Text Matching as Image Recognition

  title={Text Matching as Image Recognition},
  author={Liang Pang and Yanyan Lan and J. Guo and Jun Xu and Shengxian Wan and Xueqi Cheng},
Matching two texts is a fundamental problem in many natural language processing tasks. [] Key Method Firstly, a matching matrix whose entries represent the similarities between words is constructed and viewed as an image. Then a convolutional neural network is utilized to capture rich matching patterns in a layer-by-layer way. We show that by resembling the compositional hierarchies of patterns in image recognition, our model can successfully identify salient signals such as n-gram and n-term matchings…

Figures and Tables from this paper

Text matching based on reconstructed color interaction image

Reconstructed Color Interaction Image (RCII) is proposed to convert text matching to color image recognition, where two texts are reconstructed and similarity operations are adopted to generate Color Inter interaction Image (CII).

Two-stream Hierarchical Similarity Reasoning for Image-text Matching

A hierarchical similarity reasoning module is proposed to automatically extract context information, which is then co-exploited with local interaction information for efficient reasoning and the superiority of the proposed approach as compared to existing state-of-the-art methods is shown.

Cross-Level Matching Model for Information Retrieval

A Cross-Level Matching Model which enhances the basic matching signals by allowing terms to match hidden representation states within a sentence by aggregating the learned matching patterns of different matching channels and outputs a global matching score.

Toward the Understanding of Deep Text Matching Models for Information Retrieval

Experimental results on LETOR 4.0 and MS Marco show that all the investigated deep text matching methods, both representation and interaction based methods, satisfy the above constraints with high probabilities in statistics, and extend these constraints to the semantic settings, which are shown to be better satisfied for all theDeep text matching models.

A Survey of State-of-the-Art Short Text Matching Algorithms

This paper will review several state-of-the-art neural network based text matching algorithms in recent years and analyze the applicable scenes of each algorithm based on the effectiveness and time complexity to help beginners to choose appropriate models for their short text matching applications.

Matching Long Text Documents via Graph Convolutional Networks

Extensive evaluation of the proposed approach based on two labeled news article datasets created at Tencent for its intelligent news products show that the proposed graph approach to long document matching significantly outperforms a wide range of state-of-the-art methods.

Match-Prompt: Improving Multi-task Generalization Ability for Neural Text Matching via Prompt Learning

Experimental results on eighteen public datasets show that Match-Prompt can improve multi- Task generalization capability of PLMs in text matching and yield better in-domain multi-task, out-of-domainmulti-task and new task adaptation performance than multi- task and task-specific models trained by previous fine-tuning paradigm.

Multiresolution Graph Attention Networks for Relevance Matching

Experimental results on two datasets demonstrate that the graph approach outperforms other state-of-the-art deep matching models in relevance matching, which is critical to problems like query-document matching in information retrieval and web searching.

Knowledge Enhanced Hybrid Neural Network for Text Matching

Evaluation results from extensive experiments on public data sets of question answering and conversation show that KEHNN can significantly outperform state-of-the-art matching models and particularly improve matching accuracy on pairs with long text.



A Deep Architecture for Matching Short Texts

This paper proposes a new deep architecture to more effectively model the complicated matching relations between two objects from heterogeneous domains and applies this model to matching tasks in natural language, e.g., finding sensible responses for a tweet, or relevant answers to a given question.

Convolutional Neural Network Architectures for Matching Natural Language Sentences

Convolutional neural network models for matching two sentences are proposed, by adapting the convolutional strategy in vision and speech and nicely represent the hierarchical structures of sentences with their layer-by-layer composition and pooling.

A Latent Semantic Model with Convolutional-Pooling Structure for Information Retrieval

A new latent semantic model that incorporates a convolutional-pooling structure over word sequences to learn low-dimensional, semantic vector representations for search queries and Web documents is proposed.

Gradient-based learning applied to document recognition

This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task, and Convolutional neural networks are shown to outperform all other techniques.

Best practices for convolutional neural networks applied to visual document analysis

A set of concrete bestpractices that document analysis researchers can use to get good results with neural networks, including a simple "do-it-yourself" implementation of convolution with a flexible architecture suitable for many visual document problems.

A Convolutional Neural Network for Modelling Sentences

A convolutional architecture dubbed the Dynamic Convolutional Neural Network (DCNN) is described that is adopted for the semantic modelling of sentences and induces a feature graph over the sentence that is capable of explicitly capturing short and long-range relations.

Efficient Estimation of Word Representations in Vector Space

Two novel model architectures for computing continuous vector representations of words from very large data sets are proposed and it is shown that these vectors provide state-of-the-art performance on the authors' test set for measuring syntactic and semantic word similarities.

Modeling Interestingness with Deep Neural Networks

The results on large-scale, real-world datasets show that the semantics of documents are important for modeling interestingness and that the DSSM leads to significant quality improvement on both tasks, outperforming not only the classic document models that do not use semantics but also state-of-the-art topic models.

Learning deep structured semantic models for web search using clickthrough data

A series of new latent semantic models with a deep structure that project queries and documents into a common low-dimensional space where the relevance of a document given a query is readily computed as the distance between them are developed.

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%.