检索结果-内蒙古大学图书馆

Conference on Empirical methods in natural language processing (EMNLP)

作者： Zhang, Lu Ding, Jiandong Xu, Yi Liu, Yingyao Zhou, Shuigeng Fudan Univ Shanghai Key Lab Intelligent Informat Proc Shanghai Peoples R China Fudan Univ Sch Comp Sci Shanghai Peoples R China Alibaba Grp Hangzhou Peoples R China

ISBN: (纸本)9781955917094

Weakly-supervised text classification has received much attention in recent years for it can alleviate the heavy burden of annotating massive data. Among them, keyword-driven methods are the mainstream where user-provided keywords are exploited to generate pseudo-labels for unlabeled texts. However, existing methods treat keywords independently, thus ignore the correlation among them, which should be useful if properly exploited. In this paper, we propose a novel framework called ClassKG to explore keyword-keyword correlation on keyword graph by GNN. Our framework is an iterative process. In each iteration, we first construct a keyword graph, so the task of assigning pseudo labels is transformed to annotating keyword subgraphs. To improve the annotation quality, we introduce a self-supervised task to pretrain a subgraph annotator, and then finetune it. With the pseudo labels generated by the subgraph annotator, we then train a text classifier to classify the unlabeled texts. Finally, we re-extract keywords from the classified texts. Extensive experiments on both long-text and short-text datasets show that our method substantially outperforms the existing ones.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Text Summarization Method based on Gated Attention graph Neural Network

引用

SENSORS 2023年第3期23卷 1654-1654页

作者： Huang, Jingui Wu, Wenya Li, Jingyi Wang, Shengchun Hunan Normal Univ Coll Informat Sci & Engn Changsha 410081 Peoples R China

Text summarization is an information compression technology to extract important information from long text, which has become a challenging research direction in the field of natural language processing. At present, the text summary model based on deep learning has shown good results, but how to more effectively model the relationship between words, more accurately extract feature information and eliminate redundant information is still a problem of concern. This paper proposes a graph neural network model GA-GNN based on gated attention, which effectively improves the accuracy and readability of text summarization. first, the words are encoded using a concatenated sentence encoder to generate a deeper vector containing local and global semantic information. Secondly, the ability to extract key information features is improved by using gated attention units to eliminate local irrelevant information. Finally, the loss function is optimized from the three aspects of contrastive learning, confidence calculation of important sentences, and graph feature extraction to improve the robustness of the model. Experimental validation was conducted on a CNN/Daily Mail dataset and MR dataset, and the results showed that the model in this paper outperformed existing methods.

关键词： encoder-decoder GNN contrastive learning confidence calculation of important sentences attention mechanism

来源：评论

学校读者我要写书评

暂无评论

UIUC BioNLP at SemEval-2021 Task 11: A Cascade of Neural Models for Structuring Scholarly NLP Contributions 15

UIUC BioNLP at SemEval-2021 Task 11: A Cascade of Neural Mod...

引用

15th International workshops on Semantic Evaluation (SemEval)

作者： Liu, Haoyang Sarol, Janina Kilicoglu, Halil Univ Illinois Sch Informat Sci Urbana IL 61801 USA

ISBN: (纸本)9781954085701

We propose a cascade of neural models that performs sentence classification, phrase recognition, and triple extraction to automatically structure the scholarly contributions of NLP publications in English. To identify the most important contribution sentences in a paper, we used a BERT-based classifier with positional features (Subtask 1). A BERT-CRF model was used to recognize and characterize relevant phrases in contribution sentences (Subtask 2). We categorized the triples into several types based on whether and how their elements were expressed in text, and addressed each type using separate BERT-based classifiers as well as rules (Subtask 3). Our system was officially ranked second in Phase 1 evaluation and first in both parts of Phase 2 evaluation. After fixing a submission error in Phase 1, our approach yielded the best results overall. In this paper, in addition to a system description, we also provide further analysis of our results, highlighting its strengths and limitations. We make our code publicly available at https://***/ Liu-Hy/nlp-contrib- graph.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Guiding Transformer to Generate graph Structure for AMR Parsing

Guiding Transformer to Generate Graph Structure for AMR Pars...

引用

2022 International Conference on Neural Networks, Information, and Communication Engineering, NNICE 2022

作者： Niu, Runliang Wang, Qi Jilin University ChangChun China

ISBN: (纸本)9781510655171

Meaning Representation (AMR) is a kind of semantic representation of natural language, which aims to represent the semantics of a sentence by a rooted, directed, and acyclic graph (DAG). Most existing AMR parsing works are designed under specific dictionary. However, these works make the content length of each node limited, and they mainly need to go through a very complicated post-processing process. In this paper, we propose a novel encoder-decoder framework for AMR parsing to address these issues, which generates a graph structure and predicts node relationships simultaneously. Specifically, we represent each node as a five-tuple form, containing token sequence of variable length and the connection relationship with other nodes. BERT model is employed as the encoder module. Our decoder module first generates a linearization representation of the graph structure, then predicts multiple elements of each node by four different attention-based classifiers. We also found an effective way to improve the generalization performance of Transformer model for graph generation. By assigning different index number to nodes in each training step and remove positional encoding used in most generative models, the model can learn the relationship between nodes better. Experiments against two AMR datasets demonstrate the competitive performance of our proposed method compared with baseline methods. © 2022 SPIE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Stage-wise fine-tuning for graph-to-text generation 59

Stage-wise fine-tuning for graph-to-text generation

引用

2021 Student Research workshop, SRW 2021 at the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on natural language processing, ACL-IJCNLP 2021

作者： Wang, Qingyun Yavuz, Semih Lin, Xi Victoria Ji, Heng Rajani, Nazneen Fatema University of Illinois at Urbana-Champaign United States Salesforce Research Facebook AI

ISBN: (纸本)9781954085558

graph-to-text generation has benefited from pre-trained language models (PLMs) in achieving better performance than structured graph encoders. However, they fail to fully utilize the structure information of the input graph. In this paper, we aim to further improve the performance of the pre-trained language model by proposing a structured graph-to-text model with a two-step fine-tuning mechanism which first fine-tunes the model on Wikipedia before adapting to the graph-to-text generation. In addition to using the traditional token and position embeddings to encode the knowledge graph (KG), we propose a novel tree-level embedding method to capture the interdependency structures of the input graph. This new approach has significantly improved the performance of all text generation metrics for the English WebNLG 2017 dataset. © 2021 Association for Computational Linguistics.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Exploiting Multiple Features for Hash Codes Learning with Semantic-Alignment-Promoting Variational Auto-encoder 12th

Exploiting Multiple Features for Hash Codes Learning with Se...

引用

12th National CCF Conference on natural language processing and Chinese Computing, NLPCC 2023

作者： Chen, Jiayang Su, Qinliang School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Beijing China

ISBN: (纸本)9783031446924

Semantic hashing is an effective technique to empower information retrieval. Currently, considerable efforts have been dedicated to generating high-quality hash codes by modeling document features using generative models and other approaches. However, most of these methods rely solely on a single type of feature, such as TFIDF features, BERT embeddings, etc. As different types of features have distinct but complementary information of documents, e.g. TFIDF mainly contains the keywords information and BERT focuses on the semantics, hash codes generated solely from either may not capture the full essence of the documents. To overcome this challenge, we propose a semantic-alignment-promoting variational auto-encoder to generate hash codes from multiple document features. Specifically, a VAE-based generative model is first developed to model the multiple features. Then, we propose a semantic-alignment-promoting inference network to estimate the parameters of the variational posterior from multiple features. Additionally, the quality of hash codes is further improved by promoting the semantic alignment between the hash codes of connected documents in a constructed connection graph. The results of extensive experiments on three public datasets demonstrate that our proposed model significantly outperforms current state-of-the-art models. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Lang3DSG: language-based contrastive pre-training for 3D Scene graph prediction

Lang3DSG: Language-based contrastive pre-training for 3D Sce...

引用

International Conference on 3D Imaging, Modeling, processing, Visualization and Transmission (3DIMPVT)

作者： Sebastian Koch Pedro Hermosilla Narunas Vaskevicius Mirco Colosi Timo Ropinski Bosch Center for Artificial Intelligence Robert Bosch Corporate Research University of Ulm TU Vienna

ISBN: (数字)9798350362459

ISBN: (纸本)9798350362466

3D scene graphs are an emerging 3D scene representation, that models both the objects present in the scene as well as their relationships. However, learning 3D scene graphs is a challenging task because it requires not only object labels but also relationship annotations, which are very scarce in datasets. While it is widely accepted that pre-training is an effective approach to improve model performance in low data regimes, in this paper, we find that existing pre-training methods are ill-suited for 3D scene graphs. To solve this issue, we present the first language-based pre-training approach for 3D scene graphs, whereby we exploit the strong relationship between scene graphs and language. To this end, we leverage the language encoder of CLIP, a popular vision-language model, to distill its knowledge into our graph-based network. We formulate a contrastive pre-training, which aligns text embeddings of relationships (subject-predicate-object triplets) and predicted 3D graph features. Our method achieves state-of-the-art results on the main semantic 3D scene graph benchmark by showing improved effectiveness over pre-training baselines and outperforming all the existing fully supervised scene graph prediction methods by a significant margin. Furthermore, since our scene graph features are language-aligned, it allows us to query the language space of the features in a zero-shot manner. In this paper, we show an example of utilizing this property of the features to predict the room type of a scene without further training.

关键词： Training Point cloud compression Knowledge engineering Solid modeling Three-dimensional displays Semantics natural languages

来源：评论

学校读者我要写书评

暂无评论

graph language Model (GLM): A new graph-based approach to detect social instabilities

arXiv

引用

arXiv 2024年

作者： de Oliveira, Wallyson Lemes Shamsaddini, Vahid Ghofrani, Ali Inda, Rahul Singh Veeramaneni, Jithendra Sai Voutaz, Étienne Giotto.ai SA Place de la Gare 4 Lausanne1004 Switzerland Armasuisse Feuerwerkerstrasse 39 Thun3602 Switzerland

This scientific report presents a novel methodology for the early prediction of important political events using News datasets. The methodology leverages natural language processing, graph theory, clique analysis, and semantic relationships to uncover hidden predictive signals within the data. Initially, we designed a preliminary version of the method and tested it on a few events. This analysis revealed limitations in the initial research phase. We then enhanced the model in two key ways: first, we added a filtration step to only consider politically relevant news before further processing;second, we adjusted the input features to make the alert system more sensitive to significant spikes in the data. After finalizing the improved methodology, we tested it on eleven events including US protests, the Ukraine war, and French protests. Results demonstrate the superiority of our approach compared to baseline methods. Through targeted refinements, our model can now provide earlier and more accurate predictions of major political events based on subtle patterns in news data. © 2024, CC BY-NC-ND.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Quantum probability-inspired graph neural network for document representation and classification

引用

NEUROCOMPUTING 2021年 445卷 276-286页

作者： Yan, Peng Li, Linjing Jin, Miaotianzi Zeng, Daniel Univ Chinese Acad Sci Sch Artificial Intelligence Beijing Peoples R China Chinese Acad Sci Inst Automat Beijing Peoples R China Shenzhen Artificial Intelligence & Data Sci Inst Shenzhen Peoples R China

Recent studies have found that text can be represented in Hilbert space through a neural network driven by quantum probability, which provides a unified representation of texts with different granularities without losing the performance of downstream tasks. However, these quantum probability-inspired methods only focus on intra-document semantics and lack modeling global structural information. In this paper, we explore the potential of combining quantum probability with graph neural network, and propose a quantum probability-inspired graph neural network model to capture global structural information of interaction between documents for document representation and classification. We build a document interaction graph for a given corpus based on document word relation and frequency information, then learn a graph neural network driven by quantum probability on the defined graph. first, the proposed model represents each document node in the graph as a superposition state in a Hilbert space. Then the proposed model further computes density matrix representations for nodes to encode document interaction as mixed states. Finally, the model computes classification probability by performing quantum measurement on the mixed states. Experiments on four document classification benchmarks show that the proposed model outperforms a variety of classical neural network models and the previous quantum probability-inspired model with much smaller parameter size. Extended analyses also demonstrate the robustness of the proposed model with limited training data and its ability to learn semantically distinguishable document representation. (c) 2021 Elsevier B.V. All rights reserved.

关键词： natural language processing Document representation Document classification graph neural network Quantum probability

来源：评论

学校读者我要写书评

暂无评论

GCNGAN: Translating natural language to Programming language based on GAN 2

GCNGAN: Translating Natural Language to Programming Language...

引用

2021 2nd International workshop on Electronic communication and Artificial Intelligence, IWECAI 2021

作者： Dai, Hongming Chen, Chen Li, Yunjing Yuan, Yanghao Department of Computer Science and Engineering Northeastern University Shenyang China Department of Electronic Engineering Tsinghua University Beijing China

Cross-language translating has been well solved with the help of the processing of natural language processing(NLP). However, there are a few studies done about the domain of translating the natural language to programming snippets. Traditional method are mostly rule-based and limited to specific areas. In this paper, we propose a model based on graph Convolutional Network(GCN)-Generative Adversarial Networks(GAN) to translate natural language to programming language. The generator is the encoder-decoder framework in which the encoder and the decoder are all bidirectional RNNs and GCN. And discriminator in GAN is also bidirectional RNNs and GCN. To improve the performance of semantic parsing, we also apply the attention mechanism to it. The experimental results indicate that our model has achieved comparable performance with some other state-of-the-art methods and has the stronger generalization ability. © Published under licence by IOP Publishing Ltd.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：