Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Text": models, code, and papers

Generalized minimum dominating set and application in automatic text summarization

Feb 16, 2016
Yi-Zhi Xu, Hai-Jun Zhou

For a graph formed by vertices and weighted edges, a generalized minimum dominating set (MDS) is a vertex set of smallest cardinality such that the summed weight of edges from each outside vertex to vertices in this set is equal to or larger than certain threshold value. This generalized MDS problem reduces to the conventional MDS problem in the limiting case of all the edge weights being equal to the threshold value. We treat the generalized MDS problem in the present paper by a replica-symmetric spin glass theory and derive a set of belief-propagation equations. As a practical application we consider the problem of extracting a set of sentences that best summarize a given input text document. We carry out a preliminary test of the statistical physics-inspired method to this automatic text summarization problem.

* 11 pages, including 4 figures and 2 tables. To be published in Journal of Physics: Conference Series 

  Access Paper or Ask Questions

Automatic Document Sketching: Generating Drafts from Analogous Texts

Jun 14, 2021
Zeqiu Wu, Michel Galley, Chris Brockett, Yizhe Zhang, Bill Dolan

The advent of large pre-trained language models has made it possible to make high-quality predictions on how to add or change a sentence in a document. However, the high branching factor inherent to text generation impedes the ability of even the strongest language models to offer useful editing suggestions at a more global or document level. We introduce a new task, document sketching, which involves generating entire draft documents for the writer to review and revise. These drafts are built from sets of documents that overlap in form - sharing large segments of potentially reusable text - while diverging in content. To support this task, we introduce a Wikipedia-based dataset of analogous documents and investigate the application of weakly supervised methods, including use of a transformer-based mixture of experts, together with reinforcement learning. We report experiments using automated and human evaluation methods and discuss relative merits of these models.

* Findings of ACL 2021 

  Access Paper or Ask Questions

Generating Multiple Diverse Responses for Short-Text Conversation

Nov 29, 2018
Jun Gao, Wei Bi, Xiaojiang Liu, Junhui Li, Shuming Shi

Neural generative models have become popular and achieved promising performance on short-text conversation tasks. They are generally trained to build a 1-to-1 mapping from the input post to its output response. However, a given post is often associated with multiple replies simultaneously in real applications. Previous research on this task mainly focuses on improving the relevance and informativeness of the top one generated response for each post. Very few works study generating multiple accurate and diverse responses for the same post. In this paper, we propose a novel response generation model, which considers a set of responses jointly and generates multiple diverse responses simultaneously. A reinforcement learning algorithm is designed to solve our model. Experiments on two short-text conversation tasks validate that the multiple responses generated by our model obtain higher quality and larger diversity compared with various state-of-the-art generative models.

  Access Paper or Ask Questions

Graph Structured Network for Image-Text Matching

Apr 01, 2020
Chunxiao Liu, Zhendong Mao, Tianzhu Zhang, Hongtao Xie, Bin Wang, Yongdong Zhang

Image-text matching has received growing interest since it bridges vision and language. The key challenge lies in how to learn correspondence between image and text. Existing works learn coarse correspondence based on object co-occurrence statistics, while failing to learn fine-grained phrase correspondence. In this paper, we present a novel Graph Structured Matching Network (GSMN) to learn fine-grained correspondence. The GSMN explicitly models object, relation and attribute as a structured phrase, which not only allows to learn correspondence of object, relation and attribute separately, but also benefits to learn fine-grained correspondence of structured phrase. This is achieved by node-level matching and structure-level matching. The node-level matching associates each node with its relevant nodes from another modality, where the node can be object, relation or attribute. The associated nodes then jointly infer fine-grained correspondence by fusing neighborhood associations at structure-level matching. Comprehensive experiments show that GSMN outperforms state-of-the-art methods on benchmarks, with relative [email protected] improvements of nearly 7% and 2% on Flickr30K and MSCOCO, respectively. Code will be released at:

* Accepted by CVPR2020 

  Access Paper or Ask Questions

NMTScore: A Multilingual Analysis of Translation-based Text Similarity Measures

Apr 28, 2022
Jannis Vamvas, Rico Sennrich

Being able to rank the similarity of short text segments is an interesting bonus feature of neural machine translation. Translation-based similarity measures include direct and pivot translation probability, as well as translation cross-likelihood, which has not been studied so far. We analyze these measures in the common framework of multilingual NMT, releasing the NMTScore library (available at Compared to baselines such as sentence embeddings, translation-based measures prove competitive in paraphrase identification and are more robust against adversarial or multilingual input, especially if proper normalization is applied. When used for reference-based evaluation of data-to-text generation in 2 tasks and 17 languages, translation-based measures show a relatively high correlation to human judgments.

  Access Paper or Ask Questions

Text and Style Conditioned GAN for Generation of Offline Handwriting Lines

Sep 01, 2020
Brian Davis, Chris Tensmeyer, Brian Price, Curtis Wigington, Bryan Morse, Rajiv Jain

This paper presents a GAN for generating images of handwritten lines conditioned on arbitrary text and latent style vectors. Unlike prior work, which produce stroke points or single-word images, this model generates entire lines of offline handwriting. The model produces variable-sized images by using style vectors to determine character widths. A generator network is trained with GAN and autoencoder techniques to learn style, and uses a pre-trained handwriting recognition network to induce legibility. A study using human evaluators demonstrates that the model produces images that appear to be written by a human. After training, the encoder network can extract a style vector from an image, allowing images in a similar style to be generated, but with arbitrary text.

* Includes Supplementary Material. Accepted at BMVC 2020. 32 pages, 30 figures 

  Access Paper or Ask Questions

Text Extraction and Restoration of Old Handwritten Documents

Jan 23, 2020
Mayank Wadhwani, Debapriya Kundu, Deepayan Chakraborty, Bhabatosh Chanda

Image restoration is very crucial computer vision task. This paper describes two novel methods for the restoration of old degraded handwritten documents using deep neural network. In addition to that, a small-scale dataset of 26 heritage letters images is introduced. The ground truth data to train the desired network is generated semi automatically involving a pragmatic combination of color transformation, Gaussian mixture model based segmentation and shape correction by using mathematical morphological operators. In the first approach, a deep neural network has been used for text extraction from the document image and later background reconstruction has been done using Gaussian mixture modeling. But Gaussian mixture modelling requires to set parameters manually, to alleviate this we propose a second approach where the background reconstruction and foreground extraction (which which includes extracting text with its original colour) both has been done using deep neural network. Experiments demonstrate that the proposed systems perform well on handwritten document images with severe degradations, even when trained with small dataset. Hence, the proposed methods are ideally suited for digital heritage preservation repositories. It is worth mentioning that, these methods can be extended easily for printed degraded documents.

  Access Paper or Ask Questions

CancerBERT: a BERT model for Extracting Breast Cancer Phenotypes from Electronic Health Records

Aug 25, 2021
Sicheng Zhou, Liwei Wang, Nan Wang, Hongfang Liu, Rui Zhang

Accurate extraction of breast cancer patients' phenotypes is important for clinical decision support and clinical research. Current models do not take full advantage of cancer domain-specific corpus, whether pre-training Bidirectional Encoder Representations from Transformer model on cancer-specific corpus could improve the performances of extracting breast cancer phenotypes from texts data remains to be explored. The objective of this study is to develop and evaluate the CancerBERT model for extracting breast cancer phenotypes from clinical texts in electronic health records. This data used in the study included 21,291 breast cancer patients diagnosed from 2010 to 2020, patients' clinical notes and pathology reports were collected from the University of Minnesota Clinical Data Repository (UMN). Results: About 3 million clinical notes and pathology reports in electronic health records for 21,291 breast cancer patients were collected to train the CancerBERT model. 200 pathology reports and 50 clinical notes of breast cancer patients that contain 9,685 sentences and 221,356 tokens were manually annotated by two annotators. 20% of the annotated data was used as a test set. Our CancerBERT model achieved the best performance with macro F1 scores equal to 0.876 (95% CI, 0.896-0.902) for exact match and 0.904 (95% CI, 0.896-0.902) for the lenient match. The NER models we developed would facilitate the automated information extraction from clinical texts to further help clinical decision support. Conclusions and Relevance: In this study, we focused on the breast cancer-related concepts extraction from EHR data and obtained a comprehensive annotated dataset that contains 7 types of breast cancer-related concepts. The CancerBERT model with customized vocabulary could significantly improve the performance for extracting breast cancer phenotypes from clinical texts.

  Access Paper or Ask Questions

Iterative Data Programming for Expanding Text Classification Corpora

Feb 04, 2020
Neil Mallinar, Abhishek Shah, Tin Kam Ho, Rajendra Ugrani, Ayush Gupta

Real-world text classification tasks often require many labeled training examples that are expensive to obtain. Recent advancements in machine teaching, specifically the data programming paradigm, facilitate the creation of training data sets quickly via a general framework for building weak models, also known as labeling functions, and denoising them through ensemble learning techniques. We present a fast, simple data programming method for augmenting text data sets by generating neighborhood-based weak models with minimal supervision. Furthermore, our method employs an iterative procedure to identify sparsely distributed examples from large volumes of unlabeled data. The iterative data programming techniques improve newer weak models as more labeled data is confirmed with human-in-loop. We show empirical results on sentence classification tasks, including those from a task of improving intent recognition in conversational agents.

* 6 pages, 2 figures, In Proceedings of the AAAI Conference on Artificial Intelligence 2020 (IAAI Technical Track: Emerging Papers) 

  Access Paper or Ask Questions

Image and Encoded Text Fusion for Multi-Modal Classification

Oct 03, 2018
Ignazio Gallo, Alessandro Calefati, Shah Nawaz, Muhammad Kamran Janjua

Multi-modal approaches employ data from multiple input streams such as textual and visual domains. Deep neural networks have been successfully employed for these approaches. In this paper, we present a novel multi-modal approach that fuses images and text descriptions to improve multi-modal classification performance in real-world scenarios. The proposed approach embeds an encoded text onto an image to obtain an information-enriched image. To learn feature representations of resulting images, standard Convolutional Neural Networks (CNNs) are employed for the classification task. We demonstrate how a CNN based pipeline can be used to learn representations of the novel fusion approach. We compare our approach with individual sources on two large-scale multi-modal classification datasets while obtaining encouraging results. Furthermore, we evaluate our approach against two famous multi-modal strategies namely early fusion and late fusion.

* Accepted to DICTA 2018 

  Access Paper or Ask Questions