ACL Anthology
Browse files
README.md
CHANGED
@@ -34,7 +34,7 @@ Its input is the usage example and the instruction question "What is the definit
|
|
34 |
|
35 |
## Model description
|
36 |
|
37 |
-
See details in the paper [Enriching Word Usage Graphs with Cluster Definitions](https://
|
38 |
Mariia Fedorova, Andrey Kutuzov, Nikolay Arefyev and Dominik Schlechtweg.
|
39 |
|
40 |
## Intended uses & limitations
|
@@ -87,3 +87,26 @@ The following hyperparameters were used during training:
|
|
87 |
- Tokenizers 0.12.1
|
88 |
|
89 |
## Citation
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
|
35 |
## Model description
|
36 |
|
37 |
+
See details in the paper [Enriching Word Usage Graphs with Cluster Definitions](https://aclanthology.org/2024.lrec-main.546/) (LREC-COLING'2024) by
|
38 |
Mariia Fedorova, Andrey Kutuzov, Nikolay Arefyev and Dominik Schlechtweg.
|
39 |
|
40 |
## Intended uses & limitations
|
|
|
87 |
- Tokenizers 0.12.1
|
88 |
|
89 |
## Citation
|
90 |
+
```
|
91 |
+
@inproceedings{kutuzov-etal-2024-enriching-word,
|
92 |
+
title = "Enriching Word Usage Graphs with Cluster Definitions",
|
93 |
+
author = "Kutuzov, Andrey and
|
94 |
+
Fedorova, Mariia and
|
95 |
+
Schlechtweg, Dominik and
|
96 |
+
Arefyev, Nikolay",
|
97 |
+
editor = "Calzolari, Nicoletta and
|
98 |
+
Kan, Min-Yen and
|
99 |
+
Hoste, Veronique and
|
100 |
+
Lenci, Alessandro and
|
101 |
+
Sakti, Sakriani and
|
102 |
+
Xue, Nianwen",
|
103 |
+
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
|
104 |
+
month = may,
|
105 |
+
year = "2024",
|
106 |
+
address = "Torino, Italia",
|
107 |
+
publisher = "ELRA and ICCL",
|
108 |
+
url = "https://aclanthology.org/2024.lrec-main.546",
|
109 |
+
pages = "6189--6198",
|
110 |
+
abstract = "We present a dataset of word usage graphs (WUGs), where the existing WUGs for multiple languages are enriched with cluster labels functioning as sense definitions. They are generated from scratch by fine-tuned encoder-decoder language models. The conducted human evaluation has shown that these definitions match the existing clusters in WUGs better than the definitions chosen from WordNet by two baseline systems. At the same time, the method is straightforward to use and easy to extend to new languages. The resulting enriched datasets can be extremely helpful for moving on to explainable semantic change modeling.",
|
111 |
+
}
|
112 |
+
```
|