首页/论文/1908.07846

arXiv 1908.078462019-08cs.CLcs.AIcs.CVcs.LG

Representing text as abstract images enables image classifiers to also simultaneously classify text

Swinburne University of Technology（斯威本科技大学）

Stephen M. Petrie, T'Mir D. Julius

备注：: Minor changes in order to submit paper to a different conference (e.g. made minor changes to writing in several places and added extra data to Table 3 in order to make it clearer)

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

We introduce a novel method for converting text data into abstract image representations, which allows image-based processing techniques (e.g. image classification networks) to be applied to text-based comparison problems. We apply the technique to entity disambiguation of inventor names in US patents. The method involves converting text from each pairwise comparison between two inventor name records into a 2D RGB (stacked) image representation. We then train an image classification neural network to discriminate between such pairwise comparison images, and use the trained network to label each pair of records as either matched (same inventor) or non-matched (different inventors), obtaining highly accurate results. Our new text-to-image representation method could also be used more broadly for other NLP comparison problems, such as disambiguation of academic publications, or for problems that require simultaneous classification of both text and image datasets.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Neural Networks for Joint Sentence Classification in Medical Paper Abstracts

MIT（麻省理工学院）

Existing models based on artificial neural networks (ANNs) for sentence classification often do not incorporate the context in which sentences appear, and classify sentences individually. However, traditional sentence classification approaches have been shown to greatly benefit from jointly classifying subsequent sentences, such as with conditional random fields. In this work, we present an ANN architecture that combines the effectiveness of typical ANN models to classify sentences in isolation, with the strength of structured prediction. Our model achieves state-of-the-art results on two diff…

2016-12-15cs.AIcs.CLcs.NE

Automatic evaluation of scientific abstracts through natural language processing

Universidade Federal de Alagoas（阿拉戈斯联邦大学）

This work presents a framework to classify and evaluate distinct research abstract texts which are focused on the description of processes and their applications. In this context, this paper proposes natural language processing algorithms to classify, segment and evaluate the results of scientific work. Initially, the proposed framework categorize the abstract texts into according to the problems intended to be solved by employing a text classification approach. Then, the abstract text is segmented into problem description, methodology and results. Finally, the methodology of the abstract is r…

2021-11-14cs.CLcs.LG

Hierarchical Neural Networks for Sequential Sentence Classification in Medical Scientific Abstracts

MIT（麻省理工学院）

Prevalent models based on artificial neural network (ANN) for sentence classification often classify sentences in isolation without considering the context in which sentences appear. This hampers the traditional sentence classification approaches to the problem of sequential sentence classification, where structured prediction is needed for better overall classification performance. In this work, we present a hierarchical sequential labeling network to make use of the contextual information within surrounding sentences to help classify the current sentence. Our model outperforms the state-of-t…

2018-08-19cs.CL

Representing Numbers in NLP: a Survey and a Vision

University of Southern California（南加州大学）；Information Sciences Institute（信息科学研究所）

NLP systems rarely give special consideration to numbers found in text. This starkly contrasts with the consensus in neuroscience that, in the brain, numbers are represented differently from words. We arrange recent NLP work on numeracy into a comprehensive taxonomy of tasks and methods. We break down the subjective notion of numeracy into 7 subtasks, arranged along two dimensions: granularity (exact vs approximate) and units (abstract vs grounded). We analyze the myriad representational choices made by 18 previously published number encoders and decoders. We synthesize best practices for repr…

2021-03-24cs.AIcs.CLcs.LG

PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstracts

Adobe Research（Adobe 研究院）；MIT（麻省理工学院）

We present PubMed 200k RCT, a new dataset based on PubMed for sequential sentence classification. The dataset consists of approximately 200,000 abstracts of randomized controlled trials, totaling 2.3 million sentences. Each sentence of each abstract is labeled with their role in the abstract using one of the following classes: background, objective, method, result, or conclusion. The purpose of releasing this dataset is twofold. First, the majority of datasets for sequential short-text classification (i.e., classification of short texts that appear in sequences) are small: we hope that releasi…

2017-10-17cs.AIcs.CLstat.ML

Abstractive Text Classification Using Sequence-to-convolution Neural Networks

Sogang University（西江大学）

We propose a new deep neural network model and its training scheme for text classification. Our model Sequence-to-convolution Neural Networks(Seq2CNN) consists of two blocks: Sequential Block that summarizes input texts and Convolution Block that receives summary of input and classifies it to a label. Seq2CNN is trained end-to-end to classify various-length texts without preprocessing inputs into fixed length. We also present Gradual Weight Shift(GWS) method that stabilizes training. GWS is applied to our model's loss function. We compared our model with word-based TextCNN trained with differe…

2020-06-02cs.CL

更多相关论文收起更多论文

Don't Classify, Translate: Multi-Level E-Commerce Product Categorization Via Machine Translation

School of Computing（计算学院）；Rakuten Institute of Technology（乐天技术研究所）；National University of Singapore（新加坡国立大学）

E-commerce platforms categorize their products into a multi-level taxonomy tree with thousands of leaf categories. Conventional methods for product categorization are typically based on machine learning classification algorithms. These algorithms take product information as input (e.g., titles and descriptions) to classify a product into a leaf category. In this paper, we propose a new paradigm based on machine translation. In our approach, we translate a product's natural language description into a sequence of tokens representing a root-to-leaf path in a product taxonomy. In our experiments …

2018-12-14cs.CLcs.LG

揭示具体与抽象概念的视觉属性之谜：变异性、最近邻与挑战性类别

Unveiling the Mystery of Visual Attributes of Concrete and Abstract Concepts: Variability, Nearest Neighbors, and Challenging Categories

University of Stuttgart（斯图加特大学）；LMU Munich（慕尼黑大学）

本研究以具体性为例，利用Bing和YFCC数据集约1000个概念的图像，分析了抽象与具体概念的视觉表征变异性，发现颜色纹理等基本特征在分类上优于ViT，但ViT在最近邻分析中表现更好。

2024-10-15cs.CLcs.CV

Separating Argument Structure from Logical Structure in AMR

University of Groningen（格罗宁根大学）

The AMR (Abstract Meaning Representation) formalism for representing meaning of natural language sentences was not designed to deal with scope and quantifiers. By extending AMR with indices for contexts and formulating constraints on these contexts, a formalism is derived that makes correct prediction for inferences involving negation and bound variables. The attractive core predicate-argument structure of AMR is preserved. The resulting framework is similar to that of Discourse Representation Theory.

2020-10-27cs.CL

Classifying Patents Based on their Semantic Content

London School of Economics（伦敦经济政治学院）；Keio University（庆应义塾大学）；Université Paris VII（巴黎第七大学）；IFSTTAR（法国国家交通、规划与网络科技研究院）；Ecole Nationale des Ponts et Chaussées（法国国立路桥学院）

In this paper, we extend some usual techniques of classification resulting from a large-scale data-mining and network approach. This new technology, which in particular is designed to be suitable to big data, is used to construct an open consolidated database from raw data on 4 million patents taken from the US patent office from 1976 onward. To build the pattern network, not only do we look at each patent title, but we also examine their full abstract and extract the relevant keywords accordingly. We refer to this classification as semantic approach in contrast with the more common technologi…

2016-12-27cs.CLphysics.soc-ph