检索结果-内蒙古大学图书馆

12th International Conference on language Resources and Evaluation, LREC 2020

作者： Nigam, Anurag Hätty, Anna im Walde, Sabine Schulte Institute for Natural Language Processing University of Stuttgart Germany Robert Bosch GmbH Corporate Research Renningen Germany

ISBN: (纸本)9791095546344

We perform a comparative study for automatic term extraction from domain-specific language using a PageRank model with different edge-weighting methods. We vary vector space representations within the PageRank graph algorithm, and we go beyond standard co-occurrence and investigate the influence of measures of association strength and first- vs. second-order co-occurrence. In addition, we incorporate meaning shifts from general to domain-specific language as personalized vectors, in order to distinguish between termhood strengths of ambiguous words across word senses. Our study is performed for two domain-specific English corpora: ACL and do-it-yourself (DIY);and a domain-specific German corpus: cooking. The models are assessed by applying average precision and the roc score as evaluation metrices. © European language Resources Association (ELRA), licensed under CC-BY-NC

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Hierarchical heterogeneous graph representation learning for short text classification

arXiv

引用

arXiv 2021年

作者： Wang, Yaqing Wang, Song Yao, Quanming Dou, Dejing Baidu Research Baidu Inc. China Department of ECE University of Virginia United States Department of EE Tsinghua University China

Short text classification is a fundamental task in natural language processing. It is hard due to the lack of context information and labeled data in practice. In this paper, we propose a new method called SHINE, which is based on graph neural network (GNN), for short text classification. first, we model the short text dataset as a hierarchical heterogeneous graph consisting of word-level component graphs which introduce more semantic and syntactic information. Then, we dynamically learn a short document graph that facilitates effective label propagation among similar short texts. Thus, comparing with existing GNN-based methods, SHINE can better exploit interactions between nodes of the same types and capture similarities between short texts. Extensive experiments on various benchmark short text datasets show that SHINE consistently outperforms state-of-the-art methods, especially with fewer labels. © 2021, CC BY.

关键词： graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Reviews Meet graphs: Enhancing User and Item Representations for Recommendation with Hierarchical Attentive graph Neural Network 9

Reviews Meet Graphs: Enhancing User and Item Representations...

引用

Conference on Empirical methods in natural language processing / 9th International Joint Conference on natural language processing (EMNLP-IJCNLP)

作者： Wu, Chuhan Wu, Fangzhao Qi, Tao Ge, Suyu Huang, Yongfeng Xie, Xing Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China Microsoft Res Asia Beijing 100080 Peoples R China

ISBN: (纸本)9781950737901

User and item representation learning is critical for recommendation. Many of existing recommendation methods learn representations of users and items based on their ratings and reviews. However, the user-user and item-item relatedness are usually not considered in these methods, which may be insufficient. In this paper, we propose a neural recommendation approach which can utilize useful information from both review content and user-item graphs. Since reviews and graphs have different characteristics, we propose to use a multi-view learning framework to incorporate them as different views. In the review content-view, we propose to use a hierarchical model to first learn sentence representations from words, then learn review representations from sentences, and finally learn user/item representations from reviews. In addition, we propose to incorporate a threelevel attention network into this view to select important words, sentences and reviews for learning informative user and item representations. In the graph-view, we propose a hierarchical graph neural network to jointly model the user-item, user-user and item-item relatedness by capturing the first- and secondorder interactions between users and items in the user-item graph. In addition, we apply attention mechanism to model the importance of these interactions to learn informative user and item representations. Extensive experiments on four benchmark datasets validate the effectiveness of our approach.

关键词： Hierarchical systems

来源：评论

学校读者我要写书评

暂无评论

Event Detection with Multi-Order graph Convolution and Aggregated Attention 9

Event Detection with Multi-Order Graph Convolution and Aggre...

引用

Conference on Empirical methods in natural language processing / 9th International Joint Conference on natural language processing (EMNLP-IJCNLP)

作者： Yan, Haoran Jin, Xiaolong Meng, Xiangbin Guo, Jiafeng Cheng, Xueqi Chinese Acad Sci Inst Comp Technol CAS Key Lab Network Data Sci & Technol Beijing Peoples R China Univ CAS Sch Comp & Control Engn Beijing Peoples R China Beijing Univ Posts & Telecommun Sch Comp Sci Beijing Peoples R China

ISBN: (纸本)9781950737901

Syntactic relations are broadly used in many NLP tasks. For event detection, syntactic relation representations based on dependency tree can better capture the interrelations between candidate trigger words and related entities than sentence representations. But, existing studies only use first-order syntactic relations (i.e., the arcs) in dependency trees to identify trigger words. For this reason, this paper proposes a new method for event detection, which uses a dependency tree based graph convolution network with aggregative attention to explicitly model and aggregate multi-order syntactic representations in sentences. Experimental comparison with state-of-the-art baselines shows the superiority of the proposed method.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous graph Attention Networks for Semi-supervised Short Text Classification 9

Heterogeneous Graph Attention Networks for Semi-supervised S...

引用

Conference on Empirical methods in natural language processing / 9th International Joint Conference on natural language processing (EMNLP-IJCNLP)

作者： Hu, Linmei Yang, Tianchi Shi, Chuan Ji, Houye Li, Xiaoli Beijing Univ Posts & Telecommun Beijing Peoples R China Inst Infocomm Res Singapore Singapore

ISBN: (纸本)9781950737901

Short text classification has found rich and critical applications in news and tweet tagging to help users find relevant information. Due to lack of labeled training data in many practical use cases, there is a pressing need for studying semi-supervised short text classification. Most existing studies focus on long texts and achieve unsatisfactory performance on short texts due to the sparsity and limited labeled data. In this paper, we propose a novel heterogeneous graph neural network based method for semi-supervised short text classification, leveraging full advantage of few labeled data and large unlabeled data through information propagation along the graph. In particular, we first present a flexible HIN (heterogeneous information network) framework for modeling the short texts, which can integrate any type of additional information as well as capture their relations to address the semantic sparsity. Then, we propose Heterogeneous graph ATtention networks (HGAT) to embed the HIN for short text classification based on a dual-level attention mechanism, including node-level and type-level attentions. The attention mechanism can learn the importance of different neighboring nodes as well as the importance of different node (information) types to a current node. Extensive experimental results have demonstrated that our proposed model outperforms state-of-the-art methods across six benchmark datasets significantly.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Textgraphs 2019 shared task on multi-hop inference for explanation regeneration 13

TextGraphs 2019 shared task on multi-hop inference for expla...

引用

13th workshop on graph-based methods for natural language processing, Textgraphs 2019, in conjunction with the 2019 Conference on Empirical methods in natural language processing and 9th International Joint Conference on natural language processing, EMNLP-IJCNLP 2019

作者： Jansen, Peter Ustalov, Dmitry School of Information University of Arizona United States Data and Web Science Group University of Mannheim Germany Yandex Russia

ISBN: (纸本)9781950737864

While automated question answering systems are increasingly able to retrieve answers to natural language questions, their ability to generate detailed human-readable explanations for their answers is still quite limited. The Shared Task on Multi-Hop Inference for Explanation Regeneration tasks participants with regenerating detailed gold explanations for standardized elementary science exam questions by selecting facts from a knowledge base of semistructured tables. Each explanation contains between 1 and 16 interconnected facts that form an "explanation graph" spanning core scientific knowledge and detailed world knowledge. It is expected that successfully combining these facts to generate detailed explanations will require advancing methods in multihop inference and information combination, and will make use of the supervised training data provided by the WorldTree explanation corpus. The top-performing system achieved a mean average precision (MAP) of 0.56, substantially advancing the state-of-the-art over a baseline information retrieval model. Detailed extended analyses of all submitted systems showed large relative improvements in accessing the most challenging multi-hop inference problems, while absolute performance remains low, highlighting the difficulty of generating detailed explanations through multihop reasoning. © 2019 EMNLP-IJCNLP 2019 - graph-based methods for natural language processing - proceedings of the 13th workshop. All rights reserved.

关键词： graphic methods

来源：评论

学校读者我要写书评

暂无评论

Look one step ahead through first-order aggregation in reinforcement learning-based knowledge graph reasoning

引用

Information Sciences 2025年 718卷

作者： Hao Wang Dandan Song Zhijing Wu YuHang Tian Jing Xu Laboratory of High-Volume Language Information Processing and Cloud Computing Beijing Lab of Intelligent Information Technology School of Computer Science and Technology Beijing Institute of Technology Beijing 100081 Beijing China

Multi-hop reasoning is an effective and interpretable approach for query answering, as it finds reasoning paths over knowledge graphs (KGs) to enhance interpretability. Recent studies have applied reinforcement learning-based (RL-based) methods with policy agents to solve this problem. However, these methods primarily focus on sequential reasoning paths and candidate nodes, while overlooking the local structural information of adjacency subgraphs and the semantic correlations between relations at each decision step. In this paper, we propose a novel RL-based multi-hop reasoning model, L ook O ne S tep A head (LOSA), which leverages first-order aggregation to regard more expressive adjacency subgraphs rather than nodes as candidate actions and pays attention to the semantic correlations between relations. Specifically, an adjacency aggregation module encodes the local subgraph information and feeds the representations into the policy network to guide decision-making, thereby reducing backtracking and mitigating sparse-reward issues. Furthermore, a semantic matching module is designed to emphasize the semantic correlations of relations to improve the rationality of the reasoning paths. Extensive experiments on benchmark datasets demonstrate the effectiveness of the proposed approach.

关键词： Knowledge graph completion Knowledge graph reasoning Link prediction Multi-hop reasoning

来源：评论

学校读者我要写书评

暂无评论

Semantic graph Parsing with Recurrent Neural Network DAG Grammars 9

Semantic Graph Parsing with Recurrent Neural Network DAG Gra...

引用

Conference on Empirical methods in natural language processing / 9th International Joint Conference on natural language processing (EMNLP-IJCNLP)

作者： Fancellu, Federico Gilroy, Sorcha Lopez, Adam Lapata, Mirella Samsung AI Ctr SAIC Toronto ON Canada Peak AI Manchester Lancs England Univ Edinburgh Edinburgh Midlothian Scotland

ISBN: (纸本)9781950737901

Semantic parses are directed acyclic graphs (DAGs), so semantic parsing should be modeled as graph prediction. But predicting graphs presents difficult technical challenges, so it is simpler and more common to predict the linearized graphs found in semantic parsing datasets using well-understood sequence models. The cost of this simplicity is that the predicted strings may not be wellformed graphs. We present recurrent neural network DAG grammars, a graph-aware sequence model that ensures only well-formed graphs while sidestepping many difficulties in graph prediction. We test our model on the Parallel Meaning Bank-a multilingual semantic graphbank. Our approach yields competitive results in English and establishes the first results for German, Italian and Dutch.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

基於大型语言模型与知识图谱交互合作之推理问答系统

基於大型语言模型与知识图谱交互合作之推理问答系统

引用

作者：许兆凯

学位级别：硕士

虽然大型语言模型（LLM）在各种任务中取得了显着成就，但它们在经常面临幻觉问题，并欠缺特定领域知识推理与解释的能力。方法如微调（Fine-Tuning）、低秩适应（Low-Rank Adaptation, LoRA）、检索增强生成（Retrieval-Augmented Gene... 详细信息

虽然大型语言模型（LLM）在各种任务中取得了显着成就，但它们在经常面临幻觉问题，并欠缺特定领域知识推理与解释的能力。方法如微调（Fine-Tuning）、低秩适应（Low-Rank Adaptation, LoRA）、检索增强生成（Retrieval-Augmented Generation, RAG）等，旨在提升大语言模型（LLM）的回答准确性。微调需要极为大量的资料和计算资源才能对LLM的参数产生影响，但即使如此，仍无法解决LLM的黑箱问题。LoRA作为微调的替代方案，在减少资料量和计算资源的同时，亦能取得不错的效果，但本质上仍无法解决LLM的黑箱问题。RAG作为最广泛应用的方法，透过检索资料库来获得正确答案，从而解决LLM的黑箱问题，然而，这种方法在处理需要推理的复杂问题时效果不佳。本论文的目的是解决大语言模型（LLM）无法解释、知识图谱（Knowledge graph, KG）过大以及无法进行推理的问题。由於知识图谱作为储存广泛知识的载体，包含数亿个节点和边，对於推理链的运行构成了极大负担。本论文在第一阶段，先由LLM生成可能的起始节点，然後使用奖励斯坦纳树（Prize-Collecting Steiner Tree, PCST）演算法来去除KG中比较不相关的资讯，从而生成一个更精简的子树，解决KG过大的问题。其次，在第二阶段中，本论文开发了一个LLM与KG相互协作的系统，以交互方式探索KG中的相关实体和关系，并根据检索到的知识进行推理，从而解决LLM的不可解释性及KG的推理问题。实验显示，在两个资料集上各项指标皆获得成效。

关键词：深度学习人工智慧自然语言处理大语言模型知识图谱问答系统

来源：评论

学校读者我要写书评

暂无评论

Knowledge graph question answering via SPARQL silhouette generation

arXiv

引用

arXiv 2021年

作者： Purkayastha, Sukannya Dana, Saswati Garg, Dinesh Khandelwal, Dinesh Bhargav, G.P. Shrivatsa TCS Research IBM Research

Knowledge graph Question Answering (KGQA) has become a prominent area in natural language processing due to the emergence of large-scale Knowledge graphs (KGs). Recently Neural Machine Translation based approaches are gaining momentum that translates natural language queries to structured query languages thereby solving the KGQA task. However, most of these methods struggle with out-of-vocabulary words where test entities and relations are not seen during training time. In this work, we propose a modular two-stage neural architecture to solve the KGQA task. The first stage generates a sketch of the target SPARQL called SPARQL silhouette for the input question. This comprises of (1) Noise simulator to facilitate out-of-vocabulary words and to reduce vocabulary size (2) seq2seq model for text to SPARQL silhouette generation. The second stage is a Neural graph Search Module. SPARQL silhouette generated in the first stage is distilled in the second stage by substituting precise relation in the predicted structure. We simulate ideal and realistic scenarios by designing a noise simulator. Experimental results show that the quality of generated SPARQL silhouette in the first stage is outstanding for the ideal scenarios but for realistic scenarios (i.e. noisy linker), the quality of the resulting SPARQL silhouette drops drastically. However, our neural graph search module recovers it considerably. We show that our method can achieve reasonable performance improving the state-of-art by a margin of 3.72% F1 for the LC-QuAD-1 dataset. We believe, our proposed approach is novel and will lead to dynamic KGQA solutions that are suited for practical applications. © 2021, CC BY.

关键词： Knowledge graph

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：