检索结果-内蒙古大学图书馆

The Comprehensive Analysis of the Effect of Chinese Word Segmentation on Fuzzy-Based Classification Algorithms for Agricultural Questions

引用

INTERNATIONAL JOURNAL OF FUZZY SYSTEMS 2024年第8期26卷 2726-2749页

作者： Zhao, Xinyue Huang, Jianing Zhang, Jing Song, Yunsheng Shandong Agr Univ Sch Informat Sci & Engn Daizong St Tai An 271018 Shandong Peoples R China Shandong Agr Univ Key Lab Huang Huai Hai Smart Agr Technol Minist Agr & Rural Affars Daizong St Tai An 271018 Shandong Peoples R China

Fuzzy logic is the core method for handling uncertainty and vagueness of information in agricultural natural language processing, and it also plays a crucial role in word segmentation and text classification algorithms using the neural network. Word segmentation is often the primary step in Chinese text classification tasks and has a profound effect on the generation ability of classification algorithm-based fuzzy logic. However, the high complexity of text classification models structure and specificity of agricultural data take a great challenge to studying the effect of word segmentation. Although there have been several attempts to resolve this issue, the main effort focuses on word segment Precision or the generalization performance of multiple word segment methods for the same classification algorithm and does not involve agricultural text. To solve this problem from the perspective of rational analysis and empirical analysis, a comprehensive analysis has been made to study the effect of Chinese word segmentation on fuzzy-based classification algorithms for agricultural questions. It initially discusses the characteristics of agricultural questions for the subsequent analysis of the field adaptability of word segmentation and classification algorithms, employs fuzzy logic to convert the Chinese word segmentation task into a sequence labeling problem, and then analyzes the characteristics, techniques, and performance disparities of the seven mainstream open-source Chinese word segmentation integration tools at the current stage. Subsequently, an exploration has been conducted into the impact of Chinese word segmentation on the generalization performance of classification algorithms under the proposed unified model framework for text classification based on fuzzy logic. Finally, many experiments have been performed on the actual data crawled from typical agricultural websites to empirically study the differences and robustness of the effect of different word seg

关键词： Fuzzy logic Membership function natural language processing Word segmentation Agricultural question classification

来源：评论

学校读者我要写书评

暂无评论

FuxiTranyu: A Multilingual Large language Model Trained with Balanced Data

FuxiTranyu: A Multilingual Large Language Model Trained with...

引用

2024 conference on empirical methods in natural language processing, EMNLP 2024

作者： Sun, Haoran Jin, Renren Xu, Shaoyang Pan, Leiyu Supryadi Cui, Menglong Du, Jiangcun Lei, Yikun Yang, Lei Shi, Ling Xiao, Juesi Zhu, Shaolin Xiong, Deyi TJUNLP Lab College of Intelligence and Computing Tianjin University China

ISBN: (纸本)9798891761667

Large language models (LLMs) have demonstrated prowess in a wide range of tasks. However, many LLMs exhibit significant performance discrepancies between high- and low-resource languages. To mitigate this challenge, we present FuxiTranyu, an open-source multilingual LLM, which is designed to satisfy the need of the research community for balanced and high-performing multilingual capabilities. The base model, FuxiTranyu-8B, features 8 billion parameters and is trained from scratch on meticulously balanced multilingual data that contains 600 billion tokens covering 43 natural languages and 16 programming languages. We also develop two instruction-tuned models: FuxiTranyu-8B-SFT which is fine-tuned on a diverse multilingual instruction dataset, and FuxiTranyu-8B-DPO which is further refined with DPO on a preference dataset for enhanced alignment ability. Extensive experiments on a wide range of multilingual benchmarks demonstrate the competitive performance of FuxiTranyu against existing multilingual LLMs, e.g., BLOOM-7B, PolyLM-13B, and Mistral-7B-Instruct. Both neuron and representation interpretability analyses reveal that FuxiTranyu achieves consistent multilingual representations across languages. To promote further research into multilingual LLMs, we release both the base and instruction-tuned FuxiTranyu models together with 58 pre-training checkpoints at HuggingFace1 and Github. © 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

On the Effectiveness of Pre-Trained language Models for Legal natural language processing: An empirical Study

引用

IEEE ACCESS 2022年 10卷 75835-75858页

作者： Song, Dezhao Gao, Sally He, Baosheng Schilder, Frank Thomson Reuters Eagan MN 55123 USA Thomson Reuters New York NY 10036 USA Meta Platforms Inc Menlo Pk CA 94025 USA

We present the first comprehensive empirical evaluation of pre-trained language models (PLMs) for legal natural language processing (NLP) in order to examine their effectiveness in this domain. Our study covers eight representative and challenging legal datasets, ranging from 900 to 57K samples, across five NLP tasks: binary classification, multi-label classification, multiple choice question answering, summarization and information retrieval. We first run unsupervised, classical machine learning and/or non-PLM based deep learning methods on these datasets, and show that baseline systems' performance can be 4%similar to 35% lower than that of PLM-based methods. Next, we compare general-domain PLMs and those specifically pre-trained for the legal domain, and find that domain-specific PLMs demonstrate 1%similar to 5% higher performance than general-domain models, but only when the datasets are extremely close to the pre-training corpora. Finally, we evaluate six general-domain state-of-the-art systems, and show that they have limited generalizability to legal data, with performance gains from 0.1% to 1.2% over other PLM-based methods. Our experiments suggest that both general-domain and domain-specific PLM-based methods generally achieve better results than simpler methods on most tasks, with the exception of the retrieval task, where the best-performing baseline outperformed all PLM-based methods by at least 5%. Our findings can help legal NLP practitioners choose the appropriate methods for different tasks, and also shed light on potential future directions for legal NLP research.

关键词： Legal natural language processing pre-trained language model deep learning machine learning

来源：评论

学校读者我要写书评

暂无评论

PerturbScore: Connecting Discrete and Continuous Perturbations in NLP

PerturbScore: Connecting Discrete and Continuous Perturbatio...

引用

conference on empirical methods in natural language processing (EMNLP)

作者： Li, Linyang Ren, Ke Shao, Yunfan Wang, Pengyu Qiu, Xipeng Fudan Univ Sch Comp Sci Shanghai Peoples R China Fudan Univ Shanghai Key Lab Intelligent Informat Proc Shanghai Peoples R China

ISBN: (纸本)9798891760615

With the rapid development of neural network applications in NLP, model robustness problem is gaining more attention. Different from computer vision, the discrete nature of texts makes it more challenging to explore robustness in NLP. Therefore, in this paper, we aim to connect discrete perturbations with continuous perturbations, therefore we can use such connections as a bridge to help understand discrete perturbations in NLP models. Specifically, we first explore how to connect and measure the correlation between discrete perturbations and continuous perturbations. Then we design a regression task as a PerturbScore to learn the correlation automatically. Through experimental results, we find that we can build a connection between discrete and continuous perturbations and use the proposed PerturbScore to learn such correlation, surpassing previous methods used in discrete perturbation measuring. Further, the proposed PerturbScore can be well generalized to different datasets, perturbation methods, indicating that we can use it as a powerful tool to study model robustness in NLP. (1)

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

FastMem: Fast Memorization of Prompt Improves Context Awareness of Large language Models

FastMem: Fast Memorization of Prompt Improves Context Awaren...

引用

2024 conference on empirical methods in natural language processing, EMNLP 2024

作者： Zhu, Junyi Liu, Shuochen Yu, Yu Tang, Bo Yan, Yibo Li, Zhiyu Xiong, Feiyu Xu, Tong Blaschko, Matthew B. ESAT-PSI KU Leuven Belgium University of Science and Technology of China China Institute for Advanced Algorithms Research Shanghai China National University of Singapore Singapore

ISBN: (纸本)9798891761681

Large language models (LLMs) excel in generating coherent text, but they often struggle with context awareness, leading to inaccuracies in tasks requiring faithful adherence to provided information. We introduce FastMem, a novel method designed to enhance instruction fine-tuned LLMs' context awareness through fast memorization of the prompt. FastMem maximizes the likelihood of the prompt before inference by updating only the last Feed-Forward Network (FFN) module. This targeted approach ensures efficient optimization without overfitting, significantly improving the model's ability to comprehend and accurately follow the context. Our experiments demonstrate substantial gains in reading comprehension, text summarization and adherence to output structures. For instance, FastMem improves the accuracy of Llama 3-8B-Inst on the NQ-SWAP dataset from 59.1% to 71.6%, and reduces the output structure failure rate of Qwen 1.5-4B-Chat from 34.9% to 25.5%. Extensive experimental results highlight FastMem's potential to offer a robust solution to enhance the reliability and accuracy of LLMs in various applications. Our code is available at: https://***/IAAR-Shanghai/FastMem. © 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

Developing a Pragmatic Benchmark for Assessing Korean Legal language Understanding in Large language Models

Developing a Pragmatic Benchmark for Assessing Korean Legal ...

引用

2024 conference on empirical methods in natural language processing, EMNLP 2024

作者： Kim, Yeeun Choi, Jinhwan Choi, Young Rok Park, Hai Jin Choi, Eunkyung Hwang, Wonseok University of Seoul Korea Republic of LBox Korea Republic of Hanyang University Korea Republic of

ISBN: (纸本)9798891761681

Large language models (LLMs) have demonstrated remarkable performance in the legal domain, with GPT-4 even passing the Uniform Bar Exam in the U.S. However their efficacy remains limited for non-standardized tasks and tasks in languages other than English. This underscores the need for careful evaluation of LLMs within each legal system before application. Here, we introduce KBL, a benchmark for assessing the Korean legal language understanding of LLMs, consisting of (1) 7 legal knowledge tasks (510 examples), (2) 4 legal reasoning tasks (288 examples), and (3) the Korean bar exam (4 domains, 53 tasks, 2,510 examples). First two datasets were developed in close collaboration with lawyers to evaluate LLMs in practical scenarios in a certified manner. Furthermore, considering legal practitioners' frequent use of extensive legal documents for research, we assess LLMs in both a closed book setting, where they rely solely on internal knowledge, and a retrieval-augmented generation (RAG) setting, using a corpus of Korean statutes and precedents. The results indicate substantial room and opportunities for improvement. © 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

LAMBDA: Large language Model-Based Data Augmentation for Multi-Modal Machine Translation

LAMBDA: Large Language Model-Based Data Augmentation for Mul...

引用

2024 conference on empirical methods in natural language processing, EMNLP 2024

作者： Wang, Yusong Li, Dongyuan Shen, Jialun Xu, Yicheng Xu, Mingkun Funakoshi, Kotaro Okumura, Manabu Tokyo Institute of Technology Tokyo Japan Guangdong Institute of Intelligence Science and Technology Hengqin Guangdong Zhuhai519031 China

ISBN: (纸本)9798891761681

Multi-modal machine translation (MMT) can reduce ambiguity and semantic distortion compared with traditional machine translation (MT) by utilizing auxiliary information such as images. However, current MMT methods face two primary challenges. The first is their underperformance compared to MT methods based on pre-trained models. The second is the inadequate exploitation and integration of the image modality within the model, primarily due to a lack of triplet training data. A mainstream approach is to introduce large amounts of parallel and monolingual data to train the text model and the visual model separately. However, incorporating extensive external data can result in data imbalance, which may introduce biases during training. Additionally, the collection and cleaning of such large datasets is labor-intensive. To overcome these challenges, we introduce a novel, low-cost, large language model-based data augmentation method called LAMBDA, which can enrich the original samples and expand the dataset without requiring external images and text. We propose a fine-grained image captioning module with a noise filter to hierarchically and accurately extract unexploited information from images. Additionally, we design two specific prompts to guide the GPT-3.5 model in generating enriched texts and the corresponding translations. The enriched samples contain diverse text and strong connections between text and images, leading to significant improvements for MMT baselines, with the highest being an increase of up to 3.83 BLEU score and 3.61 METEOR score. © 2024 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

Ask-before-Plan: Proactive language Agents for Real-World Planning

Ask-before-Plan: Proactive Language Agents for Real-World Pl...

引用

2024 conference on empirical methods in natural language processing, EMNLP 2024

作者： Zhang, Xuan Deng, Yang Ren, Zifeng Ng, See-Kiong Chua, Tat-Seng National University of Singapore Singapore Singapore Management University Singapore

ISBN: (纸本)9798891761681

The evolution of large language models (LLMs) has enhanced the planning capabilities of language agents in diverse real-world scenarios. Despite these advancements, the potential of LLM-powered agents to comprehend ambiguous user instructions for reasoning and decision-making is still under exploration. In this work, we introduce a new task, Proactive Agent Planning, which requires language agents to predict clarification needs based on user-agent conversation and agent-environment interaction, invoke external tools to collect valid information, and generate a plan to fulfill the user's demands. To study this practical problem, we establish a new benchmark dataset, Ask-before-Plan. To tackle the deficiency of LLMs in proactive planning, we propose a novel multi-agent framework, Clarification-Execution-Planning (CEP), which consists of three agents specialized in clarification, execution, and planning. We introduce the trajectory tuning scheme for the clarification agent and static execution agent, as well as the memory recollection mechanism for the dynamic execution agent. Extensive evaluations and comprehensive analyses conducted on the Ask-before-Plan dataset validate the effectiveness of our proposed framework. © 2024 Association for Computational Linguistics.

关键词： Clarifiers

来源：评论

学校读者我要写书评

暂无评论

Transformer Working Memory Enables Regular language Reasoning And natural language Length Extrapolation

Transformer Working Memory Enables Regular Language Reasonin...

引用

conference on empirical methods in natural language processing (EMNLP)

作者： Chi, Ta-Chung Fan, Ting-Han Rudnicky, Alexander I. Ramadge, Peter J. Carnegie Mellon Univ Pittsburgh PA 15213 USA Princeton Univ Princeton NJ 08544 USA

ISBN: (纸本)9798891760615

Unlike recurrent models, conventional wisdom has it that Transformers cannot perfectly model regular languages. Inspired by the notion of working memory, we propose a new Transformer variant named RegularGPT. With its novel combination of Weight-Sharing, Adaptive-Depth, and Sliding-Dilated-Attention, RegularGPT constructs working memory along the depth dimension, thereby enabling efficient and successful modeling of regular languages such as PARITY. We further test RegularGPT on the task of natural language length extrapolation and surprisingly find that it rediscovers the local windowed attention effect deemed necessary in prior work for length extrapolation.

关键词： Extrapolation

来源：评论

学校读者我要写书评

暂无评论

GAMA: A Large Audio-language Model with Advanced Audio Understanding and Complex Reasoning Abilities

GAMA: A Large Audio-Language Model with Advanced Audio Under...

引用

2024 conference on empirical methods in natural language processing, EMNLP 2024

作者： Ghosh, Sreyan Kumar, Sonal Seth, Ashish Evuru, Chandra Kiran Reddy Tyagi, Utkarsh Sakshi, S. Nieto, Oriol Duraiswami, Ramani Manocha, Dinesh University of Maryland College Park United States Adobe United States

ISBN: (纸本)9798891761643

Perceiving and understanding non-speech sounds and non-verbal speech is essential to making decisions that help us interact with our surroundings. In this paper, we propose GAMA, a novel General-purpose Large Audiolanguage Model (LALM) with Advanced Audio Understanding and Complex Reasoning Abilities. We build GAMA by integrating an LLM with multiple types of audio representations, including features from a custom Audio Q-Former, a multi-layer aggregator that aggregates features from multiple layers of an audio encoder. We fine-tune GAMA on a large-scale audio-language dataset, which augments it with audio understanding capabilities. Next, we propose CompA-R (Instruction-Tuning for Complex Audio Reasoning), a synthetically generated instruction-tuning (IT) dataset with instructions that require the model to perform complex reasoning on the input audio. We instruction-tune GAMA with CompA-R to endow it with complex reasoning abilities, where we further add a soft prompt as input with high-level semantic evidence by leveraging event tags of the input audio. Finally, we also propose CompA-R-test, a human-labeled evaluation dataset for evaluating the capabilities of LALMs on open-ended audio question-answering that requires complex reasoning. Through automated and expert human evaluations, we show that GAMA outperforms all other LALMs in literature on diverse audio understanding tasks by margins of 1%-84% and demonstrates state-of-the-art performance on deductive reasoning and hallucination evaluation benchmarks. Further, GAMA IT-ed on CompA-R proves to be superior in its complex reasoning capabilities. © 2024 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

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：