langquantof commited on
Commit
1e86ec3
Β·
verified Β·
1 Parent(s): 31d42b8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -26
README.md CHANGED
@@ -18,7 +18,7 @@ metrics:
18
 
19
  # LQ-FSE-base: Korean Financial Sentence Extractor
20
 
21
- LangQuant(λž­ν€€νŠΈ)μ—μ„œ κ³΅κ°œν•œ 금육 리포트, 금육 κ΄€λ ¨ λ‰΄μŠ€μ—μ„œ λŒ€ν‘œλ¬Έμž₯을 μΆ”μΆœν•˜κ³  μ—­ν• (outlook, event, financial, risk)을 λΆ„λ₯˜ν•˜λŠ” λͺ¨λΈμž…λ‹ˆλ‹€.
22
 
23
  ## Model Description
24
 
@@ -113,37 +113,23 @@ for i, sent in enumerate(sentences):
113
  print(f" {marker} [{score:.4f}] [{role:10s}] {sent}")
114
  ```
115
 
116
- ## Model Architecture
117
 
118
  ```
119
- Input Sentences
120
- ↓
121
- [klue/roberta-base] β†’ [CLS] embeddings per sentence
122
- ↓
123
- [Inter-sentence Transformer] (2 layers, 8 heads)
124
- ↓
125
- β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
126
- β”‚ Binary Classifierβ”‚ Role Classifier β”‚
127
- β”‚ (representative?)β”‚ (outlook/event/ β”‚
128
- β”‚ β”‚ financial/risk) β”‚
129
- β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
130
  ```
131
 
132
- ## Training
133
 
134
- - Optimizer: AdamW (lr=2e-5, weight_decay=0.01)
135
- - Scheduler: Linear warmup (10%)
136
- - Loss: BCE (extraction) + CrossEntropy (role), role_weight=0.5
137
- - Max sentence length: 128 tokens
138
- - Max sentences per document: 30
139
-
140
- ## Files
141
 
142
- - `model.py`: Model definition (DocumentEncoderConfig, DocumentEncoderForExtractiveSummarization)
143
- - `config.json`: Model configuration
144
- - `model.safetensors`: Model weights
145
- - `inference_example.py`: Inference helper with usage example
146
- - `convert_checkpoint.py`: Script to convert original .pt checkpoint
147
 
148
  ## Disclaimer (λ©΄μ±… μ‘°ν•­)
149
 
 
18
 
19
  # LQ-FSE-base: Korean Financial Sentence Extractor
20
 
21
+ 금육 리포트, 금육 κ΄€λ ¨ λ‰΄μŠ€μ—μ„œ λŒ€ν‘œλ¬Έμž₯을 μΆ”μΆœν•˜κ³  μ—­ν• (outlook, event, financial, risk)을 λΆ„λ₯˜ν•˜λŠ” λͺ¨λΈμž…λ‹ˆλ‹€.
22
 
23
  ## Model Description
24
 
 
113
  print(f" {marker} [{score:.4f}] [{role:10s}] {sent}")
114
  ```
115
 
116
+ ### Input Example
117
 
118
  ```
119
+ μ‚Όμ„±μ „μžμ˜ 2024λ…„ 4λΆ„κΈ° 싀적이 μ‹œμž₯ μ˜ˆμƒμ„ μƒνšŒν–ˆλ‹€. λ©”λͺ¨λ¦¬ λ°˜λ„μ²΄ 가격 μƒμŠΉμœΌλ‘œ μ˜μ—…μ΄μ΅μ΄ μ „λΆ„κΈ° λŒ€λΉ„ 30% μ¦κ°€ν–ˆλ‹€. HBM3E 양산이 λ³Έκ²©ν™”λ˜λ©΄μ„œ AI λ°˜λ„μ²΄ μ‹œμž₯ 점유율이 ν™•λŒ€λ  전망이닀.
 
 
 
 
 
 
 
 
 
 
120
  ```
121
 
122
+ ### Output Example
123
 
124
+ ```
125
+ * [0.8732] [financial ] μ‚Όμ„±μ „μžμ˜ 2024λ…„ 4λΆ„κΈ° 싀적이 μ‹œμž₯ μ˜ˆμƒμ„ μƒνšŒν–ˆλ‹€.
126
+ * [0.7145] [financial ] λ©”λͺ¨λ¦¬ λ°˜λ„μ²΄ 가격 μƒμŠΉμœΌλ‘œ μ˜μ—…μ΄μ΅μ΄ μ „λΆ„κΈ° λŒ€λΉ„ 30% μ¦κ°€ν–ˆλ‹€.
127
+ * [0.9021] [outlook ] HBM3E 양산이 λ³Έκ²©ν™”λ˜λ©΄μ„œ AI λ°˜λ„μ²΄ μ‹œμž₯ 점유율이 ν™•λŒ€λ  전망이닀.
128
+ ```
 
 
129
 
130
+ - `*` ν‘œμ‹œ: λŒ€ν‘œλ¬Έμž₯으둜 선정됨 (score β‰₯ 0.5)
131
+ - `[score]`: λŒ€ν‘œλ¬Έμž₯ ν™•λ₯  (0~1, λ†’μ„μˆ˜λ‘ 핡심 λ¬Έμž₯)
132
+ - `[role]`: λ¬Έμž₯ μ—­ν•  λΆ„λ₯˜ (outlook / event / financial / risk)
 
 
133
 
134
  ## Disclaimer (λ©΄μ±… μ‘°ν•­)
135