Update index.html
Browse files- index.html +10 -10
index.html
CHANGED
|
@@ -187,9 +187,8 @@
|
|
| 187 |
</h4>
|
| 188 |
<p class="publication-meta">
|
| 189 |
<strong>Authors:</strong> <strong>Truong-Phuc Nguyen</strong>,
|
| 190 |
-
Quy-Nhan Nguyen
|
| 191 |
-
|
| 192 |
-
<strong>Status:</strong> Under Writing
|
| 193 |
</p>
|
| 194 |
</div>
|
| 195 |
|
|
@@ -202,9 +201,12 @@
|
|
| 202 |
<strong>Authors:</strong> <strong>Truong-Phuc Nguyen</strong>,
|
| 203 |
Quy-Nhan Nguyen, Manh-Cuong Phan, Chi-Hai Cao, Trinh-Hoai-An
|
| 204 |
Duong, Minh-Tien Nguyen<br />
|
| 205 |
-
<strong>
|
| 206 |
-
|
| 207 |
-
|
|
|
|
|
|
|
|
|
|
| 208 |
</p>
|
| 209 |
</div>
|
| 210 |
|
|
@@ -237,9 +239,7 @@
|
|
| 237 |
<strong>Authors:</strong> Thu-Ha Nguyen,
|
| 238 |
<strong>Truong-Phuc Nguyen</strong>, Khang T. Trung, Huu-Loi Le,
|
| 239 |
Le Thi Viet Huong, Chi Thanh Nguyen, and Minh-Tien Nguyen<br />
|
| 240 |
-
<strong>Published in:</strong> Proceedings of 2024 16th
|
| 241 |
-
International Conference on Knowledge and Systems Engineering
|
| 242 |
-
(KSE), Kuala Lumpur, Malaysia, 2024, pp. 1-6. IEEE<br />
|
| 243 |
<a
|
| 244 |
href="https://doi.org/10.1109/KSE63888.2024.11063637"
|
| 245 |
class="doi-link"
|
|
@@ -315,7 +315,7 @@
|
|
| 315 |
1.72B) models specifically for the legal domain in Vietnam
|
| 316 |
through continual pretraining of language models on large
|
| 317 |
datasets from four sources of authoritative legal documents
|
| 318 |
-
in Vietnam. Legal pretrained models are trained on high-quality
|
| 319 |
large-scale synthetic datasets, compared with 7 state-of-the-art
|
| 320 |
Vietnamese general and legal LMs of the same size across 10
|
| 321 |
benchmarks spanning 4 main tasks: Information Retrieval,
|
|
|
|
| 187 |
</h4>
|
| 188 |
<p class="publication-meta">
|
| 189 |
<strong>Authors:</strong> <strong>Truong-Phuc Nguyen</strong>,
|
| 190 |
+
Quy-Nhan Nguyen & Minh-Tien Nguyen<br />
|
| 191 |
+
<strong>Status:</strong> Submitted to ACL ARR 2026 January Cycle.
|
|
|
|
| 192 |
</p>
|
| 193 |
</div>
|
| 194 |
|
|
|
|
| 201 |
<strong>Authors:</strong> <strong>Truong-Phuc Nguyen</strong>,
|
| 202 |
Quy-Nhan Nguyen, Manh-Cuong Phan, Chi-Hai Cao, Trinh-Hoai-An
|
| 203 |
Duong, Minh-Tien Nguyen<br />
|
| 204 |
+
<strong>Published in:</strong> Proceedings of 2025 17th International Conference on Knowledge and System Engineering (KSE), Da Lat, Vietnam, 2025, pp. 1-5<br />
|
| 205 |
+
<a
|
| 206 |
+
href="https://doi.org/10.1109/KSE68178.2025.11309584"
|
| 207 |
+
class="doi-link"
|
| 208 |
+
target="_blank"
|
| 209 |
+
>DOI: 10.1109/KSE68178.2025.11309584</a>
|
| 210 |
</p>
|
| 211 |
</div>
|
| 212 |
|
|
|
|
| 239 |
<strong>Authors:</strong> Thu-Ha Nguyen,
|
| 240 |
<strong>Truong-Phuc Nguyen</strong>, Khang T. Trung, Huu-Loi Le,
|
| 241 |
Le Thi Viet Huong, Chi Thanh Nguyen, and Minh-Tien Nguyen<br />
|
| 242 |
+
<strong>Published in:</strong> Proceedings of 2024 16th International Conference on Knowledge and System Engineering (KSE), Kuala Lumpur, Malaysia, 2024, pp. 440-446.<br />
|
|
|
|
|
|
|
| 243 |
<a
|
| 244 |
href="https://doi.org/10.1109/KSE63888.2024.11063637"
|
| 245 |
class="doi-link"
|
|
|
|
| 315 |
1.72B) models specifically for the legal domain in Vietnam
|
| 316 |
through continual pretraining of language models on large
|
| 317 |
datasets from four sources of authoritative legal documents
|
| 318 |
+
in Vietnam. Legal pretrained models are trained on 16GB high-quality
|
| 319 |
large-scale synthetic datasets, compared with 7 state-of-the-art
|
| 320 |
Vietnamese general and legal LMs of the same size across 10
|
| 321 |
benchmarks spanning 4 main tasks: Information Retrieval,
|