Social Event Detection (SED) aims to identify significant events from social streams, and has a wide application ranging from public opinion analysis to risk management. In recent years, Graph Neural Network (GNN) based solutions have achieved state-of-the-art performance. However, GNN-based methods often struggle with missing and noisy edges between messages, affecting the quality of learned message embedding. Moreover, these methods statically initialize node embedding before training, which, in turn, limits the ability to learn from message texts and relations simultaneously. In this article, we approach social event detection from a new perspective based on Pre-trained Language Models (PLMs), and present \(\mathrm{RPLM}_{SED}\) ( R elational prompt-based P re-trained L anguage M odels for S ocial E vent D etection). We first propose a new pairwise message modeling strategy to construct social messages into message pairs with multi-relational sequences. Secondly, a new multi-relational prompt-based pairwise message learning mechanism is proposed to learn more comprehensive message representation from message pairs with multi-relational prompts using PLMs. Thirdly, we design a new clustering constraint to optimize the encoding process by enhancing intra-cluster compactness and inter-cluster dispersion, making the message representation more distinguishable. We evaluate the \(\mathrm{RPLM}_{SED}\) on three real-world datasets, demonstrating that the \(\mathrm{RPLM}_{SED}\) model achieves state-of-the-art performance in offline, online, low-resource, and long-tail distribution scenarios for social event detection tasks.
Ran Song, Shizhu He, Shuting Jiang, Yantuan Xian, Shengxiang Gao, Kang Liu, Zhengtao Yu. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.
Tremendous academic articles face serious information overload problems while supporting literature searches. Finding a research article in a relevant domain that meets researchers’ requirements is challenging. Hence, different paper recommendation models have been proposed to address this issue. However, these models lack a more comprehensive analysis of the connections between the literature, the domain knowledge provided, and the hotspot information expressed in the literature. Previous models make it impossible to locate the appropriate documents for domain literature. Additionally, these models encounter problems such as cold start papers and data sparsity. To overcome these problems, this paper presents a recommendation model termed PRHN. Inputs of the model are the hotspot information network and the domain knowledge graph, which both were developed during the preceding research phase. After the query terms are extracted and the associated heterogeneous literature networks are formed, they are aggregated in a uniform hidden space. Similarity with the candidate set is determined to transform the search problem into a TOP N recommendation problem. Compared to state-of-the-art models, results generated by PRHN on public available datasets show improvement in HR and NDCG. Concretely, results on the metallurgical literature dataset are more conspicuous, with more remarkable improvement in HR and NGCC by approximately 4.5% and 4.2%.
Because the basis of students' math and limited time, the voice recognition is facing a dilemma. This article contact teaching practice. The content of the article is divided into two types, one is voice recognition principle, the other is speech recognition practice, We propose two types of the weakening formula derivation and stressed that the process of practice teaching ideas. In order to improve the students 'interest in learning, deepen the students' understanding of speech recognition, we present an example for the pilot teaching methods; The same time, we have given some useful speech recognition practices, from the cultivation of students' practical ability and scientific interest angle, the teaching experiments in speech based on HTK platform(HTK is a kit of hidden Markov model, HMM can be used to simulate any time series), It describes a hidden Markov model speech recognition principle and implementation process, design and realization of a speech recognition system, Describes the principle of speech recognition, speech signal pre-processing, speech training and recognition. Finally, the test results indicate the feasibility of the model.
Word segmentation is a critical task in natural language processing for southeast Asian Abugida languages, including Thai, Burmese, and Khmer. Existing approaches demonstrate that models using fixed-length windowed context inputs can achieve high segmentation accuracy; however, they often rely on low-level character features or language-specific preprocessing. Character-based methods can limit feature learning, while language-specific features add complexity due to specialized preprocessing requirements. This paper introduces UnifiedCut, which is a neural model that leverages multiple n-grams within a windowed multi-head attention mechanism. This design captures segmentation features from local contexts and multi-perspective n-gram inputs, enhancing generalization and recall, particularly for out-of-vocabulary words. Compared to CNN- and RNN-based approaches, UnifiedCut’s multi-head attention enables finer-grained feature extraction and greater parallelism, resulting in a faster, more scalable solution. Comprehensive experiments on public datasets for Thai, Burmese, and Khmer show that UnifiedCutachieves state-of-the-art performance in word segmentation.