paper-with-me

Papers

Improving a tf-idf weighted document vector embedding

2019-02-26 · Craig W. Schmidt

We examine a number of methods to compute a dense vector embedding for a document in a corpus, given a set of word vectors such as those from word2vec or GloVe. We describe two methods that can improve upon a simple weighted sum, that are optimal in the sense that they maximizes a particular weighted cosine similarity measure. We consider several weighting functions, including inverse document frequency (idf), smooth inverse frequency (SIF), and the sub-sampling function used in word2vec. We find that idf works best for our applications. We also use common component removal proposed by Arora et al. as a post-process and find it is helpful in most cases. We compare these embeddings variations to the doc2vec embedding on a new evaluation task using TripAdvisor reviews, and also on the CQADupStack benchmark from the literature.

📄 PDF Abstract BibTeX arXiv:1902.09875

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

GloVe GloVe Embeddings are a type of word embedding that encode the co-occurrence probability ratio between two words as vector differences. GloVe uses a weighted least squares…

Similar Papers 제목 키워드 기반

Sentiment Classification Using Document Embeddings Trained with Cosine Similarity

2019-07-01 · ACL 2019 7 · Tan Thongtan, Tanasanee Phienthrakul

In document-level sentiment classification, each document must be mapped to a fixed length vector. Document embedding models map each document to a dense, low-dimensional vector in continuous vector space. This paper pro…

ClassificationDocument EmbeddingGeneral ClassificationSentiment Analysis+1

JOINTLY LEARNING TOPIC SPECIFIC WORD AND DOCUMENT EMBEDDING

2021-09-29 · Farid Uddin, Zuping Zhang

Document embedding generally ignores underlying topics, which fails to capture polysemous terms that can mislead to improper thematic representation. Moreover, embedding a new document during the test process needs a com…

Document ClassificationDocument EmbeddingWord Embeddings

P-SIF: Document Embeddings Using Partition Averaging

2020-05-18 · Vivek Gupta, Ankit Saw, Pegah Nokhiz, Praneeth Netrapalli 외

Simple weighted averaging of word vectors often yields effective representations for sentences which outperform sophisticated seq2seq neural models in many tasks. While it is desirable to use the same method to represent…

Improving Document Classification with Multi-Sense Embeddings

2019-11-18 · Vivek Gupta, Ankit Saw, Pegah Nokhiz, Harshit Gupta 외

Efficient representation of text documents is an important building block in many NLP tasks. Research on long text categorization has shown that simple weighted averaging of word vectors for sentence representation often…

ClassificationClusteringDocument ClassificationGeneral Classification+3

Unsupervised Document Representation using Partition Word-Vectors Averaging

2018-09-27 · Vivek Gupta, Ankit Kumar Saw, Partha Pratim Talukdar, Praneeth Netrapalli

Learning effective document-level representation is essential in many important NLP tasks such as document classification, summarization, etc. Recent research has shown that simple weighted averaging of word vectors is a…

Document ClassificationSentence