检索结果-内蒙古大学图书馆

6th Workshop on Automated Semantic Analysis of Information in Legal Text, ASAIL 2023

作者： Savelka, Jaromir Ashley, Kevin D. Gray, Morgan A. Westermann, Hannes Xu, Huihui Computer Science Department Carnegie Mellon University PittsburghPA United States Intelligent Systems Program University of Pittsburgh PA United States Cyberjustice Laboratory Faculté de Droit Université de Montréal Montréal Canada

We evaluated the capability of generative pre-trained transformers (GPT-4) in analysis of textual data in tasks that require highly specialized domain expertise. Specifically, we focused on the task of analyzing court opinions to interpret legal concepts. We found that GPT-4, prompted with annotation guidelines, performs on par with well-trained law student annotators. We observed that, with a relatively minor decrease in performance, GPT-4 can perform batch predictions leading to significant cost reductions. However, employing chain-of-thought prompting did not lead to noticeably improved performance on this task. Further, we demonstrated how to analyze GPT-4's predictions to identify and mitigate deficiencies in annotation guidelines, and subsequently improve the performance of the model. Finally, we observed that the model is quite brittle, as small formatting related changes in the prompt had a high impact on the predictions. These findings can be leveraged by researchers and practitioners who engage in semantic/pragmatic annotations of texts in the context of the tasks requiring highly specialized domain expertise. © 2023 CEUR-WS. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Opinionfinder: A system for subjectivity analysis

Opinionfinder: A system for subjectivity analysis

引用

Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, HLT/EMNLP 2005, Co-located with the 2005 Document Understanding Conference, DUC and the 9th International Workshop on Parsing Technologies, IWPT

作者： Wilson, Theresa Hoffmann, Paul Somasundaran, Swapna Kessler, Jason Wiebe, Janyce Choi, Yejin Cardie, Claire Riloff, Ellen Patwardhan, Siddharth Intelligent Systems Program University of Pittsburgh Pittsburgh PA 15260 United States Department of Computer Science University of Pittsburgh Pittsburgh PA 15260 United States Department of Computer Science Cornell University Ithaca NY 14853 United States School of Computing University of Utah Salt Lake City UT 84112 United States

来源：评论

学校读者我要写书评

暂无评论

LEATHER: A Framework for Learning to Generate Human-like Text in Dialogue

arXiv

引用

arXiv 2022年

作者： Sicilia, Anthony Alikhani, Malihe Intelligent Systems Program United States Computer Science Department University of Pittsburgh PittsburghPA United States

Algorithms for text-generation in dialogue can be misguided. For example, in task-oriented settings, reinforcement learning that optimizes only task-success can lead to abysmal lexical diversity. We hypothesize this is due to poor theoretical understanding of the objectives in text-generation and their relation to the learning process (i.e., model training). To this end, we propose a new theoretical framework for learning to generate text in dialogue. Compared to existing theories of learning, our framework allows for analysis of the multifaceted goals inherent to text-generation. We use our framework to develop theoretical guarantees for learners that adapt to unseen data. As an example, we apply our theory to study data-shift within a cooperative learning algorithm proposed for the GuessWhat?! visual dialogue game. From this insight, we propose a new algorithm, and empirically, we demonstrate our proposal improves both task-success and human-likeness of the generated text. Finally, we show statistics from our theory are empirically predictive of multiple qualities of the generated dialogue, suggesting our theory is useful for model-selection when human evaluations are not available. © 2022, CC BY.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Boosting Weakly Supervised Object Detection using Fusion and Priors from Hallucinated Depth

arXiv

引用

arXiv 2023年

作者： Gungor, Cagri Kovashka, Adriana Intelligent Systems Program University of Pittsburgh United States Department of Computer Science University of Pittsburgh United States

Despite recent attention to depth for various tasks, it is still an unexplored modality for weakly-supervised object detection (WSOD). We propose an amplifier method for enhancing the performance of WSOD by integrating depth information. Our approach can be applied to different WSOD methods based on multiple-instance learning, without necessitating additional annotations or inducing large computational cost. Our proposed method employs monocular depth estimation to obtain hallucinated depth information, which is then incorporated into a Siamese WSOD network using contrastive loss and fusion. By analyzing the relationship between language context and depth, we calculate depth priors to identify the bounding box proposals that may contain an object of interest. These depth priors are then utilized to update the list of pseudo ground-truth boxes, or adjust the confidence of per-box predictions. We evaluate our proposed method on three datasets (COCO, PASCAL VOC, and Conceptual Captions) by implementing it on top of two state-of-the-art WSOD methods, and we demonstrate a substantial enhancement in performance. © 2023, CC BY.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Strategies to Leverage Foundational Model Knowledge in Object Affordance Grounding

Strategies to Leverage Foundational Model Knowledge in Objec...

引用

IEEE computer Society Conference on computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Arushi Rai Kyle Buettner Adriana Kovashka Department of Computer Science University of Pittsburgh PA USA Intelligent Systems Program University of Pittsburgh PA USA

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

An important task for intelligent systems is affordance grounding, where the goal is to locate regions on an object where an action can be performed. Past weakly supervised approaches learn from human-object interaction (HOI) by transferring grounding knowledge from exocentric to ego-centric views of an object. The use of HOI priors is inherently noisy and thus provides a limited source of supervision. To address this challenge, we identify that recent foundational models (i.e. VLMs and LLMs) can serve as auxiliary sources of knowledge for frameworks due to their vast world knowledge. In this work, we propose strategies to extract and leverage foundational model knowledge related to attributes and object parts to enhance an HOI-based affordance grounding framework. In particular, we propose to combine HOI and foundational model priors through (1) a spatial consistency loss and (2) heatmap aggregation. Our strategies result in mKLD and mNSS improvements, and insights suggest future directions for improving affordance grounding capabilities.

关键词： Heating systems computer vision Grounding Affordances Conferences Pipelines Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Keyword annotation of biomedicai documents with graph-based similarity methods

Keyword annotation of biomedicai documents with graph-based ...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Shuguang Wang Milos Hauskrecht Intelligent Systems Program University of Pittsburgh Pittsburgh USA Department of Computer Science University of Pittsburgh Pittsburgh USA

In this paper, we present a new approach that lets us extract, and represent relations among terms (concepts) in the documents and uses these relations to support various document analysis applications. Our approach works by building a graph of local co-occurrence relations among terms that are extracted directly from text and by defining a global similarity metric among these terms and sets of terms using the graph and its connectivity. We demonstrate the benefit of the approach on the problem of MeSH keyword annotation of documents based on their abstracts.

关键词： Measurement Kernel Resistance Immune system Standards Search engines Abstracts

来源：评论

学校读者我要写书评

暂无评论

Investigating the Role of Attribute Context in Vision-Language Models for Object Recognition and Detection

Investigating the Role of Attribute Context in Vision-Langua...

引用

IEEE Workshop on Applications of computer Vision (WACV)

作者： Kyle Buettner Adriana Kovashka Intelligent Systems Program University of Pittsburgh PA USA Department of Computer Science University of Pittsburgh PA USA

Vision-language alignment learned from image-caption pairs has been shown to benefit tasks like object recognition and detection. Methods are mostly evaluated in terms of how well object class names are learned, but captions also contain rich attribute context that should be considered when learning object alignment. It is unclear how methods use this context in learning, as well as whether models succeed when tasks require attribute and object understanding. To address this gap, we conduct extensive analysis of the role of attributes in vision-language models. We specifically measure model sensitivity to the presence and meaning of attribute context, gauging influence on object embeddings through unsupervised phrase grounding and classification via description methods. We further evaluate the utility of attribute context in training for open-vocabulary object detection, fine-grained text-region retrieval, and attribution tasks. Our results show that attribute context can be wasted when learning alignment for detection, attribute meaning is not adequately considered in embeddings, and describing classes by only their attributes is ineffective. A viable strategy that we find to increase benefits from attributes is contrastive training with adjective-based negative captions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning by diagramming Supreme Court oral arguments 07

Learning by diagramming Supreme Court oral arguments

引用

11th International Conference on Artificial Intelligence and Law

作者： Ashley, Kevin Pinkwart, Niels Lynch, Collin Aleven, Vincent LRDC School of Law University of Pittsburgh Pittsburgh PA United States Computer Science Institute Clausthal University of Technology Germany Intelligent Systems Program University of Pittsburgh Pittsburgh PA United States Human-Computer Interaction Institute Carnegie Mellon University Pittsburgh PA United States

ISBN: (纸本)1595936807

This paper describes an intelligent tutoring system, LARGO, that helps students learn skills of legal reasoning with hypotheticals by analyzing oral arguments before the US Supreme Court. The skills involve proposing a rule-like test for deciding a case, posing hypotheticals to challenge the rule, and responding by analogizing or distinguishing the hypotheticals and/or modifying the proposed test. Students diagram arguments in a special-purpose graphical language and receive feedback in the form of reflection questions. Copyright 2007 ACM.

关键词： intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Incorporating coherence of topics as a criterion in automatic response-to-text assessment of the organization of writing 10

Incorporating coherence of topics as a criterion in automati...

引用

10th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2015 at the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2015

作者： Rahimi, Zahra Litman, Diane Wang, Elaine Correnti, Richard Intelligent Systems Program University of Pittsburgh PittsburghPA15260 United States Department of Computer Science University of Pittsburgh PittsburghPA15260 United States Learning Research and Development Center University of Pittsburgh PittsburghPA15260 United States

ISBN: (纸本)9781941643358

This paper presents an investigation of score prediction for the Organization dimension of an assessment of analytical writing in response to text. With the long-term goal of producing feedback for students and teachers, we designed a task-dependent model that aligns with the scoring rubric and makes use of the source material. Our experimental results show that our rubric-based model performs as well as baselines on datasets from grades 6-8. On shorter and noisier essays from grades 5-6, the rubric-based model performs better than the baselines. Further, we show that the baseline model (lexical chaining) can be improved if we extend it with information from the source text for shorter and noisier data. © NAACL-HLT 2015. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Modeling Non-Cooperative Dialogue: Theoretical and Empirical Insights

arXiv

引用

arXiv 2022年

作者： Sicilia, Anthony Maidment, Tristan Healy, Pat Alikhani, Malihe Intelligent Systems Program University of Pittsburgh Pittsburgh United States Department of Informatics and Networked Systems University of Pittsburgh Pittsburgh United States Department of Computer Science and Intelligent Systems Program University of Pittsburgh Pittsburgh United States

Investigating cooperativity of interlocutors is central in studying pragmatics of dialogue. Models of conversation that only assume cooperative agents fail to explain the dynamics of strategic conversations. Thus, we investigate the ability of agents to identify non-cooperative interlocutors while completing a concurrent visual-dialogue task. Within this novel setting, we study the optimality of communication strategies for achieving this multi-task objective. We use the tools of learning theory to develop a theoretical model for identifying non-cooperative interlocutors and apply this theory to analyze different communication strategies. We also introduce a corpus of non-cooperative conversations about images in the GuessWhat?! dataset proposed by De Vries et al. (2017). We use reinforcement learning to implement multiple communication strategies in this context and find empirical results validate our theory. © 2022, CC BY.

关键词： Reinforcement learning

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：