检索结果-内蒙古大学图书馆

Analysing domain suitability of a sentiment lexicon by identifying distributionally bipolar words 6

学校读者我要写书评

暂无评论

Analysing domain suitability of a sentiment lexicon by ident...

6th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, WASSA 2015 at the 2015 Conference on Empirical Methods in Natural Language processing, EMNLP 2015

作者： Flekova, Lucie Ruppert, Eugen Preoţiuc-Pietro, Daniel Ubiquitous Knowledge Processing Lab Technische Universität Darmstadt Germany FG Language Technology Technische Universität Darmstadt Germany Computer and Information Science University of Pennsylvania United States

ISBN: (纸本)9781941643327

Contemporary sentiment analysis approaches rely heavily on lexicon based methods. This is mainly due to their simplicity, although the best empirical results can be achieved by more complex techniques. We introduce a method to assess suitability of generic sentiment lexicons for a given domain, namely to identify frequent bigrams where a polar word switches polarity. Our bigrams are scored using Lexicographers Mutual Information and leveraging large automatically obtained corpora. Our score matches human perception of polarity and demonstrates improvements in classification results using our enhanced context-aware method. Our method enhances the assessment of lexicon based sentiment detection algorithms and can be further used to quantify ambiguous words. © 2015 Association for Computational Linguistics.

关键词： Sentiment analysis

Hierarchy identification for automatically generating table-of-contents

学校读者我要写书评

暂无评论

Hierarchy identification for automatically generating table-...

9th International Conference on Recent Advances in Natural Language processing, RANLP 2013

作者： Erbs, Nicolai Gurevych, Iryna Zesch, Torsten Ubiquitous Knowledge Processing Lab. Department of Computer Science Technische Universität Darmstadt Germany Information Center for Education German Institute for Educational Research and Educational Information Germany Language Technology University of Duisburg-Essen Germany

A table-of-contents (TOC) provides a quick reference to a document's content and structure. We present the first study on identifying the hierarchical structure for automatically generating a TOC using only textual features instead of structural hints e.g. from HTML-tags. We create two new datasets to evaluate our approaches for hierarchy identification. We find that our algorithm performs on a level that is sufficient for a fully automated system. For documents without given segment titles, we extend our work by automatically generating segment titles. We make the datasets and our experimental framework publicly available in order to foster future research in TOC generation.

关键词： Automation

Bayesian heatmaps: Probabilistic classification with multiple unreliable information sources

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Simpson, Edwin Reece, Steven Roberts, Stephen J. Ubiquitous Knowledge Processing Lab Department of Computer Science Technische Universität Darmstadt Department of Engineering Science University of Oxford

Unstructured data from diverse sources, such as social media and aerial imagery, can provide valuable up-to-date information for intelligent situation assessment. Mining these different information sources could bring major benefits to applications such as situation awareness in disaster zones and mapping the spread of diseases. Such applications depend on classifying the situation across a region of interest, which can be depicted as a spatial "heatmap". Annotating unstructured data using crowdsourcing or automated classifiers produces individual classifications at sparse locations that typically contain many errors. We propose a novel Bayesian approach that models the relevance, error rates and bias of each information source, enabling us to learn a spatial Gaussian Process classifier by aggregating data from multiple sources with varying reliability and relevance. Our method does not require gold-labelled data and can make predictions at any location in an area of interest given only sparse observations. We show empirically that our approach can handle noisy and biased data sources, and that simultaneously inferring reliability and transferring information between neighbouring reports leads to more accurate predictions. We demonstrate our method on two real-world problems from disaster response, showing how our approach reduces the amount of crowdsourced data required and can be used to generate valuable heatmap visualisations from SMS messages and satellite images. Copyright © 2019, The Authors. All rights reserved.

关键词： Crowdsourcing

Scalable Bayesian Preference Learning for Crowds

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Simpson, Edwin Gurevych, Iryna Ubiquitous Knowledge Processing Lab Dept. of Computer Science Technische Universität Darmstadt

We propose a scalable Bayesian preference learning method for jointly predicting the preferences of individuals as well as the consensus of a crowd from pairwise labels. Peoples’ opinions often differ greatly, making it difficult to predict their preferences from small amounts of personal data. Individual biases also make it harder to infer the consensus of a crowd when there are few labels per item. We address these challenges by combining matrix factorisation with Gaussian processes, using a Bayesian approach to account for uncertainty arising from noisy and sparse data. Our method exploits input features, such as text embeddings and user metadata, to predict preferences for new items and users that are not in the training set. As previous solutions based on Gaussian processes do not scale to large numbers of users, items or pairwise labels, we propose a stochastic variational inference approach that limits computational and memory costs. Our experiments on a recommendation task show that our method is competitive with previous approaches despite our scalable inference approximation. We demonstrate the method’s scalability on a natural language processing task with thousands of users and items, and show improvements over the state of the art on this task. We make our software publicly available for future work 1. Copyright © 2019, The Authors. All rights reserved.

关键词： Gaussian distribution

DP-Rewrite: Towards Reproducibility and Transparency in Differentially Private Text Rewriting

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Igamberdiev, Timour Arnold, Thomas Habernal, Ivan Trustworthy Human Language Technologies Ubiquitous Knowledge Processing Lab Department of Computer Science Technical University of Darmstadt Germany

Text rewriting with differential privacy (DP) provides concrete theoretical guarantees for protecting the privacy of individuals in textual documents. In practice, existing systems may lack the means to validate their privacy-preserving claims, leading to problems of transparency and reproducibility. We introduce DP-Rewrite, an open-source framework for differentially private text rewriting which aims to solve these problems by being modular, extensible, and highly customizable. Our system incorporates a variety of downstream datasets, models, pre-training procedures, and evaluation metrics to provide a flexible way to lead and validate private text rewriting research. To demonstrate our software in practice, we provide a set of experiments as a case study on the ADePT DP text rewriting system, detecting a privacy leak in its pre-training approach. Our system is publicly available, and we hope that it will help the community to make DP text rewriting research more accessible and transparent. © 2022, CC BY-SA.

关键词： Transparency

Are Emergent Abilities in Large Language Models just In-Context Learning?

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lu, Sheng Bigoulaeva, Irina Sachdeva, Rachneet Madabushi, Harish Tayyar Gurevych, Iryna Ubiquitous Knowledge Processing Lab Technical University of Darmstadt Germany Department of Computer Science The University of Bath United Kingdom

Large language models, comprising billions of parameters and pre-trained on extensive web-scale corpora, have been claimed to acquire certain capabilities without having been specifically trained on them. These capabilities, referred to as "emergent abilities," have been a driving force in discussions regarding the potentials and risks of language models. A key challenge in evaluating emergent abilities is that they are confounded by model competencies that arise through alternative prompting techniques, including in-context learning, which is the ability of models to complete a task based on a few examples. We present a novel theory that explains emergent abilities, taking into account their potential confounding factors, and rigorously substantiate this theory through over 1000 experiments. Our findings suggest that purported emergent abilities are not truly emergent, but result from a combination of in-context learning, model memory, and linguistic knowledge. Our work is a foundational step in explaining language model performance, providing a template for their efficient use and clarifying the paradox of their ability to excel in some instances while faltering in others. Thus, we demonstrate that their capabilities should not be overestimated. 1 © 2023, CC BY-SA.

关键词： Contrastive Learning

Focusing knowledge-based graph argument mining via topic modeling

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Abels, Patrick Ahmadi, Zahra Burkhardt, Sophie Schiller, Benjamin Gurevych, Iryna Kramer, Stefan Johannes Gutenberg University Mainz Germany Ubiquitous Knowledge Processing Lab Department of Computer Science Technical University of Darmstadt Germany

Decision-making usually takes five steps: identifying the problem, collecting data, extracting evidence, identifying pro and con arguments, and making decisions. Focusing on extracting evidence, this paper presents a hybrid model that combines latent Dirichlet allocation and word embeddings to obtain external knowledge from structured and unstructured data. We study the task of sentence-level argument mining, as arguments mostly require some degree of world knowledge to be identified and understood. Given a topic and a sentence, the goal is to classify whether a sentence represents an argument in regard to the topic. We use a topic model to extract topic- and sentence-specific evidence from the structured knowledge base Wikidata, building a graph based on the cosine similarity between the entity word vectors of Wikidata and the vector of the given sentence. Also, we build a second graph based on topic-specific articles found via Google to tackle the general incompleteness of structured knowledge bases. Combining these graphs, we obtain a graph-based model which, as our evaluation shows, successfully capitalizes on both structured and unstructured data. © 2021, CC BY-NC-SA.

关键词： knowledge based systems

Fine-tuned neural models for Propaganda Detection at the sentence and fragment levels

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Alhindi, Tariq Pfeiffer, Jonas Muresan, Smaranda Department of Computer Science Columbia University Data Science Institute Columbia University Ubiquitous Knowledge Processing Lab Technische Universitat Darmstadt

This paper presents the CUNLP submission for the NLP4IF 2019 shared-task on Fine-Grained Propaganda Detection. Our system finished 5th out of 26 teams on the sentence-level classification task and 5th out of 11 teams on the fragment-level classification task based on our scores on the blind test set. We present our models, a discussion of our ablation studies and experiments, and an analysis of our performance on all eighteen propaganda techniques present in the corpus of the shared task. Copyright © 2019, The Authors. All rights reserved.

关键词： Classification (of information)

Does my rebuttal matter? Insights from a major NLP conference

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Gao, Yang Eger, Steffen Kuznetsov, Ilia Gurevych, Iryna Miyao, Yusuke Ubiquitous Knowledge Processing Lab Department of Computer Science Technische Universität Darmstadt Department of Computer Science Graduate School of Information Science and Technology University of Tokyo

Peer review is a core element of the scientific process, particularly in conference-centered fields such as ML and NLP. However, only few studies have evaluated its properties empirically. Aiming to fill this gap, we present a corpus that contains over 4k reviews and 1.2k author responses from ACL-2018. We quantitatively and qualitatively assess the corpus. This includes a pilot study on paper weaknesses given by reviewers and on quality of author responses. We then focus on the role of the rebuttal phase, and propose a novel task to predict after-rebuttal (i.e., final) scores from initial reviews and author responses. Although author responses do have a marginal (and statistically significant) influence on the final scores, especially for borderline papers, our results suggest that a reviewer's final score is largely determined by her initial score and the distance to the other reviewers' initial scores. In this context, we discuss the conformity bias inherent to peer reviewing, a bias that has largely been overlooked in previous research. We hope our analyses will help better assess the usefulness of the rebuttal phase in NLP conferences. Copyright © 2019, The Authors. All rights reserved.

关键词： Natural language processing systems