paper-with-me

Papers

Document Network Projection in Pretrained Word Embedding Space

2020-01-16 · Antoine Gourru, Adrien Guille, Julien Velcin, Julien Jacques

We present Regularized Linear Embedding (RLE), a novel method that projects a collection of linked documents (e.g. citation network) into a pretrained word embedding space. In addition to the textual content, we leverage a matrix of pairwise similarities providing complementary information (e.g., the network proximity of two documents in a citation graph). We first build a simple word vector average for each document, and we use the similarities to alter this average representation. The document representations can help to solve many information retrieval tasks, such as recommendation, classification and clustering. We demonstrate that our approach outperforms or matches existing document network embedding methods on node classification and link prediction tasks. Furthermore, we show that it helps identifying relevant keywords to describe document classes.

📄 PDF Abstract BibTeX arXiv:2001.05727

Code (0)

등록된 구현이 없습니다.

Tasks

ClusteringGeneral ClassificationInformation RetrievalLink PredictionNetwork EmbeddingNode ClassificationRetrieval

Similar Papers 제목 키워드 기반

Multi-source Neural Topic Modeling in Multi-view Embedding Spaces

2021-04-17 · NAACL 2021 4 · Pankaj Gupta, Yatin Chaudhary, Hinrich Schütze

Though word embeddings and topics are complementary representations, several past works have only used pretrained word embeddings in (neural) topic modeling to address data sparsity in short-text or small collection of d…

Information RetrievalRetrievalWord Embeddings

A Dual Embedding Space Model for Document Ranking

2016-02-02 · Bhaskar Mitra, Eric Nalisnick, Nick Craswell, Rich Caruana

A fundamental goal of search engines is to identify, given a query, documents that have relevant text. This is intrinsically difficult because the query and the document may use different vocabulary, or the document may …

Document RankingmodelWord Embeddings

Hybrid Improved Document-level Embedding (HIDE)

2020-06-01 · Satanik Mitra, Mamata Jenamani

In recent times, word embeddings are taking a significant role in sentiment analysis. As the generation of word embeddings needs huge corpora, many applications use pretrained embeddings. In spite of the success, word em…

Sentiment AnalysisWord Embeddings

Unsupervised and Efficient Vocabulary Expansion for Recurrent Neural Network Language Models in ASR

2018-06-27 · Yerbolat Khassanov, Eng Siong Chng

In automatic speech recognition (ASR) systems, recurrent neural network language models (RNNLM) are used to rescore a word lattice or N-best hypotheses list. Due to the expensive training, the RNNLM's vocabulary set acco…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Multi-source Multi-view Transfer Learning in Neural Topic Modeling with Pretrained Topic and Word Embeddings

2019-09-25 · Pankaj Gupta, Yatin Chaudhary, Hinrich Schütze

Though word embeddings and topics are complementary representations, several past works have only used pretrained word embeddings in (neural) topic modeling to address data sparsity problem in short text or small collect…

Information RetrievalRetrievalTransfer LearningWord Embeddings