FremyCompany
commited on
Commit
•
eba56ab
1
Parent(s):
584ab2b
Update citation to ACL Anthology version
Browse files
README.md
CHANGED
@@ -36,15 +36,19 @@ This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentence
|
|
36 |
This model accompanies the [BioLORD: Learning Ontological Representations from Definitions](https://arxiv.org/abs/2210.11892) paper, accepted in the EMNLP 2022 Findings. When you use this model, please cite the original paper as follows:
|
37 |
|
38 |
```latex
|
39 |
-
@
|
40 |
-
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
|
|
|
|
|
|
|
|
48 |
}
|
49 |
```
|
50 |
|
|
|
36 |
This model accompanies the [BioLORD: Learning Ontological Representations from Definitions](https://arxiv.org/abs/2210.11892) paper, accepted in the EMNLP 2022 Findings. When you use this model, please cite the original paper as follows:
|
37 |
|
38 |
```latex
|
39 |
+
@inproceedings{remy-etal-2022-biolord,
|
40 |
+
title = "{B}io{LORD}: Learning Ontological Representations from Definitions for Biomedical Concepts and their Textual Descriptions",
|
41 |
+
author = "Remy, François and
|
42 |
+
Demuynck, Kris and
|
43 |
+
Demeester, Thomas",
|
44 |
+
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
|
45 |
+
month = dec,
|
46 |
+
year = "2022",
|
47 |
+
address = "Abu Dhabi, United Arab Emirates",
|
48 |
+
publisher = "Association for Computational Linguistics",
|
49 |
+
url = "https://aclanthology.org/2022.findings-emnlp.104",
|
50 |
+
pages = "1454--1465",
|
51 |
+
abstract = "This work introduces BioLORD, a new pre-training strategy for producing meaningful representations for clinical sentences and biomedical concepts. State-of-the-art methodologies operate by maximizing the similarity in representation of names referring to the same concept, and preventing collapse through contrastive learning. However, because biomedical names are not always self-explanatory, it sometimes results in non-semantic representations. BioLORD overcomes this issue by grounding its concept representations using definitions, as well as short descriptions derived from a multi-relational knowledge graph consisting of biomedical ontologies. Thanks to this grounding, our model produces more semantic concept representations that match more closely the hierarchical structure of ontologies. BioLORD establishes a new state of the art for text similarity on both clinical sentences (MedSTS) and biomedical concepts (MayoSRS).",
|
52 |
}
|
53 |
```
|
54 |
|