370, 2020-03-16)
Final PJ\NLP_Final.pdf (389680, 2020-03-16)
Homework 1 Spelling Correction (0, 2020-03-16)
... ...
# Natural-Language-Processing-DATA130030.01-Fudan University
This is a report including all projects in my 2019 Fall Natural Language Processing course (DATA130030.01) in [School of Data Science](https://sds.fudan.edu.cn/) of [Fudan University](https://www.fudan.edu.cn/) .
## Project
* [Homework 1 Spelling Correction](https://github.com/Guardianzc/Project-of-Natural-Language-Processing-DATA130030.01/tree/master/Homework%201%20Spelling%20Correction)
* [Homework 2 Feature Engineering and Word2Vec based Sentiment Analysis](https://github.com/Guardianzc/Project-of-Natural-Language-Processing-DATA130030.01/tree/master/Homework%202%20Feature%20Engineering%20and%20Word2Vec%20based%20Sentiment%20Analysis)
* [Homework 3 Chinese Event Extraction](https://github.com/Guardianzc/Project-of-Natural-Language-Processing-DATA130030.01/tree/master/Homework%203%20Chinese%20Event%20Extraction)
* [FinalProject Commonsense Validation Model](https://github.com/Guardianzc/Project-of-Natural-Language-Processing-DATA130030.01/tree/master/Final%20PJ)
## Details
**Homework 1 Spelling Correction**
* In this project, I write a toy system for spelling correction. (Key words: Language Model Channel Model )
* You can see the detail of project [here](https://github.com/Guardianzc/Project-of-Natural-Language-Processing-DATA130030.01/blob/master/Homework%201%20Spelling%20Correction/Homework%201/spell-correction.pptx) and my report [here](https://github.com/Guardianzc/Project-of-Natural-Language-Processing-DATA130030.01/tree/master/Homework%201%20Spelling%20Correction/Answer)
**Homework 2 Feature Engineering and Word2Vec based Sentiment Analysis**
* In this project, I use feature engineering and word2vec based models for sentiment analysis.
(Key words: Feature engineering, Word2vec, Sentiment analysis)
* You can see the detail of project [here](https://github.com/Guardianzc/Project-of-Natural-Language-Processing-DATA130030.01/tree/master/Homework%202%20Feature%20Engineering%20and%20Word2Vec%20based%20Sentiment%20Analysis/Homework%202) and my report [here](https://github.com/Guardianzc/Project-of-Natural-Language-Processing-DATA130030.01/tree/master/Homework%202%20Feature%20Engineering%20and%20Word2Vec%20based%20Sentiment%20Analysis/Answer)
**Homework 3 Chinese Event Extraction**
* In this project, I use sequence labeling models for Chinese event extraction. (Key words: Labeling model)
* You can see the detail of project [here](https://github.com/Guardianzc/Project-of-Natural-Language-Processing-DATA130030.01/tree/master/Homework%203%20Chinese%20Event%20Extraction/Homework%203) and my report [here](https://github.com/Guardianzc/Project-of-Natural-Language-Processing-DATA130030.01/tree/master/Homework%203%20Chinese%20Event%20Extraction/Answer)
**FinalProject Commonsense Validation Model**
* I do this project with [Ruipu Luo](https://rupertluo.github.io/) and Geng Lin
* In this project, we design model to choose from two natural language statements to judge which one is against commonsense.
.
* We proposed a knowledge based commonsense validation model using graph convolutional network. In addition to adding an open source knowledge graph, we also added an explanation about common sense. From the experimental results, this makes the model better understand the meaning of this common sense. Finally, our accuracy can reach about 0.87.
* You can see the detail of project [here](https://github.com/Guardianzc/Project-of-Natural-Language-Processing-DATA130030.01/tree/master/Final%20PJ/Final%20PJ) and my report [here](https://github.com/Guardianzc/Project-of-Natural-Language-Processing-DATA130030.01/blob/master/Final%20PJ/NLP_Final.pdf)
* More details about the project is updating...
近期下载者：
相关文件：
收藏者：