{"id":36632,"date":"2022-08-19T22:26:55","date_gmt":"2022-08-19T14:26:55","guid":{"rendered":"https:\/\/swarma.org\/?p=36632"},"modified":"2022-08-19T22:26:55","modified_gmt":"2022-08-19T14:26:55","slug":"%e5%a4%a7%e8%af%ad%e8%a8%80%e6%a8%a1%e5%9e%8b%e5%92%8c%e7%a4%be%e4%bc%9a%e7%a7%91%e5%ad%a6%e7%a0%94%e7%a9%b6%ef%bc%9a%e6%95%88%e7%8e%87%e4%b8%8e%e8%b6%a3%e5%91%b3-%e5%91%a8%e5%85%ad%e7%9b%b4","status":"publish","type":"post","link":"https:\/\/swarma.org\/?p=36632","title":{"rendered":"\u5927\u8bed\u8a00\u6a21\u578b\u548c\u793e\u4f1a\u79d1\u5b66\u7814\u7a76\uff1a\u6548\u7387\u4e0e\u8da3\u5473 | \u5468\u516d\u76f4\u64ad\u00b7\u8ba1\u7b97\u793e\u4f1a\u79d1\u5b66\u8bfb\u4e66\u4f1a"},"content":{"rendered":"
\n
\n
\n
\n

<\/p>\n<\/section>\n

\n
\n
\n
\n
\n
\n

<\/section>\n<\/section>\n
\n
\n

\u5bfc\u8bed<\/strong><\/p>\n<\/section>\n<\/section>\n

\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n
\n
\n
\n

<\/strong>\u8ba1\u7b97\u793e\u4f1a\u79d1\u5b66\u8bfb\u4e66\u4f1a\u7b2c\u4e8c\u5b63<\/span><\/strong><\/a>\u7b2c\u516b\u671f\u8bfb\u4e66\u4f1a\uff0c\u6211\u4eec\u9080\u8bf7\u5230\u675c\u4f26\u5927\u5b66\u8ba1\u7b97\u673a\u7cfb\u535a\u58eb\u8096\u7a0b\u660a\uff0c\u56f4\u7ed5\u6548\u7387\u4e0e\u8da3\u5473\u4e24\u4e2a\u89d2\u5ea6\uff0c\u4ecb\u7ecd\u57fa\u4e8e\u5927\u8bed\u8a00\u6a21\u578b\u7684\u9ad8\u6548\u7684\u6587\u672c\u6316\u6398\u65b9\u6cd5\u548c\u6848\u4f8b\uff0c\u8bb2\u89e3\u5927\u8bed\u8a00\u6a21\u578b\u5982\u4f55\u4ee5\u4e24\u79cd\u4e0d\u540c\u7684\u8303\u5f0f\u88ab\u7ed3\u5408\u5728\u6709\u8da3\u7684\u8bed\u8a00\u6982\u5ff5\u7814\u7a76\u4e2d\u3002\u672c\u6b21\u5206\u4eab\u65e8\u5728\u4e0d\u4ec5\u63d0\u4f9b\u9ad8\u6548\u3001\u7b80\u6613\u7684\u81ea\u7136\u8bed\u8a00\u5904\u7406\u7814\u7a76\u5de5\u5177\uff0c\u800c\u4e14\u63d0\u4f9b\u6709\u8da3\u3001\u5de7\u5999\u7684\u7814\u7a76\u601d\u8def\uff0c \u5e0c\u671b\u80fd\u5bf9\u8ba1\u7b97\u793e\u4f1a\u79d1\u5b66\u5176\u4ed6\u7814\u7a76\u63d0\u4f9b\u4e00\u5b9a\u7684\u542f\u53d1\u6027\u548c\u8f6c\u79fb\u6027\u3002\u672c\u671f\u8bfb\u4e66\u4f1a\u65f6\u95f4\u4e3a\uff1a8\u670820\u65e5\uff08\u5468\u516d\uff09\u665a\u4e0a20:00 – 22:00\uff0c\u76f4\u64ad\u62a5\u540d\u5165\u53e3\u89c1\u540e\u6587\u3002<\/strong><\/strong><\/strong><\/p>\n


<\/p>\n

\u3010\u8ba1\u7b97\u793e\u4f1a\u79d1\u5b66\u8bfb\u4e66\u4f1a\u7b2c\u4e8c\u5b63<\/a>\u3011\u7531\u6e05\u534e\u5927\u5b66\u7f57\u5bb6\u5fb7\u6559\u6388\u9886\u8854\uff0c\u5361\u5185\u57fa\u6885\u9686\u5927\u5b66\u3001\u5bc6\u6b47\u6839\u5927\u5b66\u3001\u6e05\u534e\u5927\u5b66\u3001\u5339\u5179\u5821\u5927\u5b66\u7684\u591a\u4f4d\u535a\u58eb\u751f\u8054\u5408\u53d1\u8d77\uff0c\u81ea2022\u5e746\u670818\u65e5\u5f00\u59cb\uff0c\u6301\u7eed10-12\u5468\u3002\u672c\u5b63\u8bfb\u4e66\u5c06\u805a\u7126\u8ba8\u8bbaGraph\u3001Embedding\u3001NLP\u3001Modeling\u3001Data collection\u7b49\u65b9\u6cd5\u53ca\u5176\u4e0e\u793e\u4f1a\u79d1\u5b66\u95ee\u9898\u7684\u7ed3\u5408\uff0c\u5e76\u9488\u5bf9\u6027\u8ba8\u8bba\u9884\u6d4b\u6027\u4e0e\u89e3\u91ca\u6027\u3001\u65b0\u51a0\u75ab\u60c5\u7814\u7a76\u7b49\u8bfe\u9898\u3002\u8bfb\u4e66\u4f1a\u8be6\u60c5\u53ca\u53c2\u4e0e\u65b9\u5f0f\u89c1\u6587\u672b\uff0c\u6b22\u8fce\u4ece\u4e8b\u76f8\u5173\u7814\u7a76\u6216\u5bf9\u8ba1\u7b97\u793e\u4f1a\u79d1\u5b66\u611f\u5174\u8da3\u7684\u670b\u53cb\u62a5\u540d\u53c2\u52a0\uff01<\/strong><\/span><\/strong><\/p>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n

\n
\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n
\n
<\/section>\n<\/section>\n

<\/section>\n

<\/h4>\n
<\/section>\n

<\/section>\n

<\/span><\/section>\n

\n
\n
\n
\n
\n

<\/section>\n

<\/section>\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n
\n

\u672c\u671f\u5206\u4eab<\/strong><\/strong><\/p>\n

\u4e0e\u8ba1\u7b97\u793e\u4f1a\u79d1\u5b66\u8bfb\u4e66\u4f1a\u4e4b\u95f4\u7684\u5173\u7cfb<\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/h3>\n

<\/section>\n

<\/span><\/h4>\n
\u9884\u8bad\u7ec3\u8bed\u8a00\u6a21\u578b\u56e0\u5176\u5728\u4e0b\u6e38\u4efb\u52a1\u4f18\u79c0\u7684\u6548\u679c\uff0c\u9010\u6e10\u5728\u793e\u4f1a\u79d1\u5b66\u7814\u7a76\u4e2d\u53d7\u5230\u91cd\u89c6\u3002\u672c\u671f\u901a\u8fc7\u6548\u7387\u4e0e\u8da3\u5473\u4e24\u4e2a\u89d2\u5ea6\uff0c\u8bb2\u89e3\uff081\uff09\u57fa\u4e8e\u5927\u8bed\u8a00\u6a21\u578b\u7684\u9ad8\u6548\u7684\u6587\u672c\u6316\u6398\u65b9\u6cd5\u548c\u6848\u4f8b\uff0c\uff082\uff09\u5927\u8bed\u8a00\u6a21\u578b\u5982\u4f55\u4ee5\u4e24\u79cd\u4e0d\u540c\u7684\u8303\u5f0f\u88ab\u7ed3\u5408\u5728\u6709\u8da3\u7684\u8bed\u8a00\u6982\u5ff5\u7814\u7a76\u4e2d\u3002\u672c\u671f\u5206\u4eab\u65e8\u5728\u4e0d\u4ec5\u63d0\u4f9b\u9ad8\u6548\u3001\u7b80\u6613\u7684\u81ea\u7136\u8bed\u8a00\u5904\u7406\u7814\u7a76\u5de5\u5177\uff0c\u800c\u4e14\u63d0\u4f9b\u6709\u8da3\u3001\u5de7\u5999\u7684\u7814\u7a76\u601d\u8def\uff0c \u5e0c\u671b\u80fd\u5bf9\u8ba1\u7b97\u793e\u4f1a\u79d1\u5b66\u5176\u4ed6\u7814\u7a76\u63d0\u4f9b\u4e00\u5b9a\u7684\u542f\u53d1\u6027\u548c\u8f6c\u79fb\u6027\u3002<\/span><\/section>\n

<\/span><\/section>\n

<\/span><\/section>\n

\n
\n
\n
\n
\n

<\/section>\n

<\/section>\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n
\n

\u4e3b\u8981\u6d89\u53ca\u5230\u7684\u77e5\u8bc6\u6982\u5ff5<\/strong><\/strong><\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/h3>\n

<\/section>\n

\u9884\u8bad\u7ec3\u8bed\u8a00\u6a21\u578b (Pre-trained Language Models, PLMs)<\/span><\/p>\n

\u53e5\u5b50\u8868\u793a\/\u53e5\u5b50\u5d4c\u5165 (Sentence Representation\/Sentence Embedding)<\/span><\/section>\n


<\/h4>\n


<\/p>\n

\n
\n
\n
\n
\n

<\/section>\n

<\/section>\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n
\n

\u5206\u4eab\u7b80\u4ecb<\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/h3>\n

<\/section>\n
\u672c\u6b21\u5206\u4eab\u7b2c\u4e00\u90e8\u5206\u627f\u63a5\u7b2c\u4e09<\/a>\u7b2c\u56db<\/a>\u671fembedding\u7684\u5185\u5bb9\uff0c\u4ecb\u7ecd\u53e5\u5b50\u8868\u793a\u65b9\u6cd5\u4ee5\u53ca\u57fa\u4e8e\u6b64\u7684\u9ad8\u6548\u6587\u672c\u6316\u6398\u6846\u67b6\uff1b\u7b2c\u4e8c\u90e8\u5206\u627f\u63a5\u7b2c\u4e03\u671f<\/a>\u7684\u5185\u5bb9\uff0c\u4ee5\u4e24\u7bc7\u6709\u8da3\u7684\u7814\u7a76\u4e3a\u6848\u4f8b\uff0c\u4ecb\u7ecd\u4e24\u79cd\u4e0d\u9700\u8981\u4eba\u5de5\u6807\u6ce8\u7684\u5229\u7528NLP\u8fdb\u884c\u6982\u5ff5\u7814\u7a76\u7684\u8303\u5f0f\u3002<\/span><\/section>\n


<\/h4>\n


<\/p>\n

\n
\n
\n
\n
\n

<\/section>\n

<\/section>\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n
\n

\u5206\u4eab\u5927\u7eb2<\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/h3>\n

<\/section>\n

1. Embedding\u7eed\u8c08<\/span><\/p>\n

a.<\/span>\u5927\u6a21\u578b\u7684\u7f3a\u9677\u4e0e\u53e5\u5b50\u8868\u793a\u65b9\u6cd5<\/span><\/section>\n
b. \u57fa\u4e8e\u53e5\u5b50\u8868\u793a\u7684\u9ad8\u6548\u6587\u672c\u6316\u6398\u65b9\u6cd5&\u6848\u4f8b<\/span><\/section>\n

2. \u7528NLP\u7814\u7a76\u6709\u8da3\u7684\u8bed\u8a00\u5b66\u6982\u5ff5\uff1a<\/span>\u6848\u4f8b\u4e2d\u7684\u4e24\u79cd\u8303\u5f0f<\/span><\/p>\n

a. \u6848\u4f8b\u4e00\uff1a<\/span>\u7528NLP\u7814\u7a76\u5e7d\u9ed8<\/span><\/section>\n
b. \u6848\u4f8b\u4e8c\uff1a<\/span>\u7528NLP\u7814\u7a76\u4fda\u8bed<\/span><\/section>\n


<\/span><\/p>\n


<\/span><\/p>\n

\n
\n
\n
\n
\n

<\/section>\n

<\/section>\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n
\n

\u4e3b\u8bb2\u4eba\u7b80\u4ecb<\/strong><\/strong><\/p>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/h3>\n


<\/section>\n
<\/section>\n
\u8096\u7a0b\u660a<\/span><\/strong>\uff0c\u675c\u4f26\u5927\u5b66\u8ba1\u7b97\u673a\u7cfb\u535a\u4e00\u5728\u8bfb\u3002<\/span>\u7814\u7a76\u65b9\u5411\u4e3a\u81ea\u7136\u8bed\u8a00\u5904\u7406\uff0c\u7814\u7a76\u56f4\u7ed5\u4fe1\u606f\u83b7\u53d6\u7684\u6548\u7387\u4e0e\u516c\u5e73\u4e24\u4e2a\u7ef4\u5ea6\u8fdb\u884c\uff0c\u81f4\u529b\u4e8eNLP for social good\u3002<\/span>\u73b0\u9636\u6bb5\u4e3b\u8981\u5173\u6ce8\u7684\u95ee\u9898\u662f\uff081\uff09\u6784\u5efa\u9ad8\u6548\u3001\u8f7b\u91cf\u7ea7\u7684\u57fa\u4e8e\u53e5\u5b50\u8868\u793a\u7684\u4fe1\u606f\u83b7\u53d6\u6846\u67b6\uff082\uff09\u4f7f\u7528\u8bed\u8a00\u6a21\u578b\u4f5c\u4e3a\u5916\u90e8\u7ea6\u675f\uff0c\u5e2e\u52a9\u4e0d\u540c\u793e\u4f1a\u9636\u5c42\u7684\u7528\u6237\u9003\u79bb\u4fe1\u606f\u8327\u623f\u3002<\/span>\u4ed6\u7684\u4e2a\u4eba\u4e3b\u9875\u662f\uff1a<\/span>https:\/\/haii.webspace.durham.ac.uk\/chenghao-xiao\/<\/span>
<\/section>\n


<\/h4>\n


<\/p>\n

\n
\n
\n
\n
\n

<\/section>\n

<\/section>\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n
\n

\u53c2\u8003\u6587\u732e<\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/h3>\n

<\/section>\n

<\/span><\/h4>\n
\n
\u672c\u6b21\u89e3\u8bfb\u7684\u6587\u7ae0<\/span><\/strong><\/section>\n
1. Xiao, C., Shi, L., Cristea, A., Li, Z. and Pan, Z., 2022. Fine-grained Main Ideas Extraction and Clustering of Online Course Reviews. In International Conference on Artificial Intelligence in Education (pp. 294-306). Springer, Cham.<\/span><\/section>\n
2. Yang, Z., Hooshmand, S. and Hirschberg, J., 2021, November. CHoRaL: Collecting humor reaction labels from millions of social media users. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (pp. 4429-4435).<\/span><\/section>\n
3. Keidar, D., Opedal, A., Jin, Z. and Sachan, M., 2022, May. Slangvolution: A Causal Analysis of Semantic Change and Frequency Dynamics in Slang. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 1422-1442).<\/span><\/section>\n<\/h5>\n
\n

<\/section>\n
\u53c2\u8003\u7684\u6587\u7ae0<\/span><\/strong><\/span><\/section>\n

1. Reimers, N. and Gurevych, I., 2019, November. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (pp. 3982-3992).<\/span><\/p>\n

2. Gao, T., Yao, X. and Chen, D., 2021, November. SimCSE: Simple Contrastive Learning of Sentence Embeddings. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (pp. 6894-6910).<\/span><\/p>\n<\/h5>\n


<\/section>\n

<\/section>\n

<\/section>\n

\n
\n
\n
\n
\n

<\/section>\n

<\/section>\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n
\n

\u76f4\u64ad\u4fe1\u606f<\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/h3>\n

<\/section>\n
\u76f4\u64ad\u65f6\u95f4\uff1a<\/span><\/strong><\/span><\/section>\n
2<\/span>022\u5e748\u670820\u65e5\uff08\u5468\u516d\uff09\u665a\u4e0a20:00 – 22:00<\/span><\/section>\n

<\/section>\n
\u53c2\u4e0e\u65b9\u5f0f\uff1a<\/span><\/strong><\/span><\/section>\n