检索结果-内蒙古大学图书馆

Speaker identification combining role knowledge graph correction and contextual block attention

EXPERT SYSTEMS WITH APPLICATIONS 2025年 284卷

作者： Tao, Ye Wang, Fei Cai, Yanchang Li, Wei Qingdao Univ Sci & Technol Coll Informat Sci & Technol Qingdao 26606 Shandong Peoples R China China Telecom Res Inst 3 Penglaiyuan South St Beijing Peoples R China

Character dialogue play a crucial role in novels, serving as a key element for understanding both the plot and character relationships. With advancements in artificial intelligence and natural language processing, dialogue speaker recognition has seen significant progress. In this paper, we integrate a character role knowledge graph with a self-training mechanism to perform the speaker recognition on Chinese novel quotations using large-scale novel corpora. Quotes in novels can generally be classified as explicit or implicit. Implicit quotes require identifying speakers from extensive contextual information, which poses challenges for existing models in handling long and detail-rich contexts. In addition, existing end-to-end speaker recognition methods are ineffective because they do not fully consider the relationship between context and quotes. In this paper, we first propose a Narrative Unit-based Context Selection (NUCS) algorithm for determining the context to which quotes belong. Secondly, a speaker recognition method based on Role Knowledge graph Correction (RKGC) and Contextual Block Attention (CBA) is proposed. The proposed role knowledge graph correction algorithm improves speaker attribution by deeply analyzing role entities, their relationships, and relevant trigger words within quotations. It then refines candidate speaker probabilities obtained from the previous module. Additionally, the algorithm captures character relationships within the context using role mappings from existing novels. The CBA method introduces a block attention mechanism to capture character relationships within the context. It effectively computes the probability of each character being the speaker and determines the start and end indices of the most probable speaker segments. This allows the model to focus more precisely on speaker-related content, leading to more accurate speaker predictions. Experimental results demonstrate that our approach achieves competitive performance: o

关键词： End-to-end speaker recognition Knowledge graph Contextual chunk attention

来源：评论

学校读者我要写书评

暂无评论

Learning Relation-Enhanced Hierarchical Solver for Math Word Problems

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024年第10期35卷 13830-13844页

作者： Lin, Xin Huang, Zhenya Zhao, Hongke Chen, Enhong Liu, Qi Lian, Defu Li, Xin Wang, Hao Univ Sci & Technol China Sch Comp Sci & Technol Anhui Prov Key Lab Big Data Anal & Applicat Hefei Peoples R China State Key Lab Cognit Intelligence Hefei 230088 Peoples R China Tianjin Univ Coll Management & Econ Tianjin 300072 Peoples R China Univ Sci & Technol China Sch Informat Sci & Technol Hefei 230027 Peoples R China iFLYTEK Co Ltd Artificial Intelligence Res Inst Hefei 230088 Peoples R China

Automatically solving math word problems (MWPs) is a challenging task for artificial intelligence (AI) and machine learning (ML) research, which aims to answer the problem with a mathematical expression. Many existing solutions simply model the MWP as a sequence of words, which is far from precise solving. To this end, we turn to how humans solve MWPs. Humans read the problem part-by-part and capture dependencies between words for a thorough understanding and infer the expression precisely in a goal-driven manner with knowledge. Moreover, humans can associate different MWPs to help solve the target with related experience. In this article, we present a focused study on an MWP solver by imitating such procedure. Specifically, we first propose a novel hierarchical math solver (HMS) to exploit semantics in one MWP. first, to imitate human reading habits, we propose a novel encoder to learn the semantics guided by dependencies between words following a hierarchical "word-clause-problem" paradigm. Next, we develop a goal-driven tree-based decoder with knowledge application to generate the expression. One step further, to imitate human associating different MWPs for related experience in problemsolving, we extend HMS to the Relation-enHanced Math Solver (RHMS) to utilize the relation between MWPs. first, to capture the structural similarity relation, we develop a meta-structure tool to measure the similarity based on the logical structure of MWPs and construct a graph to associate related MWPs. Then, based on the graph, we learn an improved solver to exploit related experience for higher accuracy and robustness. Finally, we conduct extensive experiments on two large datasets, which demonstrates the effectiveness of the two proposed methods and the superiority of RHMS.

关键词： Human-like comprehension math word problem (MWP) natural language processing (NLP) relation learning structure-based association

来源：评论

学校读者我要写书评

暂无评论

MOAT: graph Prompting for 3D Molecular graphs 24

MOAT: Graph Prompting for 3D Molecular Graphs

引用

33rd ACM International Conference on Information and Knowledge Management (CIKM)

作者： Long, Qingqing Yan, Yuchen Cui, Wentao Ju, Wei Zhu, Zhihong Zhou, Yuanchun Wang, Xuezhi Xiao, Meng Chinese Acad Sci CNIC Beijing Peoples R China UCAS Beijing Peoples R China UCAS HIAS Beijing Peoples R China Peking Univ Beijing Peoples R China Sichuan Univ Chengdu Sichuan Peoples R China

ISBN: (纸本)9798400704369

Molecular property prediction stands as a cornerstone task in AI-driven drug design and discovery, wherein the atoms within a molecule serve as nodes, collectively forming a graph with bonds acting as edges. Given the crucial role of geometric structures in molecular property prediction, the integration of 3D information with various graph learning methods has been explored to enhance prediction performance. Despite the increasing adoption of the "graph pre-training and fine-tuning" paradigm to refine molecular representations, a significant challenge persists due to the misalignment between pre-training objectives and downstream tasks. Drawing inspiration from prompt tuning techniques in natural language processing (NLP), several graph prompt-based methods have emerged. However, existing approaches tend to overlook the unique properties inherent in molecular graphs. To address this gap, our paper introduces a novel approach named 3D MOleculArprompT (MOAT) designed specifically for geometric molecules. Specifically, we propose atom-level prompts to capture atom distribution, geometry-level prompts tailored for molecular conformers, where different conformations have distinct chemical properties, and task-level prompts to leverage functional group properties. Results on both 3D and 2D downstream tasks demonstrate its ability to successfully bridge the data gap across diverse settings. To the best of our knowledge, this paper is the first attempt to introduce geometric graph-prompting learning for molecules.

关键词： graph prompting 3D Molecules Molecular Prompting Molecular Fine-tuning

来源：评论

学校读者我要写书评

暂无评论

Investigating natural and Artificial Dynamics in graph Data Mining and Machine Learning 23

Investigating Natural and Artificial Dynamics in Graph Data ...

引用

32nd ACM International Conference on Information and Knowledge Management (CIKM)

作者： Fu, Dongqi Univ Illinois Dept Comp Sci Urbana IL 61801 USA

ISBN: (纸本)9798400701245

The complexity of relationships between entities is increasing in the era of big data, leading to a growing interest in graph (network) data, owing to its ability to encode intricate relational information. graph data mining and machine learning methods extract informative node and graph representations to support broad applications, which have been proven effective for various high-impact tasks in the fields such as computer vision, natural language processing, and recommendation systems. Despite their effectiveness, graph data mining and machine learning methods face practical challenges in real-world scenarios. first, the input graphs may change over time, making it necessary to integrate time-evolving information to enhance representation capabilities. Second, the input graphs may contain unreliable, noisy, or sub-optimal information, requiring researchers and practitioners to intentionally modify the graph topology and node features to improve downstream performance. Facing these two phenomena, our research works focus on natural and artificial dynamics for benefiting graph data mining and machine learning. In this paper, we will briefly introduce our recent works in investigative natural and artificial dynamics and point out some under-explored research problems in the interaction of these dynamics.

关键词： graph Data Mining graph Machine Learning Temporal graphs graph Augmentation

来源：评论

学校读者我要写书评

暂无评论

Large language Models for Few-Shot Automatic Term Extraction 29th

Large Language Models for Few-Shot Automatic Term Extraction

引用

29th International Conference on Applications of natural language to Information Systems (NLDB)

作者： Banerjee, Shubhanker Chakravarthi, Bharathi Raja McCrae, John Philip ADAPT Ctr Dublin Ireland Univ Galway Sch Comp Sci Galway Ireland

ISBN: (纸本)9783031702389;9783031702396

Automatic term extraction is the process of identifying domain-specific terms in a text using automated algorithms and is a key first step in ontology learning and knowledge graph creation. Large language models have shown good few-shot capabilities, thus, in this paper, we present a study to evaluate the few-shot in-context learning performance of GPT-3.5-Turbo on automatic term extraction. To benchmark the performance we compare the results with fine-tuning of a BERT-sized model. We also carry out experiments with count-based term extractors to assess their applicability to few-shot scenarios. We quantify prompt sensitivity with experiments to analyze the variation in performance of large language models across different prompt templates. Our results show that in-context learning with GPT-3.5-Turbo outperforms the BERT-based model and unsupervised count-based methods in few-shot scenarios.

关键词： few-shot automatic term extraction large language models

来源：评论

学校读者我要写书评

暂无评论

Label-aware debiased causal reasoning for natural language Inference

引用

AI OPEN 2024年第1期5卷 70-78页

作者： Zhang, Kun Zhang, Dacao Wu, Le Hong, Richang Zhao, Ye Wang, Meng Hefei Univ Technol Sch Comp Sci & Informat Engn Hefei 230601 Anhui Peoples R China Hefei Univ Technol Key Lab Knowledge Engn Big Data Hefei 230601 Anhui Peoples R China Hefei Comprehens Natl Sci Ctr Inst Dataspace Hefei 230009 Anhui Peoples R China

Recently, researchers have argued that the impressive performance of natural language Inference (NLI) models is highly due to the spurious correlations existing in training data, which makes models vulnerable and poorly generalized. Some work has made preliminary debiased attempts by developing data-driven interventions or model-level debiased learning. Despite the progress, existing debiased methods either suffered from the high cost of data annotation processing, or required elaborate design to identify biased factors. By conducting detailed investigations and data analysis, we argue that label information can provide meaningful guidance to identify these spurious correlations in training data, which has not been paid enough attention. Thus, we design a novel Label-aware Debiased Causal Reasoning Network ( LDCRN ). Specifically, according to the data analysis, we first build a causal graph to describe causal relations and spurious correlations in NLI. Then, we employ an NLI model (e.g., RoBERTa) to calculate total causal effect of input sentences to labels. Meanwhile, we design a novel label-aware biased module to model spurious correlations and calculate their causal effect in a fine-grained manner. The debiasing process is realized by subtracting this causal effect from total causal effect. Finally, extensive experiments over two well-known NLI datasets and multiple human-annotated challenging test sets are conducted to prove the superiority of LDCRN . Moreover, we have developed novel challenging test sets based on MultiNLI to facilitate the community.

关键词： natural language inference Spurious correlations Debiased reasoning Causal effect

来源：评论

学校读者我要写书评

暂无评论

IJS at Textgraphs-16 natural language Premise Selection Task: Will Contextual Information Improve natural language Premise Selection? 16

IJS at TextGraphs-16 Natural Language Premise Selection Task...

引用

16th workshop on graph-based methods for natural language processing, Textgraphs 2022, in conjunction with the 29th International Conference on Computational Linguistics, COLING 2022

作者： Tran, Hanh Thi Hong Martinc, Matej Doucet, Antoine Pollak, Senja Jožef Stefan Institute Slovenia Jozef Stefan International Postgraduate School Slovenia University of La Rochelle France

natural language Premise Selection (NLPS) is a mathematical natural language processing (NLP) task that retrieves a set of useful relevant premises to support the end-user finding the proof for a particular statement. In this paper, we evaluate the impact of Transformer-based contextual information and different fundamental similarity scores towards NLPS. The results demonstrate that the contextual representation is better at capturing meaningful information despite not being pretrained on mathematical background in comparison with the statistical approach (e.g., the TF-IDF) with a boost of around 3.00% MAP@500. Our code is publicly available at https://***/honghanhh/premise-selection. © 2022 proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Deep Learning on graphs: methods and Applications (DLG-KDD2023) 23

Deep Learning on Graphs: Methods and Applications (DLG-KDD20...

引用

29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)

作者： Wu, Lingfei Pei, Jian Tang, Jiliang Xia, Yinglong Guo, Xiaojie Pinterest San Francisco CA 94107 USA Duke Univ Durham NC USA Michigan State Univ E Lansing MI 48824 USA Meta Menlo Pk CA USA IBM TJ Watson Res Ctr Yorktown Height NY USA

ISBN: (纸本)9798400701030

Deep Learning models are at the core of research in Artificial Intelligence research today. A tide in research for deep learning on graphs or graph neural networks. This wave of research at the intersection of graph theory and deep learning has also influenced other fields of science, including computer vision, natural language processing, program synthesis and analysis, financial security, Drug Discovery and so on. However, there are still many challenges regarding a broad range of the topics in deep learning on graphs, from methodologies to applications, and from foundations to the new frontiers of GNNs. This international workshop on "Deep Learning on graphs: Method and Applications (DLG-KDD'23)" aims to bring together both academic researchers and industrial practitioners from different backgrounds and perspectives to above challenges.

关键词： graph neural network deep learning graph representation learning graph mining

来源：评论

学校读者我要写书评

暂无评论

SustaiNLP 2022 - 3rd workshop on Simple and Efficient natural language processing, proceedings of the workshop

SustaiNLP 2022 - 3rd Workshop on Simple and Efficient Natura...

引用

3rd workshop on Simple and Efficient natural language processing, SustaiNLP 2022

ISBN: (纸本)9781959429241

The proceedings contain 8 papers. The topics discussed include: efficient two-stage progressive quantization of BERT;KGRefiner: knowledge graph refinement for improving accuracy of translational link prediction methods;algorithmic diversity and tiny models: comparing binary networks and the fruit fly algorithm on document representation tasks;look ma, only 400 samples! revisiting the effectiveness of automatic N-Gram rule generation for spelling normalization in Filipino;who says elephants can’t run: bringing large scale MoE models into cloud scale production;data-efficient auto-regressive document retrieval for fact verification;AfroLM: a self-active learning-based multilingual pretrained language model for 23 African languages;and towards fair dataset distillation for text classification.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SumTablets : A Transliteration Dataset of Sumerian Tablets 1

SumTablets : A Transliteration Dataset of Sumerian Tablets

引用

1st workshop on Machine Learning for Ancient languages, ML4AL 2024

作者： Simmons, Cole Martinez, Richard Diehl Jurafsky, Dan Stanford University United States University of Cambridge United Kingdom

ISBN: (纸本)9798891761445

Sumerian transliteration is a conventional system for representing a scholar’s interpretation of a tablet in the Latin script. Thanks to visionary digital Assyriology projects such as ETCSL, CDLI, and Oracc, a large number of Sumerian transliterations have been published online, and these data are well-structured for a variety of search and analysis tasks. However, the absence of a comprehensive, accessible dataset pairing transliterations with a digital representation of the tablet’s cuneiform glyphs has prevented the application of modern natural language processing (NLP) methods to the task of Sumerian transliteration. To address this gap, we present SumTablets, a dataset pairing Unicode representations of 91,606 Sumerian cuneiform tablets (totaling 6,970,407 glyphs) with the associated transliterations published by Oracc. We construct SumTablets by first preprocessing and standardizing the Oracc transliterations before mapping each reading back to the Unicode representation of the source glyph. Further, we retain parallel structural information (e.g., surfaces, newlines, broken segments) through the use of special tokens. We release SumTablets as a Hugging Face Dataset (CC BY 4.0) and open source data preparation code via GitHub. Additionally, we leverage SumTablets to implement and evaluate two transliteration baselines: (1) weighted sampling from a glyph’s possible readings, and (2) fine-tuning an autoregressive language model. Our fine-tuned language model achieves an average transliteration character-level F-score (chrF) of 97.55, demonstrating the immediate potential of transformer-based transliteration models in allowing experts to rapidly verify generated transliterations rather than manually transliterating tablets one-by-one. © 2024 Association for Computational Linguistics.

关键词： natural language processing systems

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：