检索结果-内蒙古大学图书馆

Explainable Video Topics for Content Taxonomy: A Multimodal Retrieval Approach to Industry-Compliant Contextual Advertising

引用

IEEE ACCESS 2025年 13卷 30597-30612页

作者： de Silva, Waruna Fernando, Anil Univ Strathclyde Dept Comp & Informat Sci Glasgow G1 1XQ Scotland

Owing to the increased video content consumption in recent years, the need for advanced contextual advertising methods that leverage increasing user engagement and relevance on advertisement-based video-on-demand platforms has increased. Traditional behavior-based advertisement targeting is waning, particularly owing to the recent strict privacy policies that favor user consent and privacy. This study proposes an innovative approach for integrating advanced natural language processing with multimodal analysis for video contextual advertising. To this end, transformer-based architectures, specifically BERTopic, computer vision techniques, and large language models were used to extract sets of topics from visual and textual video data automatically and systematically. The proposed framework decodes the taxonomy of content efficiently through videos in different levels of noise and languages. empirical analysis of the YouTube-8M dataset shows the potential for the approach to change the paradigm in video advertising. Built to be scalable and easily adaptable, this solution can handle multifarious and complex user-generated content well, suited for a wide range of applications across various media platforms.

关键词： Advertising Semantics Visualization Taxonomy Analytical models Feature extraction Context modeling Streaming media Media Image color analysis natural language processing video contextual advertisements multimodal fusion topic modeling BERTopic contextual taxonomy standards multi-label classification

来源：评论

学校读者我要写书评

暂无评论

Understanding and Mitigating language Confusion in LLMs

Understanding and Mitigating Language Confusion in LLMs

引用

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

作者： Marchisio, Kelly Ko, Wei-Yin Bérard, Alexandre Dehaze, Théo Ruder, Sebastian Cohere

ISBN: (纸本)9798891761643

We investigate a surprising limitation of LLMs: their inability to consistently generate text in a user's desired language. We create the language Confusion Benchmark (LCB) to evaluate such failures, covering 15 typologically diverse languages with existing and newly-created English and multilingual prompts. We evaluate a range of LLMs on monolingual and crosslingual generation reflecting practical use cases, finding that Llama Instruct and Mistral models exhibit high degrees of language confusion and even the strongest models fail to consistently respond in the correct language. We observe that base and English-centric instruct models are more prone to language confusion, which is aggravated by complex prompts and high sampling temperatures. We find that language confusion can be partially mitigated via few-shot prompting, multilingual SFT and preference tuning. We release our language confusion benchmark, which serves as a first layer of efficient, scalable multilingual evaluation. © 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

Why LLMs Hallucinate, And How To Get (Evidential) Closure: Perceptual, Intensional and Extensional Learning for Faithful natural language Generation

Why LLMs Hallucinate, And How To Get (Evidential) Closure: P...

引用

conference on empirical methods in natural language processing (EMNLP)

作者： Bouyamourn, Adam Univ Calif Berkeley Berkeley CA 94720 USA

ISBN: (纸本)9798891760608

We show that LLMs hallucinate because their output is not constrained to be synonymous with claims for which they have evidence: a condition that we call evidential closure. Information about the truth or falsity of sentences is not statistically identified in the standard neural language generation setup, and so cannot be conditioned on to generate new strings. We then show how to constrain LLMs to produce output that satisfies evidential closure. A multimodal LLM must learn about the external world (perceptual learning);it must learn a mapping from strings to states of the world (extensional learning);and, to achieve fluency when generalizing beyond a body of evidence, it must learn mappings from strings to their synonyms (intensional learning). The output of a unimodal LLM must be synonymous with strings in a validated evidence set. Finally, we present a heuristic procedure, Learn-Babble-Prune, that yields faithful output from an LLM by rejecting output that is not synonymous with claims for which the LLM has evidence.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

SRAP-Agent: Simulating and Optimizing Scarce Resource Allocation Policy with LLM-based Agent

SRAP-Agent: Simulating and Optimizing Scarce Resource Alloca...

引用

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

作者： Ji, Jiarui Li, Yang Liu, Hongtao Du, Zhicheng Wei, Zhewei Shen, Weiran Qi, Qi Lin, Yankai Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China

ISBN: (纸本)9798891761681

Public scarce resource allocation plays a crucial role in economics as it directly influences the efficiency and equity in society. Traditional studies including theoretical model-based, empirical study-based and simulation-based methods encounter limitations due to the idealized assumption of complete information and individual rationality, as well as constraints posed by limited available data. In this work, we propose an innovative framework, SRAP-Agent (Simulating and Optimizing Scarce Resource Allocation Policy with LLM-based Agent), which integrates Large language Models (LLMs) into economic simulations, aiming to bridge the gap between theoretical models and real-world dynamics. Using public housing allocation scenarios as a case study, we conduct extensive policy simulation experiments to verify the feasibility and effectiveness of the SRAP-Agent and employ the Policy Optimization Algorithm with certain optimization objectives. The source code can be found in https://***/jijiarui-cather/SRAPAgent_Framework. © 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

Exploring Distributional Shifts in Large language Models for Code Analysis

Exploring Distributional Shifts in Large Language Models for...

引用

conference on empirical methods in natural language processing (EMNLP)

作者： Arakelyan, Shushan Das, Rocktim Jyoti Mao, Yi Ren, Xiang Univ Southern Calif Los Angeles CA 90007 USA IIT Delhi India MBZUAI Abu Dhabi U Arab Emirates Microsoft Azure AI Redmond WA USA

ISBN: (纸本)9798891760608

We systematically study how three large language models with code capabilities - CodeT5, Codex, and ChatGPT - generalize to out-of-domain data. We consider two fundamental applications - code summarization, and code generation. We split data into domains following its natural boundaries - by an organization, by a project, and by a module within the software project. We establish that samples from each new domain present all the models with a significant challenge of distribution shift. We study how established methods adapt models to better generalize to new domains. Our experiments show that while multitask learning alone is a reasonable baseline, combining it with few-shot finetuning on examples retrieved from training data can achieve very strong performance. Moreover, this solution can outperform direct finetuning for very low-data scenarios. Finally, we consider variations of this approach to create a more broadly applicable method to adapt to multiple domains at once. We find that for code generation, a model adapted to multiple domains simultaneously performs on par with those adapted to a single domain(1).

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Cross-domain NER with Generated Task-Oriented Knowledge: An empirical Study from Information Density Perspective

Cross-domain NER with Generated Task-Oriented Knowledge: An ...

引用

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

作者： Zhang, Zhihao Lee, Sophia Yat Mei Wu, Junshuang Zhang, Dong Li, Shoushan Cambria, Erik Zhou, Guodong School of Computer Science & Technology NLP Lab Soochow University China Department of Chinese and Bilingual Studies The Hong Kong Polytechnic University Hong Kong Beijing Jinghang Research Institute of Computing and Communication China College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)9798891761643

Cross-domain Named Entity Recognition (CDNER) is crucial for Knowledge Graph (KG) construction and natural language processing (NLP), enabling learning from source to target domains with limited data. Previous studies often rely on manually collected entity-relevant sentences from the web or attempt to bridge the gap between tokens and entity labels across domains. These approaches are time-consuming and inefficient, as these data are often weakly correlated with the target task and require extensive pre-training. To address these issues, we propose automatically generating task-oriented knowledge (GTOK) using large language models (LLMs), focusing on the reasoning process of entity extraction. Then, we employ task-oriented pre-training (TOPT) to facilitate domain adaptation. Additionally, current cross-domain NER methods often lack explicit explanations for their effectiveness. Therefore, we introduce the concept of information density to better evaluate the model's effectiveness before performing entity recognition. We conduct systematic experiments and analyses to demonstrate the effectiveness of our proposed approach and the validity of using information density for model evaluation. © 2024 Association for Computational Linguistics.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

On Bilingual Lexicon Induction with Large language Models

On Bilingual Lexicon Induction with Large Language Models

引用

conference on empirical methods in natural language processing (EMNLP)

作者： Li, Yaoyiran Korhonen, Anna Vulic, Ivan Univ Cambridge Language Technol Lab TAL Cambridge England

ISBN: (纸本)9798891760608

Bilingual Lexicon Induction (BLI) is a core task in multilingual NLP that still, to a large extent, relies on calculating cross-lingual word representations. Inspired by the global paradigm shift in NLP towards Large language Models (LLMs), we examine the potential of the latest generation of LLMs for the development of bilingual lexicons. We ask the following research question: Is it possible to prompt and fine-tune multilingual LLMs (mLLMs) for BLI, and how does this approach compare against and complement current BLI approaches? To this end, we systematically study 1) zero-shot prompting for unsupervised BLI and 2) few-shot in-context prompting with a set of seed translation pairs, both without any LLM finetuning, as well as 3) standard BLI-oriented finetuning of smaller LLMs. We experiment with 18 open-source text-to-text mLLMs of different sizes (from 0.3B to 13B parameters) on two standard BLI benchmarks covering a range of typologically diverse languages. Our work is the first to demonstrate strong BLI capabilities of text-to-text mLLMs. The results reveal that few-shot prompting with in-context examples from nearest neighbours achieves the best performance, establishing new state-of-the-art BLI scores for many language pairs. We also conduct a series of in-depth analyses and ablation studies, providing more insights on BLI with (m)LLMs, also along with their limitations.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Prompting is not a substitute for probability measurements in large language models

Prompting is not a substitute for probability measurements i...

引用

conference on empirical methods in natural language processing (EMNLP)

作者： Hu, Jennifer Levy, Roger Harvard Univ Kempner Inst Cambridge MA 02138 USA MIT Dept Brain & Cognit Sci Cambridge MA USA

ISBN: (纸本)9798891760608

Prompting is now a dominant method for evaluating the linguistic knowledge of large language models (LLMs). While other methods directly read out models' probability distributions over strings, prompting requires models to access this internal information by processing linguistic input, thereby implicitly testing a new type of emergent ability: metalinguistic judgment. In this study, we compare metalinguistic prompting and direct probability measurements as ways of measuring models' linguistic knowledge. Broadly, we find that LLMs' metalinguistic judgments are inferior to quantities directly derived from representations. Furthermore, consistency gets worse as the prompt query diverges from direct measurements of next-word probabilities. Our findings suggest that negative results relying on metalinguistic prompts cannot be taken as conclusive evidence that an LLM lacks a particular linguistic generalization. Our results also highlight the value that is lost with the move to closed APIs where access to probability distributions is limited.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

Dealing with Controversy: An Emotion and Coping Strategy Corpus Based on Role Playing

Dealing with Controversy: An Emotion and Coping Strategy Cor...

引用

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

作者： Troiano, Enrica Labat, Sofie Stranisci, Marco Antonio Patti, Viviana Damiano, Rossana Klinger, Roman Computational Linguistics and Text Mining Lab Vrije Universiteit Amsterdam Netherlands HK3Lab Rovereto Italy LT3 Language and Translation Technology Team Ghent University Belgium Dipartimento di Informatica Università degli Studi di Torino Italy Aequa-Tech Turin Italy Fundamentals of Natural Language Processing University of Bamberg Germany

ISBN: (纸本)9798891761681

There is a mismatch between psychological and computational studies on emotions. Psychological research aims at explaining and documenting internal mechanisms of these phenomena, while computational work often simplifies them into labels. Many emotion fundamentals remain under-explored in natural language processing, particularly how emotions develop and how people cope with them. To help reduce this gap, we follow theories on coping, and treat emotions as strategies to cope with salient situations (i.e., how people deal with emotion-eliciting events). This approach allows us to investigate the link between emotions and behavior, which also emerges in language. We introduce the task of coping identification, together with a corpus to do so, constructed via role-playing. We find that coping strategies realize in text even though they are challenging to recognize, both for humans and automatic systems trained and prompted on the same task. We thus open up a promising research direction to enhance the capability of models to better capture emotion mechanisms from text. © 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

AN empirical INVESTIGATION OF DOMAIN ADAPTATION ABILITY FOR CHINESE SPELLING CHECK MODELS 49

AN EMPIRICAL INVESTIGATION OF DOMAIN ADAPTATION ABILITY FOR ...

引用

49th IEEE International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Wang, Xi Zhao, Ruoqing Dai, Hongliang Li, Piji Nanjing Univ Aeronaut & Astronaut Nanjing Peoples R China

ISBN: (纸本)9798350344868;9798350344851

Chinese Spelling Check (CSC) is a meaningful task in the area of natural language processing (NLP) which aims at detecting spelling errors in Chinese texts and then correcting these errors. However, CSC models are based on pretrained language models, which are trained on a general corpus. Consequently, their performance may drop when confronted with downstream tasks involving domain-specific terms. In this paper, we conduct a thorough evaluation about the domain adaption ability of various typical CSC models by building three new datasets encompassing rich domain-specific terms from the financial, medical, and legal domains. Then we conduct empirical investigations in the corresponding domain-specific test datasets to ascertain the cross-domain adaptation ability of several typical CSC models. We also test the performance of the popular large language model ChatGPT. As shown in our experiments, the performances of the CSC models drop significantly in the new domains.

关键词： natural language processing Chinese Spelling Check Domain Adaptation

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：