The proceedings contain 20 papers. The topics discussed include: bootstrapping large-scale fine-grained contextual advertising classifier from Wikipedia;modeling graph structure via relative position for text generati...
ISBN:
(纸本)9781954085381
The proceedings contain 20 papers. The topics discussed include: bootstrapping large-scale fine-grained contextual advertising classifier from Wikipedia;modeling graph structure via relative position for text generation from knowledge graphs;entity prediction in knowledge graphs with joint embeddings;hierarchical graph convolutional networks for jointly resolving cross-document coreference of entity and event mentions;learning clause representation from dependency-anchor graph for connective prediction;selective attention basedgraph convolutional networks for aspect-level sentiment classification;keyword extraction using unsupervised learning on the document’s adjacency matrix;improving human text simplification with sentence fusion;and on geodesic distances and contextual embedding compression for text classification.
The proceedings contain 15 papers. The topics discussed include: a graphical framework for contextual search and name disambiguation in email;graphbased semi-supervised approach for information extraction;graph-based...
The proceedings contain 15 papers. The topics discussed include: a graphical framework for contextual search and name disambiguation in email;graphbased semi-supervised approach for information extraction;graph-based text representation for novelty detection;measuring aboutness of an entity in a text;a study of two graph algorithms in topic-driven summarization;similarity between pairs of co-indexed trees for textual entailment recognition;learning of graph-based question answering rules;seeing stars when there aren’t many stars: graph-based semi-supervised learning for sentiment categorization;and random-walk term weighting for improved text classification.
The proceedings contain 14 papers. The topics discussed include: a survey of embedding models of entities and relationships for knowledge graph completion;graph-based aspect representation learning for entity resoluti...
ISBN:
(纸本)9781952148422
The proceedings contain 14 papers. The topics discussed include: a survey of embedding models of entities and relationships for knowledge graph completion;graph-based aspect representation learning for entity resolution;merge and recognize: a geometry and 2D context aware graph model for named entity recognition from visual documents;joint learning of the graph and the data representation for graph-based semi-supervised learning;contextual BERT: conditioning the language model using a global state;semi-supervised word sense disambiguation using example similarity graph;incorporating temporal information in entailment graph mining;relation specific transformations for open world knowledge graph completion;and PGL at Textgraphs 2020 Shared Task: explanation regeneration using language and graph learning methods.
The proceedings contain 10 papers. The topics discussed include: adapting predominant and novel sense discovery algorithms for identifying corpus-specific sense differences;merging knowledge bases in different languag...
ISBN:
(纸本)9781945626609
The proceedings contain 10 papers. The topics discussed include: adapting predominant and novel sense discovery algorithms for identifying corpus-specific sense differences;merging knowledge bases in different languages;parameter free hierarchical graph-based clustering for analyzing continuous word embeddings;spectral graph-based method of multimodal word embedding;extract with order for coherent multi-document summarization;work hard, play hard: email classification on the avocado and Enron corpora;a graphbased semi-supervised approach for analysis of derivational nouns in Sanskrit;and evaluating text coherence based on semantic similarity graph.
language models are being developed and deployed in many applications, "small"-scale and large-scale, generic and specialized, text-only and multimodal, etc. Meanwhile, the missingness of important knowledge...
详细信息
ISBN:
(纸本)9798400701030
language models are being developed and deployed in many applications, "small"-scale and large-scale, generic and specialized, text-only and multimodal, etc. Meanwhile, the missingness of important knowledge causes limitations and safety challenges. The knowledge includes commonsense, world facts, domain expertise, personalization, and especially the unique patterns that need to be discovered from big data applications. Training and inference processes of the language models can be and should be augmented with the knowledge. The first KnowledgeNLP at AAAI 2023 attracted scientists on knowledge augmentation methods towards higher language intelligence. This workshop offers a broad platform to share ideas and discuss various topics, such as (1) synergy between knowledge and language model, (2) scalable architectures that integrate NLP, knowledge graph, and graph learning technologies, (3) KnowledgeNLP for e-commerce, education, and healthcare, (4) human factors and social good in KnowledgeNLP.
The proceedings contain 23 papers. The topics discussed include: graph-based and graph-supported machine learning and deep learning methods;graph-based and graph-supported deep learning (e.g., graph-based recurrent an...
ISBN:
(纸本)9781950737864
The proceedings contain 23 papers. The topics discussed include: graph-based and graph-supported machine learning and deep learning methods;graph-based and graph-supported deep learning (e.g., graph-based recurrent and recursive networks);exploration of capabilities and limitations of graph-basedmethods being applied to neural networks;graph-based techniques for text summarization, simplification, and paraphrasing;graph-based techniques for document navigation and visualization;and using graphs-basedmethods to populate ontologies using textual data.
The proceedings contain 21 papers. The topics discussed include: improving the generalizability of text-based emotion detection by leveraging transformers with psycholinguistic features;fine-grained extraction and cla...
ISBN:
(纸本)9781959429203
The proceedings contain 21 papers. The topics discussed include: improving the generalizability of text-based emotion detection by leveraging transformers with psycholinguistic features;fine-grained extraction and classification of skill requirements in German-speaking job ads;experiencer-specific emotion and appraisal prediction;understanding narratives from demographic survey data: a comparative study with multiple neural topic models;to prefer or to choose? generating agency and power counterfactuals jointly for gender bias mitigation;conspiracy narratives in the protest movement against COVID-19 restrictions in Germany. A long-term content analysis of telegram chat groups;conditional language models for community-level linguistic variation;examining political rhetoric with epistemic stance detection;and linguistic elements of engaging customer service discourse on social media.
The proceedings contain 21 papers. The topics discussed include: the early modern Dutch mediascape. detecting media mentions in chronicles using word embeddings and CRF;FrameNet-like annotation of olfactory informatio...
ISBN:
(纸本)9781954085916
The proceedings contain 21 papers. The topics discussed include: the early modern Dutch mediascape. detecting media mentions in chronicles using word embeddings and CRF;FrameNet-like annotation of olfactory information in texts;Batavia asked for advice. pretrained language models for named entity recognition in historical texts;quantifying contextual aspects of inter-annotator agreement in intertextuality research;the multilingual corpus of survey questionnaires query interface;the FairyNet corpus - character networks for German fairy tales;end-to-end style-conditioned poetry generation: what does it take to learn from examples alone?;emotion classification in German plays with transformer-basedlanguage models pretrained on historical and contemporary language;automating the detection of poetic features: the limerick as model organism;unsupervised adverbial identification in modern Chinese literature;and data-driven detection of general chiasmi using lexical and semantic features.
The proceedings contain 8 papers. The topics discussed include: embedding text in hyperbolic spaces;scientific discovery as link prediction in influence and citation graphs;efficient generation and processing of word ...
ISBN:
(纸本)9781948087254
The proceedings contain 8 papers. The topics discussed include: embedding text in hyperbolic spaces;scientific discovery as link prediction in influence and citation graphs;efficient generation and processing of word co-occurrence networks using corpus2graph;multi-hop inference for sentence-level Textgraphs: how challenging is meaningfully combining information for science question answering?;multi-sentence compression with word vertex-labeled graphs and integer linear programming;large-scale spectral clustering using diffusion coordinates on landmark-based bipartite graphs;efficient graph-based word sense induction by distributional inclusion vector embeddings;fusing document, collection and label graph-based representations with word embeddings for text classification;and embedding text in hyperbolic spaces.
The Common Vulnerabilities and Exposures (CVE) system is crucial for cybersecurity, providing standardized identification of vulnerabilities. In February 2024, the National Vulnerability Database (NVD) announced it co...
详细信息
ISBN:
(纸本)9798400712548
The Common Vulnerabilities and Exposures (CVE) system is crucial for cybersecurity, providing standardized identification of vulnerabilities. In February 2024, the National Vulnerability Database (NVD) announced it could no longer enrich new CVEs due to increasing volumes, significantly impacting global security efforts. This paper introduces VulnScopper, an innovative approach to automate and enhance vulnerability enrichment using graph Neural Networks (GNNs). VulnScopper combines Knowledge graphs (KG) with naturallanguageprocessing (NLP) by leveraging ULTRA, a GNN-based knowledge graph foundation model, alongside a Large language Model (LLM). VulnScopper's inductive approach enables it to handle unseen entities, overcoming a crucial limitation of previous CVE enrichment methods. We evaluate VulnScopper on the NVD dataset in inductive and transductive setups for CVE to Common Platform Enumerations (CPE) linking. Our results show that VulnScopper outperforms state-of-the-art techniques, achieving up to 60% Hits@10 accuracy in linking CVEs to CPE on unseen CVE records. We demonstrate VulnScopper's effectiveness on unseen 2023 CVEs, showcasing its ability to uncover new vulnerable products and potentially reduce vulnerability remediation time.
暂无评论