Learning semantic representations using convolutional neural networks for web search

By Yelong Shen, Xiaodong He, Jianfeng Gao, Li Deng, Grégoire Mesnil. 2014

726 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

In Representation & Self-Supervised Learning

Citations in the corpus

Few-shot Learning with Retrieval Augmented Language Models (2022, methodology): “These usually follow a dual-encoder architecture (Yih et al., 2011; Huang et al., 2013; Shen et al., 2014), where queries and passages are encoded independently as vectors, and relevance is computed using the inner product or Euclidean distance.”
End-to-End Neural Ad-hoc Ranking with Kernel Pooling (2017, methodology): “For example, DSSM [11] and its convolutional version CDSSM [22] map words to letter-tri-grams, embed query and documents using neural networks built upon the letter-tri-grams, and rank documents using their embedding similarity with the query. interaction based neural models, on the other hand,…”
A Deep Relevance Matching Model for Ad-hoc Retrieval (2016, methodology): “Examples include DSSM [12], C-DSSM [23, 8] and ARC-I [11].”
Unsupervised Dense Information Retrieval with Contrastive Learning (2021, methodology): “This method was later refined by replacing the bag-of-words model by convolutional neural networks (Shen et al., 2014) or recurrent neural network (Palangi et al.”
Convolutional Neural Networks for Sentence Classification (2014, methodology): “…vision, CNN models have subsequently been shown to be effective for NLP and have achieved excellent results in semantic parsing (Yih et al., 2014), search query retrieval (Shen et al., 2014), sentence modeling (Kalch-brenner et al., 2014), and other traditional NLP tasks (Collobert et al., 2011).”
Convolutional Neural Network Architectures for Matching Natural Language Sentences (2014, methodology): “When dealing with language objects, most methods still focus on seeking vectorial representations in a common latent space, and calculating the matching score with inner product[18, 25].”
Deep Learning: Methods and Applications (2014, background): “Most recently, the DSSM described above has been extended to its convolutional version, or C-DSSM [328].”
Natural Language Processing for EHR-Based Computational Phenotyping (2018, background): “tion [146], semantic analysis [147], [148], information retrieval [149], [150], entity recognition [151], [152], relation extraction [153], [154], [155], [156], and event detection [157], [158].”
Semantic Parsing for Single-Relation Question Answering (2014, methodology): “We adapt the work of (Huang et al., 2013; Shen et al., 2014b) for measuring the semantic distance between a question and relational triples in the KB as the core component of our semantic parsing approach.”
Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base (2015, methodology): “In this work, we adapt a convolutional neural network (CNN) framework (Shen et al., 2014b; Shen et al., 2014a; Gao et al., 2014) to this matching problem.”
Embedding Entities and Relations for Learning and Inference in Knowledge Bases (2014, methodology): “This general framework for relationship modeling also applies to the recent deep-structured semantic model (Huang et al., 2013; Shen et al., 2014a;b; Gao et al., 2014; Yih et al., 2014), which learns the relevance or a single relation between a pair of word sequences.”
Learning to Match using Local and Distributed Representations of Text for Web Search (2016, methodology): “Both the deep structured semantic model (DSSM) [16] and its convolutional variant CDSSM [38] consider only the document title for matching with the query.”
A Survey on Dialogue Systems: Recent Advances and New Frontiers (2017, methodology): “The CNN-based classification framework also resembled [22] and [64].”
Neural Ranking Models with Weak Supervision (2017, methodology): “lnetworkwithawordhashingphaseasthe•rstlayertopredict the click probability given a query string and a document title. „e DSSM model was further improved by incorporating convolutional neural networks [35]. On the other hand, the early combination models are designed based on the interactions between”
FlexFlow: A Flexible Dataflow Accelerator Architecture for Convolutional Neural Networks (2017, background): “Recent years, more and more applications based on CNN models are spotlighted, such as handwriting recognition [18], face detection [9], [12], video surveillance [27], nature language analysis [10], [11], [24], and intelligent transportation [14], [28], [30].”
A Latent Semantic Model with Convolutional-Pooling Structure for Information Retrieval (2014, background): “Extended from our previous work [20] [33], the CLSM and its variations have also been demonstrated giving superior performance on a range of natural language processing tasks beyond information retrieval, including machine translation [13], semantic parsing and question answering [40], entity search”
From Neural Re-Ranking to Neural Ranking: Learning a Sparse Representation for Inverted Indexing (2018, neutral): “This model is similar to CDSSM [43] andNRM-F [58], except in the use ofword embedding instead of trigram hashing.”