chore: import upstream snapshot with attribution
This commit is contained in:
@@ -0,0 +1,23 @@
|
||||
========================
|
||||
Text Classification
|
||||
========================
|
||||
|
||||
Text classification is a fundamental NLP task that assigns predefined categories to text instances. It is widely applied in multiple scenarios:
|
||||
|
||||
- **Sentiment analysis**: Determine emotional polarity (positive/negative/neutral) in reviews or comments
|
||||
- **Topic labeling**: Categorize news articles or documents by subject
|
||||
- **Spam detection**: Identify unsolicited emails/messages
|
||||
- **Intent recognition**: Classify user queries in dialog systems
|
||||
- **Question answering**: Determine answerability of questions
|
||||
|
||||
Key technical challenges include:
|
||||
1. Variable text lengths (from phrases to documents)
|
||||
2. Multilingual and cross-domain generalization
|
||||
3. Discrepancies in label systems across domains
|
||||
4. Class imbalance issues
|
||||
|
||||
Common solutions involve:
|
||||
- Data cleaning and preprocessing
|
||||
- Feature engineering (TF-IDF, embeddings)
|
||||
- Model selection (from traditional ML to deep learning)
|
||||
- Hyperparameter tuning and ensemble methods
|
||||
@@ -0,0 +1,3 @@
|
||||
========================
|
||||
Word Vectors
|
||||
========================
|
||||
@@ -0,0 +1,3 @@
|
||||
========================
|
||||
General Conversation
|
||||
========================
|
||||
@@ -0,0 +1,29 @@
|
||||
========================
|
||||
Lexical Analysis
|
||||
========================
|
||||
|
||||
Lexical Analysis (词法分析)
|
||||
--------------------------
|
||||
|
||||
Lexical analysis is the process of converting a character sequence into a token sequence. It is the first phase of compilation and also the foundation of natural language processing.
|
||||
|
||||
Main Tasks:
|
||||
1. Tokenization (分词)
|
||||
2. Removing whitespace/comments
|
||||
3. Tracking line numbers
|
||||
4. Generating symbol tables
|
||||
|
||||
Example code:
|
||||
```python
|
||||
# This is a comment
|
||||
x = 123
|
||||
if (x > 0) {
|
||||
print("Positive")
|
||||
}
|
||||
```
|
||||
|
||||
Mathematical Representation:
|
||||
$$ T = Lex(S) $$
|
||||
Where $S$ is the input string and $T$ is the output token sequence.
|
||||
|
||||
See details in [link](#lexer-implementation). For HTML tags: <div class="important"></div>
|
||||
@@ -0,0 +1,3 @@
|
||||
========================
|
||||
Machine Translation
|
||||
========================
|
||||
@@ -0,0 +1,3 @@
|
||||
========================
|
||||
Sequence Labeling
|
||||
========================
|
||||
@@ -0,0 +1,42 @@
|
||||
============
|
||||
Overview
|
||||
============
|
||||
|
||||
Case Collections
|
||||
----------
|
||||
|
||||
- Word Vectors
|
||||
|
||||
- `Improve Model Performance with Pre-trained Word Vectors <https://aistudio.baidu.com/aistudio/projectdetail/1535355>`_
|
||||
|
||||
- Text Classification
|
||||
|
||||
- `Text Classification Based on LSTM and Other RNN Networks <https://aistudio.baidu.com/aistudio/projectdetail/1283423>`_
|
||||
- `Text Classification Using Pre-trained Models <https://aistudio.baidu.com/aistudio/projectdetail/1294333>`_
|
||||
- `Custom Dataset for Text Multi-classification Task <https://aistudio.baidu.com/aistudio/projectdetail/1468469>`_
|
||||
|
||||
- Information Extraction
|
||||
|
||||
- `Express Bill Information Extraction with BiGRU-CRF Model <https://aistudio.baidu.com/aistudio/projectdetail/1317771>`_
|
||||
- `Optimizing Express Bill Extraction with Pre-trained Model ERNIE <https://aistudio.baidu.com/aistudio/projectdetail/1329361>`_
|
||||
- `Relation Extraction <https://aistudio.baidu.com/aistudio/projectdetail/1639963>`_
|
||||
- `Event Extraction <https://aistudio.baidu.com/aistudio/projectdetail/1639964>`_
|
||||
|
||||
- Machine Reading Comprehension
|
||||
|
||||
- `Machine Reading Comprehension Using Pre-trained Models <https://aistudio.baidu.com/aistudio/projectdetail/1339612>`_
|
||||
|
||||
- Dialogue
|
||||
|
||||
- `Multi-skill Dialogue <https://aistudio.baidu.com/aistudio/projectdetail/1640180>`_
|
||||
|
||||
- Text Generation
|
||||
|
||||
- `Automatic Couplet Generation with Seq2Seq Model <https://aistudio.baidu.com/aistudio/projectdetail/1321118>`_
|
||||
- `Intelligent Poetry Generation with ERNIE-GEN Model <https://aistudio.baidu.com/aistudio/projectdetail/1339888>`_
|
||||
|
||||
- Time Series Prediction
|
||||
|
||||
- `COVID-19 Case Prediction Using TCN Network <https://aistudio.baidu.com/aistudio/projectdetail/1290873>`_
|
||||
|
||||
More tutorials available at `PaddleNLP on AI Studio <https://aistudio.baidu.com/aistudio/personalcenter/thirdview/574995>`_
|
||||
@@ -0,0 +1,3 @@
|
||||
========================
|
||||
Reading Comprehension
|
||||
========================
|
||||
@@ -0,0 +1,3 @@
|
||||
========================
|
||||
Semantic Matching
|
||||
========================
|
||||
@@ -0,0 +1,3 @@
|
||||
========================
|
||||
Text Generation
|
||||
========================
|
||||
Reference in New Issue
Block a user