Published in Information Fusion, 2020
An empirical comparison of fusion strategies for multimodal language analysis.
Recommended citation: Dmitris Gkoumas, Qiuchi Li, Christina Lioma and Dawei Song. (2021). "What makes the difference? An Empirical Comparison of Fusion Strategies for Multimodal Language Analysis." In Information Fusion. https://qiuchili.github.io/files/if2020-2.pdf
Published in Information Fusion, 2020
A quantum-inspired approach to fusing multimodal features for video sentiment analysis.
Recommended citation: Qiuchi Li, Dmitris Gkoumas, Christina Lioma and Massimo Melucci. (2021). "Quantum-inspired Multimodal Fusion for Video Sentiment Analysis." In Information Fusion. https://qiuchili.github.io/files/if2020-1.pdf
Published in The 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020), 2020
A Multi-task Learning Framework for Extracting Opinion Triplet.
Recommended citation: Chen Zhang, Qiuchi Li, Dawei Song and Benyou Wang. "A Multi-task Learning Framework for Opinion Triplet Extraction (2020). " In Findings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020, Long, Findings). https://qiuchili.github.io/files/emnlp20-finding.pdf
Published in Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21), 2020
Approaching video sentiment analysis with a quantum cognitive framework on the decision level.
Recommended citation: Dimitris Gkoumas, Qiuchi Li, Massimo Melucci, Yijun Yu and Dawei Song. (2021). "Quantum Cognitively Motivated Decision Fusion Framework for Video Sentiment Analysis." To appear in Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21). https://qiuchili.github.io/files/aaai20-2.pdf
Published in Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21), 2020
An end-to-end quantum-like approach to emotion recognition in a conversational context.
Recommended citation: Qiuchi Li, Dimitris Gkoumas, Alessandro Sordoni, Jianyun Nie and Massimo Melucci. (2021). "Quantum-inspired Neural Network for Conversational Emotion Recognition." To appear in Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21). https://qiuchili.github.io/files/aaai20-1.pdf
Published in 2020 International Conference on Learning Representations (ICLR 2020), 2019
We encode word order information in a complex-value word embedding mechanism.
Recommended citation: Benyou Wang, Donghao Zhao, Christina Lioma, Qiuchi Li, Peng Zhang and Jakob Grue Simonsen. (2020). "Encoding Word Order in Complex Embeddings." 2020 International Conference on Learning Representations (ICLR 2020). https://qiuchili.github.io/files/iclr20-long.pdf
Published in 2020 European Conference on Artificial Intelligence (ECAI 2020), 2019
We propose novel metrics to assess the memory ability of RNNs.
Recommended citation: Cheng Zhang, Qiuchi Li, Lingyu Hua and Dawei Song. (2020). "Assessing the Memory Ability of Recurrent Neural Networks." 2020 European Conference on Artificial Intelligence (ECAI 2020). https://qiuchili.github.io/files/ecai20-long.pdf
Published in The 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2019), 2019
We build a promixity weighted convolution network for aspect-level sentiment classification.
Recommended citation: Chen Zhang, Qiuchi Li and Dawei Song. (2019). "Syntax-Aware Aspect-Level Sentiment Classification with Proximity-Weighted Convolution Network." To appear in The 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2019). https://qiuchili.github.io/files/sigir19-short.pdf
Published in 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT 2019), 2019
We build a semantic matching network with complex-valued components driven by quantum theory. It outperforms strong baseline question answering (QA) models and exhibits a certain degree of interpretability.
Recommended citation: Qiuchi Li, Benyou Wang and Massimo Melucci. (2019). "CNM: An Interpretable Complex-valued Network for Matching." 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT 2019). https://qiuchili.github.io/files/naacl19-long.pdf
Published in WWW2019 International Workshop on Deep Learning for Graphs and Structured Data Embedding (DL4G-SDE), 2019
We claim the phrase compositionality detection is a contextual task and address the task by considering the context of a phrase.
Recommended citation: Dongsheng Wang, Qiuchi Li, Lucas Chaves Lima, Jakob Grue Simenson and Christina Lioma. (2019). "Contextual Compositionality Detection with External Knowledge Bases and Word Embeddings." WWW2019 International Workshop on Deep Learning for Graphs and Structured Data Embedding (DL4G-SDE). https://qiuchili.github.io/files/www19-workshop.pdf
Published in The 28th International Joint Conference on Artificial Intelligence (IJCAI2019), 2019
We build the first quantum-inspired model for conversational sentiment analysis.
Recommended citation: Yazhou Zhang, Qiuchi Li, Peng Zhang, Panpan Wang and Dawei Song (2019). "Quantum-inspired Interactive Networks for Conversational Sentiment Analysis." The 28th International Joint Conference on Artificial Intelligence (IJCAI2019). https://qiuchili.github.io/files/ijcai19-long.pdf
Published in The Web Conference 2019 (WWW2019), 2019
We introduce the Semantic Hilbert Space to model different levels of linguistics units, and build a complex-valued network to implement the framework for text classification.
Recommended citation: Benyou Wang, Qiuchi Li, Massimo Melucci and Dawei Song. (2019). "Semantic Hilbert Space for Text Representation Learning." The Web Conference 2019 (WWW2019) . https://qiuchili.github.io/files/www19-short.pdf
Published in The 4th ACM SIGIR International Conference on the Theory of Information Retrieval (ICTIR 2018), 2018
We build a query expansion framework based on the improved quantum language model (QLM).
Recommended citation: Qiuchi Li, Massimo Melucci and Prayag Tiwari. (2018). "Quantum Language Model-based Query Expansion." The 4th ACM SIGIR International Conference on the Theory of Information Retrieval (ICTIR 2018). pp.183-186. https://qiuchili.github.io/files/ictir18-short.pdf
Published in The 4th ACM SIGIR International Conference on the Theory of Information Retrieval (ICTIR 2018), 2018
We propose a binary classification model, inspired by the quantum signal detection theory.
Recommended citation: Emanuele Di Buccio, Qiuchi Li, Massimo Melucci and Prayag Tiwari. (2018). "Binary Classification Model Inspired from Quantum Detection Theory." The 4th ACM SIGIR International Conference on the Theory of Information Retrieval (ICTIR 2018). pp.187-190. https://qiuchili.github.io/files/ictir18-short-2.pdf
Published in the 3rd ACL Workshop on Representation Learning for NLP (Rep4NLP), 2018
We build a complex-valued word embedding approach, inspired by quantum theory and quantum probability.
Recommended citation: Qiuchi Li, Sagar Uprety, Benyou Wang and Dawei Song. (2018). "Quantum-inspired Complex Word Embedding." the 3rd ACL Workshop on Representation Learning for NLP (RepL4NLP). https://qiuchili.github.io/files/acl18-workshop.pdf
Published in the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR2015), 2015
We propose a Session-based Quantum Language Model (SQLM) that deals with multi-query session search task.
Recommended citation: Qiuchi Li, Jingfei Li, Peng Zhang and Dawei Song. (2015). "Modeling Multi-query Retrieval Tasks Using Density Matrix Transformation." Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval. pp. 871-874. https://qiuchili.github.io/files/sigir15-short.pdf
Published in The 8th ACL SIGHAN Workshop on Chinese Language Processing (SIGHAN-8), 2015
We report our system for Chinese microblog sentiment analysis task in SIGHAN-8 bakeoff.
Recommended citation: Qiuchi Li, Qiyu Zhi and Miao Li. (2015). "A Combined Sentiment Classification System for SIGHAN-8." The 8th ACL SIGHAN Workshop on Chinese Language Processing (SIGHAN-8). https://qiuchili.github.io/files/acl15-workshop.pdf