update

index.html

@@ -411,7 +411,7 @@ <h4><alert>Educational NLP</alert></h4>
                 title="MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solvers">
                 <div><strong>MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solvers</strong><br>
                     Yihuai Lan, Lei Wang, Qiyuan Zhang, <strong>Yunshi Lan#</strong>, Bing Tian Dai, Yan Wang, Dongxiang Zhang, Ee-Peng Lim<br>
-                    AAAI demo, 2022 <br>
+                    AAAI, demo paper, 2022 <br>
                     <a href="https://arxiv.org/pdf/2109.00799.pdf">[Paper]</a>
                     <a href="https://mp.weixin.qq.com/s/2lLInVAMZ7s_8pc1A5Czjg">[中文解读]</a>
                     <a href="https://github.com/LYH-YF/MWPToolkit">[GitHub Page]</a>
@@ -424,7 +424,7 @@ <h4><alert>Educational NLP</alert></h4>
             <div class="paper"><img class="paper" src="./resources/paper_icon/nlpcc2023_csc.png"
                 title="Towards Robust Chinese Spelling Check Systems: Multi-round Error Correction with Ensemble Enhancement">
                 <div><strong>Towards Robust Chinese Spelling Check Systems: Multi-round Error Correction with Ensemble Enhancement</strong><br>
-                    Alex Xiang Li and Hanyue Du and Yike Zhao and <strong>Yunshi Lan#</strong><br>
+                    Alex Xiang Li, Hanyue Du, Yike Zhao, <strong>Yunshi Lan#</strong><br>
                     NLPCC, evaluation paper, 2023 <br>
                     <a href="https://drive.google.com/file/d/1DZOZfUwnaTmQrpv7TUgDgtX0Ga6cdvbB/view">[Paper]</a>
                     <a href="https://github.com/Ashura5/MECEE">[GitHub Page]</a>
@@ -448,6 +448,17 @@ <h4><alert>Educational NLP</alert></h4>
                 </div>
                 <div class="spanner"></div>
             </div>
+            <div class="paper"><img class="paper" src="./resources/paper_icon/coling2024-textsimplification.png"
+                title="An LLM-Enhanced Adversarial Editing System for Lexical Simplification">
+                <div><strong>An LLM-Enhanced Adversarial Editing System for Lexical Simplification</strong><br>
+                    Keren Tan, Kangyang Luo, <strong>Yunshi Lan#</strong>, Zheng Yuan and Jinlong Shu<br>
+                    COLING, 2024 <br>
+                    <a href="https://arxiv.org/abs/2402.14704">[Paper]</a>
+                    <br>
+                    We propose a novel LS method without parallel corpora, which includes an innovative LLM-enhanced loss to enable the distillation of knowledge from Large Language Models (LLMs) into a small-size LS system.
+                </div>
+                <div class="spanner"></div>
+            </div>
         </div>
     </div>
     <br>

resources/bibtex/coling2024_ts.txt

@@ -0,0 +1,17 @@
+@inproceedings{tan_coling2024,
+author = {Tan, Keren and Luo, Kangyang and Lan, Yunshi and Yuan, Zheng and She, Jinlong},
+title = {An LLM-Enhanced Adversarial Editing System for Lexical Simplification},
+year = {2024},
+isbn = {9798400701245},
+publisher = {Association for Computing Machinery},
+address = {New York, NY, USA},
+url = {https://doi.org/10.1145/3583780.3615119},
+doi = {10.1145/3583780.3615119},
+abstract = {Chinese Grammatical Error Correction (CGEC) has been attracting growing attention from researchers recently. In spite of the fact that multiple CGEC datasets have been developed to support the research, these datasets lack the ability to provide a deep linguistic topology of grammar errors, which is critical for interpreting and diagnosing CGEC approaches. To address this limitation, we introduce FlaCGEC, which is a new CGEC dataset featured with fine-grained linguistic annotation. Specifically, we collect raw corpus from the linguistic schema defined by Chinese language experts, conduct edits on sentences via rules, and refine generated samples manually, which results in 10k sentences with 78 instantiated grammar points and 3 types of edits. We evaluate various cutting-edge CGEC methods on the proposed FlaCGEC dataset and their unremarkable results indicate that this dataset is challenging in covering a large range of grammatical errors. In addition, we also treat FlaCGEC as a diagnostic dataset for testing generalization skills and conduct a thorough evaluation of existing CGEC models.},
+booktitle = {Proceedings of the 32nd ACM International Conference on Information and Knowledge Management},
+pages = {5321–5325},
+numpages = {5},
+keywords = {deep learning, fine-grained linguistic annotation, Chinese grammatical error correction},
+location = {Birmingham, United Kingdom},
+series = {CIKM '23}
+}