The proceedings contain 194 papers. The special focus in this conference is on naturallanguageprocessing and Chinese Computing. The topics include: Hierarchical knowledge Aggregation for Personalized Response Genera...
ISBN:
(纸本)9789819794423
The proceedings contain 194 papers. The special focus in this conference is on naturallanguageprocessing and Chinese Computing. The topics include: Hierarchical knowledge Aggregation for Personalized Response Generation in Dialogue Systems;multi-hop Reading Comprehension Model Based on Abstract Meaning Representation and Multi-task Joint Learning;Leveraging Large language Models for QA Dialogue Dataset Construction and Analysis in Public Services;MCFC: A Momentum-Driven Clicked Feature Compressed Pre-trained language Model for Information Retrieval;integrating Syntax Tree and Graph Neural Network for Conversational Question Answering over Heterogeneous Sources;pqE: Zero-Shot Document Expansion for Dense Retrieval with Large language Models;CKF: Conditional knowledge Fusion Method for CommonSense Question Answering;MPPQA: Structure-Aware Extractive Multi-span Question Answering for Procedural Documents;GraphLLM: A General Framework for Multi-hop Question Answering over knowledge Graphs Using Large language Models;local or Global Optimization for Dialogue Discourse Parsing;structure and Behavior Dual-Graph Reasoning with Integrated Key-Clue Parsing for Multi-party Dialogue Reading Comprehension;enhancing Emotional Support Conversation with Cognitive Chain-of-Thought Reasoning;a Simple and Effective Span Interaction Modeling Method for Enhancing Multiple Span Question Answering;FacGPT: An Effective and Efficient Method for Evaluating knowledge-Based Visual Question Answering;PAPER: A Persona-Aware Chain-of-Thought Learning Framework for Personalized Dialogue Response Generation;towards Building a Robust knowledge Intensive Question Answering Model with Large language Models;model-Agnostic knowledge Distillation Between Heterogeneous Models;exploring Multimodal Information Fusion in Spoken Off-Topic Degree Assessment;integrating Hierarchical Key Information and Semantic Difference Features for Long Text Matching;CausalAPM: Generalizable Literal Disentanglement for NLU
Folktales are a rich resource of knowledge about the society and culture of a *** folklore research aims to use automated techniques to better understand these folktales, and it relies on abstract representations of t...
Large neural language model like BERT can be pre trained to get extraordinary profits through multiple naturallanguageprocessing task. Though, General Domain Corpora including web and news wire are focused on pre tr...
详细信息
The proceedings contain 194 papers. The special focus in this conference is on naturallanguageprocessing and Chinese Computing. The topics include: Hierarchical knowledge Aggregation for Personalized Response Genera...
ISBN:
(纸本)9789819794331
The proceedings contain 194 papers. The special focus in this conference is on naturallanguageprocessing and Chinese Computing. The topics include: Hierarchical knowledge Aggregation for Personalized Response Generation in Dialogue Systems;multi-hop Reading Comprehension Model Based on Abstract Meaning Representation and Multi-task Joint Learning;Leveraging Large language Models for QA Dialogue Dataset Construction and Analysis in Public Services;MCFC: A Momentum-Driven Clicked Feature Compressed Pre-trained language Model for Information Retrieval;integrating Syntax Tree and Graph Neural Network for Conversational Question Answering over Heterogeneous Sources;pqE: Zero-Shot Document Expansion for Dense Retrieval with Large language Models;CKF: Conditional knowledge Fusion Method for CommonSense Question Answering;MPPQA: Structure-Aware Extractive Multi-span Question Answering for Procedural Documents;GraphLLM: A General Framework for Multi-hop Question Answering over knowledge Graphs Using Large language Models;local or Global Optimization for Dialogue Discourse Parsing;structure and Behavior Dual-Graph Reasoning with Integrated Key-Clue Parsing for Multi-party Dialogue Reading Comprehension;enhancing Emotional Support Conversation with Cognitive Chain-of-Thought Reasoning;a Simple and Effective Span Interaction Modeling Method for Enhancing Multiple Span Question Answering;FacGPT: An Effective and Efficient Method for Evaluating knowledge-Based Visual Question Answering;PAPER: A Persona-Aware Chain-of-Thought Learning Framework for Personalized Dialogue Response Generation;towards Building a Robust knowledge Intensive Question Answering Model with Large language Models;model-Agnostic knowledge Distillation Between Heterogeneous Models;exploring Multimodal Information Fusion in Spoken Off-Topic Degree Assessment;integrating Hierarchical Key Information and Semantic Difference Features for Long Text Matching;CausalAPM: Generalizable Literal Disentanglement for NLU
Federated Learning (FL) is a new pivotal paradigm for decentralized training on heterogeneous data. Recently fine-tuning of Vision-language Models (VLMs) has been extended to the federated setting to improve overall p...
详细信息
The proceedings contain 194 papers. The special focus in this conference is on naturallanguageprocessing and Chinese Computing. The topics include: Hierarchical knowledge Aggregation for Personalized Response Genera...
ISBN:
(纸本)9789819794300
The proceedings contain 194 papers. The special focus in this conference is on naturallanguageprocessing and Chinese Computing. The topics include: Hierarchical knowledge Aggregation for Personalized Response Generation in Dialogue Systems;multi-hop Reading Comprehension Model Based on Abstract Meaning Representation and Multi-task Joint Learning;Leveraging Large language Models for QA Dialogue Dataset Construction and Analysis in Public Services;MCFC: A Momentum-Driven Clicked Feature Compressed Pre-trained language Model for Information Retrieval;integrating Syntax Tree and Graph Neural Network for Conversational Question Answering over Heterogeneous Sources;pqE: Zero-Shot Document Expansion for Dense Retrieval with Large language Models;CKF: Conditional knowledge Fusion Method for CommonSense Question Answering;MPPQA: Structure-Aware Extractive Multi-span Question Answering for Procedural Documents;GraphLLM: A General Framework for Multi-hop Question Answering over knowledge Graphs Using Large language Models;local or Global Optimization for Dialogue Discourse Parsing;structure and Behavior Dual-Graph Reasoning with Integrated Key-Clue Parsing for Multi-party Dialogue Reading Comprehension;enhancing Emotional Support Conversation with Cognitive Chain-of-Thought Reasoning;a Simple and Effective Span Interaction Modeling Method for Enhancing Multiple Span Question Answering;FacGPT: An Effective and Efficient Method for Evaluating knowledge-Based Visual Question Answering;PAPER: A Persona-Aware Chain-of-Thought Learning Framework for Personalized Dialogue Response Generation;towards Building a Robust knowledge Intensive Question Answering Model with Large language Models;model-Agnostic knowledge Distillation Between Heterogeneous Models;exploring Multimodal Information Fusion in Spoken Off-Topic Degree Assessment;integrating Hierarchical Key Information and Semantic Difference Features for Long Text Matching;CausalAPM: Generalizable Literal Disentanglement for NLU
Recently, Profile-based Spoken language Understanding (SLU) has gained increasing attention, which aims to incorporate various types of supplementary profile information (i.e., knowledge Graph, User Profile, Context A...
详细信息
ISBN:
(纸本)9798350344868;9798350344851
Recently, Profile-based Spoken language Understanding (SLU) has gained increasing attention, which aims to incorporate various types of supplementary profile information (i.e., knowledge Graph, User Profile, Context Awareness) to eliminate the prevalent ambiguities in user utterances. However, existing approaches can only separately model different profile information, without considering their interrelationships or excluding irrelevant and conflicting information within them. To address the above issues, we introduce a Heterogeneous Graph Attention Network to perform reasoning across multiple PROfile information, called PRO-HAN. Specifically, we design three types of edges, denoted as intra-PRO, inter-PRO, and utterance-PRO, to capture interrelationships among multiple PROs. We establish a new state-of-the-art on the ProSLU dataset, with an improvement of approximately 8% across all three metrics. Further analysis experiments also confirm the effectiveness of our method in modeling multi-source profile information.
We present a novel multimodal interpretable VQA model that can answer the question more accurately and generate diverse explanations. Although researchers have proposed several methods that can generate human-readable...
详细信息
ISBN:
(纸本)9781728198354
We present a novel multimodal interpretable VQA model that can answer the question more accurately and generate diverse explanations. Although researchers have proposed several methods that can generate human-readable and fine-grained naturallanguage sentences to explain a model's decision, these methods have focused solely on the information in the image. Ideally, the model should refer to various information inside and outside the image to correctly generate explanations, just as we use background knowledge daily. The proposed method incorporates information from outside knowledge and multiple image captions to increase the diversity of information available to the model. The contribution of this paper is to construct an interpretable visual question answering model using multimodal inputs to improve the rationality of generated results. Experimental results show that our model can outperform state-of-the-art methods regarding answer accuracy and explanation rationality.
Retrieval augmented generation (RAG) has emerged as a promising approach in naturallanguageprocessing, combining retrieval and generation techniques to produce high-quality text. By incorporating external knowledge ...
详细信息
The proceedings contain 194 papers. The special focus in this conference is on naturallanguageprocessing and Chinese Computing. The topics include: Hierarchical knowledge Aggregation for Personalized Response Genera...
ISBN:
(纸本)9789819794393
The proceedings contain 194 papers. The special focus in this conference is on naturallanguageprocessing and Chinese Computing. The topics include: Hierarchical knowledge Aggregation for Personalized Response Generation in Dialogue Systems;multi-hop Reading Comprehension Model Based on Abstract Meaning Representation and Multi-task Joint Learning;Leveraging Large language Models for QA Dialogue Dataset Construction and Analysis in Public Services;MCFC: A Momentum-Driven Clicked Feature Compressed Pre-trained language Model for Information Retrieval;integrating Syntax Tree and Graph Neural Network for Conversational Question Answering over Heterogeneous Sources;pqE: Zero-Shot Document Expansion for Dense Retrieval with Large language Models;CKF: Conditional knowledge Fusion Method for CommonSense Question Answering;MPPQA: Structure-Aware Extractive Multi-span Question Answering for Procedural Documents;GraphLLM: A General Framework for Multi-hop Question Answering over knowledge Graphs Using Large language Models;local or Global Optimization for Dialogue Discourse Parsing;structure and Behavior Dual-Graph Reasoning with Integrated Key-Clue Parsing for Multi-party Dialogue Reading Comprehension;enhancing Emotional Support Conversation with Cognitive Chain-of-Thought Reasoning;a Simple and Effective Span Interaction Modeling Method for Enhancing Multiple Span Question Answering;FacGPT: An Effective and Efficient Method for Evaluating knowledge-Based Visual Question Answering;PAPER: A Persona-Aware Chain-of-Thought Learning Framework for Personalized Dialogue Response Generation;towards Building a Robust knowledge Intensive Question Answering Model with Large language Models;model-Agnostic knowledge Distillation Between Heterogeneous Models;exploring Multimodal Information Fusion in Spoken Off-Topic Degree Assessment;integrating Hierarchical Key Information and Semantic Difference Features for Long Text Matching;CausalAPM: Generalizable Literal Disentanglement for NLU
暂无评论