检索结果-内蒙古大学图书馆

4th workshop on Trustworthy natural language processing, TrustNLP 2024

ISBN: (纸本)9798891761131

The proceedings contain 21 papers. The topics discussed include: beyond Turing: a comparative analysis of approaches for detecting machine-generated text;automated adversarial discovery for safety classifiers;the trade-off between performance, efficiency, and fairness in adapter modules for text classification;towards healthy ai: large language models need therapists too;exploring causal mechanisms for machine text detection methods;FactAlign: fact-level hallucination detection and classification through knowledge graph alignment;cross-task defense: instruction-tuning LLMs for content safety;on the interplay between fairness and explainability;and holistic evaluation of large language models: assessing robustness, accuracy, and toxicity for real world applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modal-adaptive Knowledge-enhanced graph-based Financial Prediction from Monetary Policy Conference Calls with LLM 7

Modal-adaptive Knowledge-enhanced Graph-based Financial Pred...

引用

Joint workshop of the 7th Financial Technology and natural language processing, 5th Knowledge Discovery from Unstructured Data in Financial Services and 4th Economics and natural language processing, FinNLP-KDF-ECONLP 2024

作者： Ouyang, Kun Liu, Yi Li, Shicheng Bao, Ruihan Harimoto, Keiko Sun, Xu National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China Mizuho Securities Co. Ltd. Japan

ISBN: (纸本)9782493814197

Financial prediction from Monetary Policy Conference (MPC) calls is a new yet challenging task, which targets at predicting the price movement and volatility for specific financial assets by analyzing multimodal information including text, video, and audio. Although the existing work has achieved great success using cross-modal transformer blocks, it overlooks the potential external financial knowledge, the varying contributions of different modalities to financial prediction, as well as the innate relations among different financial assets. To tackle these limitations, we propose a novel Modal-Adaptive kNowledge-enhAnced graph-based financial pRediction scheme, named MANAGER. Specifically, MANAGER resorts to FinDKG to obtain the external related knowledge for the input text. Meanwhile, MANAGER adopts BEiT-3 and Hidden-unit BERT (HuBERT) to extract the video and audio features, respectively. Thereafter, MANAGER introduces a novel knowledge-enhanced cross-modal graph that fully characterizes the semantic relations among text, external knowledge, video and audio, to adaptively utilize the information in different modalities, with ChatGLM2 as the backbone. Extensive experiments on a publicly available dataset Monopoly verify the superiority of our model over cutting-edge methods. © 2024 ELRA language Resource Association.

关键词： Teleconferencing

来源：评论

学校读者我要写书评

暂无评论

Cross Examine: An Ensemble-based approach to leverage Large language Models for Legal Text Analytics 6

Cross Examine: An Ensemble-based approach to leverage Large ...

引用

6th natural Legal language processing workshop 2024, NLLP 2024, co-located with the 2024 Conference on Empirical methods in natural language processing

作者： Chowdhury, Saurav Joshi, Suyog Dey, Lipika Indian Institute of Technology Jodhpur India Ashoka University India

ISBN: (纸本)9798891761834

Legal documents are complex in nature, describing a course of argumentative reasoning that is followed to settle a case. Churning through large volumes of legal documents is a daily requirement for a large number of professionals who need access to the information embedded in them. natural language processing(NLP) methods that help in document summarization with key information components, insight extraction and question answering play a crucial role in legal text processing. Most of the existing document analysis systems use supervised machine learning, which require large volumes of annotated training data for every different application and are expensive to build. In this paper we propose a legal text analytics pipeline using Large language Models (LLMs), which can work with little or no training data. For document summarization, we propose an iterative pipeline using retrieval augmented generation to ensure that the generated text remains contextually relevant. For question answering, we propose a novel ontology-driven ensemble approach similar to cross-examination that exploits questioning and verification principles. A knowledge graph, created with the extracted information, stores the key entities and relationships reflecting the repository content structure. A new dataset is created with Indian court documents related to bail applications for cases filed under POCSO1 Act. Analysis of insights extracted from the answers reveal patterns of crime and social conditions leading to those crimes, which are important inputs for social scientists as well as legal system. ©2024 Association for Computational Linguistics.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Reducing Knowledge Noise for Improved Semantic Analysis in Biomedical natural language processing Applications 5

Reducing Knowledge Noise for Improved Semantic Analysis in B...

引用

5th workshop on Clinical natural language processing, ClinicalNLP 2023. held at ACL 2023

作者： Naseem, Usman Thapa, Surendrabikram Zhang, Qi Hu, Liang Masood, Anum Nasim, Mehwish University of Sydney Australia Virginia Tech United States Tongji University China DeepBlue Academy of Sciences China Norwegian University of Science and Technology Norway University of Western Australia Australia Flinders University Australia

ISBN: (纸本)9781959429883

graph-based techniques have gained traction for representing and analyzing data in various natural language processing (NLP) tasks. Knowledge graph-based language representation models have shown promising results in leveraging domain-specific knowledge for NLP tasks, particularly in the biomedical NLP field. However, such models have limitations, including knowledge noise and neglect of contextual relationships, leading to potential semantic errors and reduced accuracy. To address these issues, this paper proposes two novel methods. The first method combines knowledge graphbased language model with nearest-neighbor models to incorporate semantic and category information from neighboring instances. The second method involves integrating knowledge graph-based language model with graph neural networks (GNNs) to leverage feature information from neighboring nodes in the graph. Experiments on relation extraction (RE) and classification tasks in English and Chinese language datasets demonstrate significant performance improvements with both methods, highlighting their potential for enhancing the performance of language models and improving NLP applications in the biomedical domain. © 2023 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Automated Generation of Competency Questions Using Large language Models and Knowledge graphs 3

Automated Generation of Competency Questions Using Large Lan...

引用

3rd International workshop on natural language processing for Knowledge graph Creation, NLP4KGC 2024

作者： Di Nuzzo, Dario Vakaj, Edlira Saadany, Hadeel Grishti, Eglantina Mihindukulasooriya, Nandana College of Computing Birmigham City University United Kingdom University of Tirana Tirana Albania IBM Research USA United States

This research presents a novel approach to automated competency question generation by integrating Large language Models (LLMs) with Knowledge graphs (KGs), particularly within the context of sustainability assessment standards like BREEAM. The study develops a comprehensive methodology combining natural language processing and knowledge representation to address the challenges of manual question generation in competency-based assessments. The methodology begins with text extraction from BREEAM standards, followed by preprocessing, transformation into graph documents, and the construction of a structured KG. Advanced LLMs, including GPT-4o and Mistral, are employed to generate competency questions based on entity-specific and community-focused retrieval methods. The system is rigorously evaluated using quantitative metrics such as cosine similarity scores and qualitative assessments using the "LLM-as-a-Judge"method. Results demonstrate that GPT-4 and Mistral models generate highly relevant, clear, and complex questions, highlighting the potential for scalable, domainspecific competency assessments. This research opens avenues for improving AI-driven educational technologies and personalised learning through automated, adaptive assessment tools. © 2024 Copyright for this paper by its authors.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Enhancing Semantic Relation Classification With Shortest Dependency Path Reasoning

引用

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND language processing 2023年 31卷 1550-1560页

作者： Li, Jijie Shuang, Kai Guo, Jinyu Shi, Zengyi Wang, Hongman Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Beijing Acad Artificial Intelligence Beijing 100085 Peoples R China

Relation Classification (RC) is a basic and essential task of natural language processing. Existing RC methods can be classified into two categories: sequence-based methods and dependency-based methods. Sequence-based methods identify the target relation based on the overall semantics of the whole sentence, which will inevitably introduce noisy features. Dependency-based methods extract indicative word-level features from the Shortest Dependency Path (SDP) between given entities and attempt to establish a statistical association between the words and the target relations. This pattern relatively eliminates the influence of noisy features and achieves a robust performance on long sentences. Nevertheless, we observe that majority of relation classification processes involve complex semantic reasoning which is hard to be achieved based on the word-level statistical association. To solve this problem, we categorize all relations into atomic relations and composed-relations. The atomic relations are the basic relations that can be identified based on the word-level features, while the composed-relation requires to be deducted from multiple atomic relations. Correspondingly, we propose the Atomic Relation Encoding and Reasoning Model (ATERM). In the atomic relation encoding stage, ATERM groups the word-level features and encodes multiple atomic relations in parallel. In the atomic relation reasoning stage, ATERM establishes the atomic relation chain where relation-level features are extracted to identify composed-relations. Experiments show that our method achieves state-of-the-art results on the three most popular relation classification datasets - TACRED, TACRED-Revisit, and SemEval 2010 task 8 with significant improvements.

关键词： Semantics Knowledge based systems Ontologies Feature extraction Cognition Encoding natural language processing Information extraction graph convolution shortest dependency path semantic reasoning

来源：评论

学校读者我要写书评

暂无评论

NLLP 2024 - natural Legal language processing workshop 2024, proceedings of the workshop

NLLP 2024 - Natural Legal Language Processing Workshop 2024,...

引用

6th natural Legal language processing workshop 2024, NLLP 2024, co-located with the 2024 Conference on Empirical methods in natural language processing

ISBN: (纸本)9798891761834

The proceedings contain 33 papers. The topics discussed include: LeGen: complex information extraction from legal sentences using generative models;summarizing long regulatory documents with a multi-step pipeline;enhancing legal expertise in large language models through composite model integration: the development and evaluation of Law-Neo;uOttawa at LegalLens-2024: transformer-based classification experiments;Quebec automobile insurance question-answering with retrieval-augmented generation;rethinking legal judgement prediction in a realistic scenario in the era of large language models;information extraction for planning court cases;and towards an automated pointwise evaluation metric for generated long-form legal summaries.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sixth Knowledge-aware and Conversational Recommender Systemsworkshop (KaRS) 24

Sixth Knowledge-aware and Conversational Recommender Systems...

引用

18h ACM Conference on Recommender Systems (RecSys)

作者： Anelli, Vito Walter Ferrara, Antonio Musto, Cataldo Narducci, Fedelucio Ragone, Azzurra Zanker, Markus Polytech Univ Bari Bari Italy Univ Bari Aldo Moro Bari Italy Free Univ Bozen Bolzano Bolzano Italy

ISBN: (纸本)9798400705052

Recommender systems, though widely used, often struggle to engage users effectively. While deep learning methods have enhanced connections between users and items, they often neglect the user's perspective. Knowledge-based approaches, utilizing knowledge graphs, offer semantic insights and address issues like knowledge graph embeddings, hybrid recommendation, and interpretable recommendation. More recently, neural-symbolic systems, combining data-driven and symbolic techniques, show promise in recommendation systems, especially when used with knowledge graphs. Moreover, content features become vital in conversational recommender systems, which demand multi-turn dialogues. Recent literature highlights increasing interest in this area, particularly with the emergence of Large language Models (LLMs), which excel in understanding user queries and generating recommendations in natural language. Sixth Knowledge-aware and Conversational Recommender Systems (KaRS) workshop aims to disseminate advancements and discuss about challenges and opportunities.

关键词： recommender systems knowledge graphs neuro-symbolic natural language processing conversational agents large language models

来源：评论

学校读者我要写书评

暂无评论

Leveraging Semi-Supervised Learning on a Financial-Specialized Pre-trained language Model for Multilingual ESG Impact Duration and Type Classification 7

Leveraging Semi-Supervised Learning on a Financial-Specializ...

引用

作者： Kim, Jungdae Jeon, Eunkwang Jeon, Sanghyun KakaoBank Corp Korea Republic of

ISBN: (纸本)9782493814197

This paper presents the results of our participation in the Multilingual ESG Impact Duration Inference (ML-ESG-3) shared task organized by FinNLP-KDF@LREC-COLING-2024. The objective of this challenge is to leverage natural language processing (NLP) techniques to identify the impact duration or impact type of events that may affect a company based on news articles written in various languages. Our approach employs semi-supervised learning methods on a finance-specialized pre-trained language model. Our methodology demonstrates strong performance, achieving 1st place in the Korean - Impact Type subtask and 2nd place in the Korean - Impact Duration subtask. These results showcase the efficacy of our approach in detecting ESG-related issues from news articles. Our research shows the potential to improve existing ESG ratings by quickly reflecting the latest events of companies. © 2024 ELRA language Resource Association.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

LAR-ECHR: A New Legal Argument Reasoning Task and Dataset for Cases of the European Court of Human Rights 6

LAR-ECHR: A New Legal Argument Reasoning Task and Dataset fo...

引用

6th natural Legal language processing workshop 2024, NLLP 2024, co-located with the 2024 Conference on Empirical methods in natural language processing

作者： Chlapanis, Odysseas S. Galanis, Dimitrios Androutsopoulos, Ion Department of Informatics Athens University of Economics and Business Greece Institute for Language and Speech Processing Athena Research Center Greece Archimedes Unit Athena Research Center Greece

ISBN: (纸本)9798891761834

We present Legal Argument Reasoning (LAR), a novel task designed to evaluate the legal reasoning capabilities of Large language Models (LLMs). The task requires selecting the correct next statement (from multiple choice options) in a chain of legal arguments from court proceedings, given the facts of the case. We constructed a dataset (LAR-ECHR) for this task using cases from the European Court of Human Rights (ECHR). We evaluated seven general-purpose LLMs on LAR-ECHR and found that (a) the ranking of the models is aligned with that of LegalBench, an established US-based legal reasoning benchmark, even though LAR-ECHR is based on EU law, (b) LAR-ECHR distinguishes top models more clearly, compared to LegalBench, (c) even the best model (GPT-4o) obtains 75.8% accuracy on LAR-ECHR, indicating significant potential for further model improvement. The process followed to construct LAR-ECHR can be replicated with cases from other legal systems. ©2024 Association for Computational Linguistics.

关键词： Case based reasoning

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：