Search Results for author: Dingmin Wang

Found 12 papers, 8 papers with code

A Template-guided Hybrid Pointer Network for Knowledge-based Task-oriented Dialogue Systems

1 code implementation ACL (dialdoc) 2021 Dingmin Wang, Ziyao Chen, Wanwei He, Li Zhong, Yunzhe Tao, Min Yang

Most existing neural network based task-oriented dialog systems follow encoder-decoder paradigm, where the decoder purely depends on the source texts to generate a sequence of words, usually suffering from instability and poor readability.

Task-Oriented Dialogue Systems

Calibrate and Boost Logical Expressiveness of GNN Over Multi-Relational and Temporal Graphs

1 code implementation NeurIPS 2023 Yeyuan Chen, Dingmin Wang

Moreover, we extend our analysis of expressiveness and graph transformation to temporal graphs, exploring several temporal GNN architectures and providing an expressiveness hierarchy for them.

Graph Representation Learning Node Classification

Working Memory Capacity of ChatGPT: An Empirical Study

2 code implementations30 Apr 2023 Dongyu Gong, Xingchen Wan, Dingmin Wang

Working memory is a critical aspect of both human intelligence and artificial intelligence, serving as a workspace for the temporary storage and manipulation of information.

Benchmarking Language Modelling +1

Seminaive Materialisation in DatalogMTL

1 code implementation15 Aug 2022 Dingmin Wang, Przemysław Andrzej Wałęga, Bernardo Cuenca Grau

DatalogMTL is an extension of Datalog with metric temporal operators that has found applications in temporal ontology-based data access and query answering, as well as in stream reasoning.

MeTeoR: Practical Reasoning in Datalog with Metric Temporal Operators

1 code implementation12 Jan 2022 Dingmin Wang, Pan Hu, Przemysław Andrzej Wałęga, Bernardo Cuenca Grau

DatalogMTL is an extension of Datalog with operators from metric temporal logic which has received significant attention in recent years.

A Template-guided Hybrid Pointer Network for Knowledge-basedTask-oriented Dialogue Systems

1 code implementation10 Jun 2021 Dingmin Wang, Ziyao Chen, Wanwei He, Li Zhong, Yunzhe Tao, Min Yang

Most existing neural network based task-oriented dialogue systems follow encoder-decoder paradigm, where the decoder purely depends on the source texts to generate a sequence of words, usually suffering from instability and poor readability.

Task-Oriented Dialogue Systems

Fast and Scalable Dialogue State Tracking with Explicit Modular Decomposition

no code implementations NAACL 2021 Dingmin Wang, Chenghua Lin, Qi Liu, Kam-Fai Wong

We present a fast and scalable architecture called Explicit Modular Decomposition (EMD), in which we incorporate both classification-based and extraction-based methods and design four modules (for classification and sequence labelling) to jointly extract dialogue states.

Classification Dialogue State Tracking +3

Confusionset-guided Pointer Networks for Chinese Spelling Check

no code implementations ACL 2019 Dingmin Wang, Yi Tay, Li Zhong

This paper proposes Confusionset-guided Pointer Networks for Chinese Spell Check (CSC) task.

Sentence

A Hybrid Approach to Automatic Corpus Generation for Chinese Spelling Check

1 code implementation EMNLP 2018 Dingmin Wang, Yan Song, Jing Li, Jialong Han, Haisong Zhang

Chinese spelling check (CSC) is a challenging yet meaningful task, which not only serves as a preprocessing in many natural language processing(NLP) applications, but also facilitates reading and understanding of running texts in peoples{'} daily lives.

Language Modelling Optical Character Recognition (OCR) +1

NLPTEA 2017 Shared Task -- Chinese Spelling Check

no code implementations WS 2017 Gabriel Fung, Maxime Debosschere, Dingmin Wang, Bo Li, Jia Zhu, Kam-Fai Wong

This paper provides an overview along with our findings of the Chinese Spelling Check shared task at NLPTEA 2017.

Sentence

Cannot find the paper you are looking for? You can Submit a new open access paper.