Text Matching is a core problem in natural language understanding. Many natural language processing tasks can be abstracted into text matching problems, such as Semantic Textual Similarity(STS), Answer/Response Selection(QA/Chatbot), Natural Language Inference(NLI), and Information Retrieval(IR). Since text matching has a wide application field, the knowledge system is complicated, and the research is difficult, this project plans to integrate and classify the different tasks of applying text matching models in the field of natural language processing, so as to help students who love natural language processing to better understand the concept and application of text matching from the perspective of different tasks.
Here is the first version of the project. The main goal is to organize papers for different tasks, including Semantic Textual Similarity(STS), Natural Language Inference(NLI), Answer/Response Selection(QA/Chatbot), and Image-Text Matching(MultiModal). The research time is mainly from 2013 to 2019. The research will include ACL, EMNLP, NAACL, COLING, CONLL, TACL and other NLP conferences, AAAI, IJCAI, ICLR, ICML, NIPS and other AI mainstream conferences, as well as IR conferences such as SIGIR, CIKM, ICDM. It also plans to open source the second release in the first half of the year, adding Information Retrieval(IR) related content as well as a revision and completion of the overall.
At present, we have collected a total of 273 papers as follows, including 103 for text matching/semantic textual similarity, 22 for image-text matching, 69 for answer/reponse selection and 79 for natural language inference/textual entailment. The focus of our future work will be mainly organized in a more fine-grained direction, real-time update of the innovation and application of matching methods, code reproduction work for important papers, etc.
The organizer is a 2016 undergraduate from Zhengzhou University, and his instructor during the undergraduate period was Hongying Zan. Currently studying for a master's degree in Beijing Institute of Technology's natural language processing team, and the instructor is Heyan Huang. Also thanks for Hanlin Tang, a PhD student in Computer Science at Beijing Institute of Technology, has done a lot of work in project organization. Other contributors are as follows. If anyone wants to join us to study in the field of text matching or to give valuable suggestions, please send a message to my email, [email protected], we look forward to your participation or guidance.
-
Peiyuan Gong (bit)
-
Hanlin Tang (bit)
-
Tongfeng Guan (zzu)
-
Shuai Ye (zju)
-
Xiangwei Wang (bit)