Multi-Granularity Neural Sentence Model for Measuring Short Text Similarity

Huang, Jiangping; Yao, Shuxin; Lyu, Chen; Ji, Donghong

doi:10.1007/978-3-319-55753-3_28

Cited by 12 publications

(13 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Models in this category typically enhance the inputs by extending it from words to phrases/n-grams or sentences, apply certain single-granularity architectures over each input form, and aggregate all the granularity for final relevance output. For example, in [94], a CNN and an LSTM are applied to obtain the character-level, word-level, and sentence-level representations of the inputs, and each level representations are then interacted and aggregated by the evaluation function g to produce the final relevance score. Similar ideas can be found in Conv-KNRM [84] and MIX [95].…”

Section: Single-granularitymentioning

confidence: 99%

A Deep Look into neural ranking models for information retrieval

Guo

Fan

Pang

et al. 2020

Information Processing & Management

236

147

View full text Add to dashboard Cite

Ranking models lie at the heart of research on information retrieval (IR). During the past decades, different techniques have been proposed for constructing ranking models, from traditional heuristic methods, probabilistic methods, to modern machine learning methods. Recently, with the advance of deep learning technology, we have witnessed a growing body of work in applying shallow or deep neural networks to the ranking problem in IR, referred to as neural ranking models in this paper. The power of neural ranking models lies in the ability to learn from the raw text inputs for the ranking problem to avoid many limitations of hand-crafted features. Neural networks have sufficient capacity to model complicated tasks, which is needed to handle the complexity of relevance estimation in ranking. Since there have been a large variety of neural ranking models proposed, we believe it is the right time to summarize the current status, learn from existing methodologies, and gain some insights for future development. In contrast to existing reviews, in this survey, we will take a deep look into the neural ranking models from different dimensions to analyze their underlying assumptions, major design principles, and learning strategies. We compare these models through benchmark tasks to obtain a comprehensive empirical understanding of the existing techniques. We will also discuss what is missing in the current literature and what are the promising and desired future directions.

show abstract

Section: Single-granularitymentioning

confidence: 99%

A Deep Look into neural ranking models for information retrieval

Guo

Fan

Pang

et al. 2020

Information Processing & Management

236

147

View full text Add to dashboard Cite

show abstract

“…The hybrid model can capture multiple layers of feature information for short text representation. Huang et al 62 proposed a multiple‐granularity neural sentence model, which uses CNN to extract character‐level and word‐level features and uses LSTM to model sentence‐level semantic representations to obtain fine‐grained features, semantic representation, and important contextual and grammatical features. Zheng et al 26 introduced a hybrid bidirectional recurrent convolutional neural network, which captures contexts and long text information by BiLSTM.…”

Section: Semantic Similarity Measuresmentioning

confidence: 99%

“…In addition, according to the mainstream DL methods, we summarize the DL similarity measures. These DL similarity measures are divided into three categories: general model, 21,22 attention model, 23,24 and hybrid model 25,26 . The main contributions of this article are summarized as follows.…”

Section: Introductionmentioning

confidence: 99%

A survey on the techniques, applications, and performance of short text semantic similarity

Han

Zhang

Yuan

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

Summary Short text similarity plays an important role in natural language processing (NLP). It has been applied in many fields. Due to the lack of sufficient context in the short text, it is difficult to measure the similarity. The use of semantics similarity to calculate textual similarity has attracted the attention of academia and industry and achieved better results. In this survey, we have conducted a comprehensive and systematic analysis of semantic similarity. We first propose three categories of semantic similarity: corpus‐based, knowledge‐based, and deep learning (DL)‐based. We analyze the pros and cons of representative and novel algorithms in each category. Our analysis also includes the applications of these similarity measurement methods in other areas of NLP. We then evaluate state‐of‐the‐art DL methods on four common datasets, which proved that DL‐based can better solve the challenges of the short text similarity, such as sparsity and complexity. Especially, bidirectional encoder representations from transformer model can fully employ scarce information of short texts and semantic information and obtain higher accuracy and F1 value. We finally put forward some future directions.

show abstract

“…Based on the experiments, they concluded that by overlapping word/n gram, word alignment by METEOR, scores of BLEU and Edit Distance, one can find semantic information of Twitter dataset at a low cost. In [20], the authors presented a novel deep learning model for detecting paraphrases and semantics similarity among short texts like tweets. They also studied how different levels (character, word and sentence) of features could be extracted for modeling sentence representation.…”

Section: Short Text Similaritymentioning

confidence: 99%

“…Their measured cross entropy loss was 0.29568. Likewise, a deep learning model presented by [20] for detecting paraphrases and semantics similarity among short texts like tweets. For evaluating their model, they used a twitter dataset, and their results showed that character level features play an important role in finding similarity between tweets.…”

Section: Figurementioning

confidence: 99%

Deep Learning based Semantic Similarity Detection using Text Data

Mansoor¹,

Rehman²,

Shaheen³

et al. 2020

ITC

View full text Add to dashboard Cite

Similarity detection in the text is the main task for a number of Natural Language Processing (NLP) applications. As textual data is comparatively large in quantity and huge in volume than the numeric data, therefore measuring textual similarity is one of the important problems. Most of the similarity detection algorithms are based upon word to word matching, sentence/paragraph matching, and matching of the whole document. In this research, a novel approach is proposed using deep learning models, combining Long Short Term Memory network (LSTM) with Convolutional Neural Network (CNN) for measuring semantics similarity between two questions. The proposed model takes sentence pairs as input to measure the similarity between them. The model is tested on publicly available Quora’s dataset. The model in comparison to the existing techniques gave 87.50 % accuracy which is better than the previous approaches.

show abstract

Multi-Granularity Neural Sentence Model for Measuring Short Text Similarity

Cited by 12 publications

References 20 publications

A Deep Look into neural ranking models for information retrieval

A Deep Look into neural ranking models for information retrieval

A survey on the techniques, applications, and performance of short text semantic similarity

Deep Learning based Semantic Similarity Detection using Text Data

Contact Info

Product

Resources

About