检索结果-内蒙古大学图书馆

6th workshop on Clinical natural language processing, ClinicalNLP 2024, held at NAACL 2024

作者： Gunal, Aylin Lin, Baihan Bouneffouf, Djallel University of Michigan Ann ArborMI United States Icahn School of Medicine at Mount Sinai New YorkNY United States IBM Research Yorktown HeightsNY United States

ISBN: (纸本)9798891761094

Given the increasing demand for mental health assistance, artificial intelligence (AI), particularly large language models (LLMs), may be valuable for integration into automated clinical support systems. In this work, we leverage a decision transformer architecture for topic recommendation in counseling conversations between patients and mental health professionals. The architecture is utilized for offline reinforcement learning, and we extract states (dialogue turn embeddings), actions (conversation topics), and rewards (scores measuring the alignment between patient and therapist) from previous turns within a conversation to train a decision transformer model. We demonstrate an improvement over baseline reinforcement learning methods, and propose a novel system of utilizing our model’s output as synthetic labels for fine-tuning a large language model for the same task. Although our implementation based on LLaMA-2 7B has mixed results, future work can undoubtedly build on the design. © 2024 Association for Computational Linguistics.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Aspect-based Summarization of Climate Change Reports with Small language Models 3

Efficient Aspect-Based Summarization of Climate Change Repor...

引用

3rd workshop on NLP for Positive Impact, NLP4PI 2024, held in conjunction with the 2024 Conference on Empirical methods in natural language processing, EMNLP 2024

作者： Ghinassi, Iacopo Catalano, Leonardo Colella, Tommaso Queen Mary University of London London United Kingdom University of Pisa Pisa Italy

ISBN: (纸本)9798891761759

The use of natural language processing (NLP) for helping decision-makers with Climate Change action has recently been highlighted as a use case aligning with a broader drive towards NLP technologies for social good. In this context, Aspect-based Summarization (ABS) systems that extract and summarize relevant information are particularly useful as they provide stakeholders with a convenient way of finding relevant information in expert-curated reports. In this work, we release a new dataset for ABS of Climate Change reports and we employ different Large language Models (LLMs) and so-called Small language Models (SLMs) to tackle this problem in an unsupervised way. Considering the problem at hand, we also show how SLMs are not significantly worse for the problem while leading to reduced carbon footprint;we do so by applying for the first time an existing framework considering both energy efficiency and task performance to the evaluation of zero-shot generative models for ABS. Overall, our results show that modern language models, both big and small, can effectively tackle ABS for Climate Change reports but more research is needed when we frame the problem as a Retrieval Augmented Generation (RAG) problem and our work and dataset will help foster efforts in this direction. © 2024 Association for Computational Linguistics.

关键词： Kyoto Protocol

来源：评论

学校读者我要写书评

暂无评论

Lexicon-Augmented Cross-Domain Chinese Word Segmentation with graph Convolutional Network

引用

Chinese Journal of Electronics 2022年第5期31卷 949-957页

作者： YU Hao HUANG Kaiyu WANG Yu HUANG Degen School of Computer Science and Technology Dalian University of Technology School of Foreign Languages Dalian University of Technology

Existing neural approaches have achieved significant progress for Chinese word segmentation(CWS). The performances of these methods tend to drop dramatically in the cross-domain scenarios due to the data distribution mismatch across domains and the out of vocabulary words problem. To address these two issues,proposes a lexicon-augmented graph convolutional network for cross-domain CWS. The novel model can capture the information of word boundaries from all candidate words and utilize domain lexicons to alleviate the distribution gap across domains. Experimental results on the cross-domain CWS datasets(SIGHAN-2010 and TCM)show that the proposed method successfully models information of domain lexicons for neural CWS approaches and helps to achieve competitive performance for crossdomain CWS. The two problems of cross-domain CWS can be effectively solved through various interactions between characters and candidate words based on ***, experiments on the CWS benchmarks(Bakeoff-2005) also demonstrate the robustness and efficiency of the proposed method.

关键词： cross-domain CWS datasets candidate words neural CWS approaches vocabulary words problem text analysis vocabulary convolutional neural nets domain lexicons natural language processing lexicon-augmented cross-domain Chinese word segmentation graph neural networks lexicon-augmented graph convolutional network learning (artificial intelligence) cross-domain scenarios word processing word boundaries

来源：评论

学校读者我要写书评

暂无评论

COLING 2022 - proceedings of Textgraphs-16: graph-based methods for natural language processing, NLP 2022 - 29th International Conference on Computational Linguistics

COLING 2022 - Proceedings of TextGraphs-16: Graph-based Meth...

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

The proceedings contain 15 papers. The topics discussed include: multilevel hypernode graphs for effective and efficient entity linking;cross-modal contextualized hidden state projection method for expanding of taxonomic graphs;sharing parameter by conjugation for knowledge graph embeddings in complex space;a clique-based graphical approach to detect interpretable adjectival senses in Hungarian;the effectiveness of masked language modeling and adapters for factual knowledge injection;text-aware graph embeddings for donation behavior prediction;word sense disambiguation of French lexicographical examples using lexical networks;temporal graph analysis of misinformation spreaders in social media;IJS at Textgraphs-16 natural language premise selection task: will contextual information improve natural language premise selection?;and keyword-based natural language premise selection for an automatic mathematical statement proving.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Approach to Co-reference Resolution and Formula Grounding for Mathematical Identifiers using Large language Models 2

An Approach to Co-reference Resolution and Formula Grounding...

引用

2nd workshop on Mathematical natural language processing, MathNLP 2024

作者： Dev, Aamin Asakura, Takuto Sætre, Rune Germany Japan Norway

ISBN: (纸本)9782493814227

The high cost of human annotation labor and the advent of low-cost Large language Models (LLMs) offer opportunities to accelerate science. This study addresses the critical challenge of disambiguating mathematical identifiers in Mathematical language processing (MLP), a significant step toward the effective interpretation and utilization of mathematical documents. Unlike traditional annotation methods, which are labor-intensive and prone to inconsistencies, our approach leverages the capabilities of LLMs to automate the disambiguation process. We employ state-of-the-art LLMs, including GPT-3.5 and GPT-4, and open-source alternatives to generate a dictionary for annotating mathematical identifiers, linking each identifier to its conceivable descriptions, and then assigning these definitions to the respective identifier instances based on context. We offer a novel solution to the ambiguity problem inherent in mathematical expressions by exploiting this capability of LLMs which were unknown until now. Our extensive evaluation metrics include the CoNLL score for co-reference cluster quality and semantic correctness of the annotations. We demonstrate the effectiveness of our approach in resolving identifier ambiguities, thereby making a substantial contribution to the advancement of MLP. This work paves the way for future research in automating the interpretation of complex scientific texts, highlighting the potential of LLMs in transforming the landscape of mathematical documentation analysis, expanding model options, improving annotation coverage, and reducing annotation expenses. © 2024 ELRA language Resource Association.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

On the Efficiency of NLP-Inspired methods for Tabular Deep Learning 4

On the Efficiency of NLP-Inspired Methods for Tabular Deep L...

引用

4th NeurIPS Efficient natural language and Speech processing workshop

作者： Thielmann, Anton Frederik Samiee, Soheila BASF SE Germany BASF Canada Inc. Canada

Recent advancements in tabular deep learning (DL) have led to substantial performance improvements, surpassing the capabilities of traditional models. With the adoption of techniques from natural language processing (NLP), such as language model-based approaches, DL models for tabular data have also grown in complexity and size. Although tabular datasets do not typically pose scalability issues, the escalating size of these models has raised efficiency concerns. Despite its importance, efficiency has been relatively underexplored in tabular DL research. This paper critically examines the latest innovations in tabular DL, with a dual focus on performance and computational efficiency. The source code is available at https://***/basf/mamba-tabular. © 2024 proceedings of Machine Learning Research.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

NLP CHRISTINE@LT-EDI: RoBERTa & DeBERTa Fine-tuning for Detecting Signs of Depression from Social Media Text 3

NLP CHRISTINE@LT-EDI: RoBERTa & DeBERTa Fine-tuning for Dete...

引用

3rd workshop on language Technology for Equality, Diversity and Inclusion, LTEDI 2023

作者： Christodoulou, Christina Institute of Informatics & Telecommunications National Centre for Scientific Research "Demokritos" Athens Greece

ISBN: (纸本)9789544520847

The paper outlines the approach used to detect signs of depression from English social media text for the 4th Shared Task at LT-EDI@RANLP 2023. The solution involved data cleaning and pre-processing, leveraging additional data, addressing data imbalance, and fine-tuning RoBERTa-Large and DeBERTa-V3-Large transformer-based pre-trained language models. Four different model architectures were developed using different word embedding pooling methods, including a RoBERTa-Large bidirectional GRU model using GRU pooling and three DeBERTa models using CLS pooling, mean pooling, and max pooling, respectively. Although ensemble learning of DeBERTa’s pooling methods was used to improve performance, the RoBERTa bidirectional GRU model received the 8th place out of 31 submissions with a Macro-F1 score of 0.42. © 2023 LTEDI 2023 - 3rd workshop on language Technology for Equality, Diversity and Inclusion, associated with the 14th International Conference on Recent Advances in natural language processing, RANLP 2023 - proceedings. 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

Enhancing Scholarly Understanding: A Comparison of Knowledge Injection Strategies in Large language Models

Enhancing Scholarly Understanding: A Comparison of Knowledge...

引用

2023 workshop on Deep Learning for Knowledge graphs, DL4KG 2023

作者： Cadeddu, Andrea Chessa, Alessandro De Leo, Vincenzo Fenu, Gianni Motta, Enrico Osborne, Francesco Recupero, Diego Reforgiato Salatino, Angelo Secchi, Luca Linkalab s.r.l. Cagliari Italy Department of Mathematics and Computer Science University of Cagliari Cagliari Italy Knowledge Media Institute The Open University Milton Keynes United Kingdom Department of Business and Law University of Milano Bicocca Milan Italy

The use of transformer-based models like BERT for natural language processing has achieved remarkable performance across multiple domains. However, these models face challenges when dealing with very specialized domains, such as scientific literature. In this paper, we conduct a comprehensive analysis of knowledge injection strategies for transformers in the scientific domain, evaluating four distinct methods for injecting external knowledge into transformers. We assess these strategies in a single-label multi-class classification task involving scientific papers. For this, we develop a public benchmark based on 12k scientific papers from the AIDA knowledge graph, categorized into three fields. We utilize the Computer Science Ontology as our external knowledge source. Our findings indicate that most proposed knowledge injection techniques outperform the BERT baseline. © 2022 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

Vector-based Stylistic Analysis on Ancient Chinese Books: Take the Three Commentaries on the Spring and Autumn Annals as an Example 1

Vector-Based Stylistic Analysis on Ancient Chinese Books: Ta...

引用

1st workshop on Ancient language processing, ALP 2023

作者： Qi, Yue Liu, Liu Li, Bin Wang, Dongbo College of Information Management Nanjing Agricultural University Nanjing China School of Chinese Language and Literature Nanjing Normal University Nanjing China

ISBN: (纸本)9789544520878

Commentary of Gongyang, Commentary of Guliang, and Commentary of Zuo are collectively called the Three Commentaries on the Spring and Autumn Annals, which are the supplement and interpretation of the content of Spring and Autumn Annals with value in historical and literary research. In traditional research paradigms, scholars often explored the differences between the Three Commentaries within the details in contexts. Starting from the view of Stylistic Analysis, this paper examines the differences in the language style of the Three Commentaries through the representation of language, which takes the methods of deep learning. Specifically, this study vectorizes the context at word and sentence levels. It maps them into the same plane to find the differences between the use of words and sentences in the Three Commentaries. The results show that the Commentary of Gongyang and the Commentary of Guliang are relatively similar, while the Commentary of Zuo is significantly different. This paper verifies the feasibility of deep learning methods in stylistics study under computational humanities. It provides a valuable perspective for studying the Three Commentaries on the Spring and Autumn Annals. © RANLP-ALP 2023 - proceedings of the Ancient language processing workshop, associated with 14th International Conference on Recent Advances in natural language processing.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Team NLPeers at Chemotimelines 2024: Evaluation of two timeline extraction methods, can generative LLM do it all or is smaller model fine-tuning still relevant ? 6

Team NLPeers at Chemotimelines 2024: Evaluation of two timel...

引用

6th workshop on Clinical natural language processing, ClinicalNLP 2024, held at NAACL 2024

作者： Bannour, Nesrine Andrew, Judith Jeyafreeda Vincent, Marc Université de Paris Imagine Institute Data Science Platform INSERM UMR 1163 ParisF-75015 France Paris France

ISBN: (纸本)9798891761094

This paper presents our two deep learning-based approaches to participate in subtask 1 of the Chemotimelines 2024 Shared task. The first uses a fine-tuning strategy on a relatively small general domain Masked language Model (MLM) model, with additional normalization steps obtained using a simple Large language Model (LLM) prompting technique. The second is an LLM-based approach combining advanced automated prompt search with few-shot in-context learning using the DSPy framework. Our results confirm the continued relevance of the smaller MLM fine-tuned model. It also suggests that the automated few-shot LLM approach can perform close to the fine-tuning-based method without extra LLM normalization and be advantageous under scarce data access conditions. We finally hint at the possibility to choose between lower training examples or lower computing resources requirements when considering both methods. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

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：