Weijian Xie - Academia.edu (original) (raw)

Papers by Weijian Xie

Proceedings of the AAAI Conference on Artificial Intelligence

Procedural text understanding requires machines to reason about entity states within the dynamica... more Procedural text understanding requires machines to reason about entity states within the dynamical narratives. Current procedural text understanding approaches are commonly entity-wise, which separately track each entity and independently predict different states of each entity. Such an entity-wise paradigm does not consider the interaction between entities and their states. In this paper, we propose a new scene-wise paradigm for procedural text understanding, which jointly tracks states of all entities in a scene-by-scene manner. Based on this paradigm, we propose Scene Graph Reasoner (SGR), which introduces a series of dynamically evolving scene graphs to jointly formulate the evolution of entities, states and their associations throughout the narrative. In this way, the deep interactions between all entities and states can be jointly captured and simultaneously derived from scene graphs. Experiments show that SGR not only achieves the new state-of-the-art performance but also sig...

ACL, 2021

Current event-centric knowledge graphs highly rely on explicit connectives to mine relations betw... more Current event-centric knowledge graphs highly rely on explicit connectives to mine relations between events. Unfortunately, due to the sparsity of connectives, these methods severely undermine the coverage of EventKGs. The lack of high-quality labelled corpora further exacerbates that problem. In this paper, we propose a knowledge projection paradigm for event relation extraction: projecting discourse knowledge to narratives by exploiting the commonalities between them. Specifically, we propose Multi-tier Knowledge Projection Network (MKPNet), which can leverage multi-tier discourse knowledge effectively for event relation extraction. In this way, the labelled data requirement is significantly reduced, and implicit event relations can be effectively extracted. Intrinsic experimental results show that MKPNet achieves the new state-of-the-art performance, and extrinsic experimental results verify the value of the extracted event relations.

2019 International Joint Conference on Neural Networks (IJCNN), Jul 1, 2019

Question Answering (QA) systems are used to provide proper responses to users' questions automati... more Question Answering (QA) systems are used to provide proper responses to users' questions automatically. Sentence matching is an essential task in the QA systems and is usually reformulated as a Paraphrase Identification (PI) problem. Given a question, the aim of the task is to find the most similar question from a QA knowledge base. In this paper, we propose a Multi-task Sentence Encoding Model (MSEM) for the PI problem, wherein a connected graph is employed to depict the relation between sentences, and a multi-task learning model is applied to address both the sentence matching and sentence intent classification problem. In addition, we implement a general semantic retrieval framework that combines our proposed model and the Approximate Nearest Neighbor (ANN) technology, which enables us to find the most similar question from all available candidates very quickly during online serving. The experiments show the superiority of our proposed method as compared with the existing sentence matching models.

Proceedings of the 28th International Conference on Computational Linguistics

Proceedings of the Eighth SIGHAN Workshop on Chinese Language Processing, 2015

This paper presents our Chinese microblog sentiment classification (CMSC) system in the Topic-Bas... more This paper presents our Chinese microblog sentiment classification (CMSC) system in the Topic-Based Chinese Message Polarity Classification task of SIGHAN-8 Bake-Off. Given a message from Chinese Weibo platform and a topic, our system is designed to classify whether the message is of positive, negative, or neutral sentiment towards the given topic. Due to the difficulties like the out-ofvocabulary Internet words and emoticons, polarity classification of Chinese microblogs is still an open problem today. In our system, Maximum Entropy (MaxEnt) is employed, which is a discriminative model that directly models the class posteriors, allowing them to incorporate a rich set of features. Moreover, oversampling approach is used to hand the unbalance problem. Evaluation results demonstrate the utility of our system, showing an accuracy of 66.4% for restricted resource and 66.6% for unrestricted resource.

Proceedings of The Third CIPS-SIGHAN Joint Conference on Chinese Language Processing, 2014

This paper describes our system in the Chinese spelling check (CSC) task of CLP-SIGHAN Bake-Off 2... more This paper describes our system in the Chinese spelling check (CSC) task of CLP-SIGHAN Bake-Off 2014. CSC is still an open problem today. To the best of our knowledge, n-gram language modeling (LM) is widely used in CSC because of its simplicity and fair predictive power. Our work in this paper continues this general line of research by using a tri-gram LM to detect and correct possible spelling errors. In addition, we use dynamic programming to improve the efficiency of the algorithm, and additive smoothing to solve the data sparseness problem in training set. Empirical evaluation results demonstrate the utility of our CSC system.

Proceedings of the Eighth SIGHAN Workshop on Chinese Language Processing, 2015

Proceedings of the AAAI Conference on Artificial Intelligence

Procedural text understanding requires machines to reason about entity states within the dynamica... more Procedural text understanding requires machines to reason about entity states within the dynamical narratives. Current procedural text understanding approaches are commonly entity-wise, which separately track each entity and independently predict different states of each entity. Such an entity-wise paradigm does not consider the interaction between entities and their states. In this paper, we propose a new scene-wise paradigm for procedural text understanding, which jointly tracks states of all entities in a scene-by-scene manner. Based on this paradigm, we propose Scene Graph Reasoner (SGR), which introduces a series of dynamically evolving scene graphs to jointly formulate the evolution of entities, states and their associations throughout the narrative. In this way, the deep interactions between all entities and states can be jointly captured and simultaneously derived from scene graphs. Experiments show that SGR not only achieves the new state-of-the-art performance but also sig...

ACL, 2021

Current event-centric knowledge graphs highly rely on explicit connectives to mine relations betw... more Current event-centric knowledge graphs highly rely on explicit connectives to mine relations between events. Unfortunately, due to the sparsity of connectives, these methods severely undermine the coverage of EventKGs. The lack of high-quality labelled corpora further exacerbates that problem. In this paper, we propose a knowledge projection paradigm for event relation extraction: projecting discourse knowledge to narratives by exploiting the commonalities between them. Specifically, we propose Multi-tier Knowledge Projection Network (MKPNet), which can leverage multi-tier discourse knowledge effectively for event relation extraction. In this way, the labelled data requirement is significantly reduced, and implicit event relations can be effectively extracted. Intrinsic experimental results show that MKPNet achieves the new state-of-the-art performance, and extrinsic experimental results verify the value of the extracted event relations.

2019 International Joint Conference on Neural Networks (IJCNN), Jul 1, 2019

Question Answering (QA) systems are used to provide proper responses to users' questions automati... more Question Answering (QA) systems are used to provide proper responses to users' questions automatically. Sentence matching is an essential task in the QA systems and is usually reformulated as a Paraphrase Identification (PI) problem. Given a question, the aim of the task is to find the most similar question from a QA knowledge base. In this paper, we propose a Multi-task Sentence Encoding Model (MSEM) for the PI problem, wherein a connected graph is employed to depict the relation between sentences, and a multi-task learning model is applied to address both the sentence matching and sentence intent classification problem. In addition, we implement a general semantic retrieval framework that combines our proposed model and the Approximate Nearest Neighbor (ANN) technology, which enables us to find the most similar question from all available candidates very quickly during online serving. The experiments show the superiority of our proposed method as compared with the existing sentence matching models.

Proceedings of the 28th International Conference on Computational Linguistics

Proceedings of the Eighth SIGHAN Workshop on Chinese Language Processing, 2015

This paper presents our Chinese microblog sentiment classification (CMSC) system in the Topic-Bas... more This paper presents our Chinese microblog sentiment classification (CMSC) system in the Topic-Based Chinese Message Polarity Classification task of SIGHAN-8 Bake-Off. Given a message from Chinese Weibo platform and a topic, our system is designed to classify whether the message is of positive, negative, or neutral sentiment towards the given topic. Due to the difficulties like the out-ofvocabulary Internet words and emoticons, polarity classification of Chinese microblogs is still an open problem today. In our system, Maximum Entropy (MaxEnt) is employed, which is a discriminative model that directly models the class posteriors, allowing them to incorporate a rich set of features. Moreover, oversampling approach is used to hand the unbalance problem. Evaluation results demonstrate the utility of our system, showing an accuracy of 66.4% for restricted resource and 66.6% for unrestricted resource.

Proceedings of The Third CIPS-SIGHAN Joint Conference on Chinese Language Processing, 2014

This paper describes our system in the Chinese spelling check (CSC) task of CLP-SIGHAN Bake-Off 2... more This paper describes our system in the Chinese spelling check (CSC) task of CLP-SIGHAN Bake-Off 2014. CSC is still an open problem today. To the best of our knowledge, n-gram language modeling (LM) is widely used in CSC because of its simplicity and fair predictive power. Our work in this paper continues this general line of research by using a tri-gram LM to detect and correct possible spelling errors. In addition, we use dynamic programming to improve the efficiency of the algorithm, and additive smoothing to solve the data sparseness problem in training set. Empirical evaluation results demonstrate the utility of our CSC system.

Proceedings of the Eighth SIGHAN Workshop on Chinese Language Processing, 2015