Update readme
Browse files
README.md
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
### Model and entities
|
| 2 |
-
`roberta_classics_ner` is a domain-specific RoBERTa-
|
| 3 |
|
| 4 |
|
| 5 |
| id | label | desciption | Example |
|
|
@@ -19,6 +19,7 @@
|
|
| 19 |
|
| 20 |
### Example
|
| 21 |
|
|
|
|
| 22 |
```
|
| 23 |
B-AAUTHOR B-AWORK B-REFSCOPE
|
| 24 |
Homer 's Iliad opens with an invocation to the muse ( Il. I. 1).
|
|
@@ -28,7 +29,8 @@ Homer 's Iliad opens with an invocation to the muse ( Il. I. 1).
|
|
| 28 |
|
| 29 |
### Dataset
|
| 30 |
|
| 31 |
-
|
|
|
|
| 32 |
Entity counts of the `Epibau` dataset are the following:
|
| 33 |
|
| 34 |
| | train-set | dev-set | test-set |
|
|
@@ -43,8 +45,10 @@ Entity counts of the `Epibau` dataset are the following:
|
|
| 43 |
|
| 44 |
|
| 45 |
### Results
|
|
|
|
| 46 |
Trained and tested on `EpiBau` with a 85-15 split, the model yields a general F1 score of **.82** (micro-averages). Detailed scores are displayed below. Evaluation was performed with the [CLEF-HIPE-scorer](https://github.com/impresso/CLEF-HIPE-2020-scorer), in strict mode)
|
| 47 |
|
|
|
|
| 48 |
| metric | AAUTHOR | AWORK | REFSCOPE | REFAUWORK |
|
| 49 |
| --------- | ------- | ----- | -------- | --------- |
|
| 50 |
| F1 | .819 | .796 | .863 | .756 |
|
|
@@ -53,3 +57,6 @@ Trained and tested on `EpiBau` with a 85-15 split, the model yields a general F1
|
|
| 53 |
|
| 54 |
|
| 55 |
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
### Model and entities
|
| 2 |
+
`roberta_classics_ner` is a domain-specific RoBERTa-based model for named entity recognition in Classical Studies. It recognises bibliographical entities, such as:
|
| 3 |
|
| 4 |
|
| 5 |
| id | label | desciption | Example |
|
|
|
|
| 19 |
|
| 20 |
### Example
|
| 21 |
|
| 22 |
+
|
| 23 |
```
|
| 24 |
B-AAUTHOR B-AWORK B-REFSCOPE
|
| 25 |
Homer 's Iliad opens with an invocation to the muse ( Il. I. 1).
|
|
|
|
| 29 |
|
| 30 |
### Dataset
|
| 31 |
|
| 32 |
+
|
| 33 |
+
`roberta_classics_ner` was fine-tuned and evaluated on `EpiBau`, a dataset which has not been released publicly yet. It is composed of four volumes of **Structures of Epic Poetry**, a compendium on the narrative patterns and structural elements in ancient epic.
|
| 34 |
Entity counts of the `Epibau` dataset are the following:
|
| 35 |
|
| 36 |
| | train-set | dev-set | test-set |
|
|
|
|
| 45 |
|
| 46 |
|
| 47 |
### Results
|
| 48 |
+
|
| 49 |
Trained and tested on `EpiBau` with a 85-15 split, the model yields a general F1 score of **.82** (micro-averages). Detailed scores are displayed below. Evaluation was performed with the [CLEF-HIPE-scorer](https://github.com/impresso/CLEF-HIPE-2020-scorer), in strict mode)
|
| 50 |
|
| 51 |
+
|
| 52 |
| metric | AAUTHOR | AWORK | REFSCOPE | REFAUWORK |
|
| 53 |
| --------- | ------- | ----- | -------- | --------- |
|
| 54 |
| F1 | .819 | .796 | .863 | .756 |
|
|
|
|
| 57 |
|
| 58 |
|
| 59 |
|
| 60 |
+
|
| 61 |
+
Questions, remarks, help or contribution ? Get in touch [here](https://github.com/AjaxMultiCommentary), we'll be happy to chat !
|
| 62 |
+
|