paper-with-me

홈 › Papers

The Document Vectors Using Cosine Similarity Revisited

2022-05-26 · insights (ACL) 2022 5 · Zhang Bingyu, Nikolay Arefyev

The current state-of-the-art test accuracy (97.42\%) on the IMDB movie reviews dataset was reported by \citet{thongtan-phienthrakul-2019-sentiment} and achieved by the logistic regression classifier trained on the Document Vectors using Cosine Similarity (DV-ngrams-cosine) proposed in their paper and the Bag-of-N-grams (BON) vectors scaled by Naive Bayesian weights. While large pre-trained Transformer-based models have shown SOTA results across many datasets and tasks, the aforementioned model has not been surpassed by them, despite being much simpler and pre-trained on the IMDB dataset only. In this paper, we describe an error in the evaluation procedure of this model, which was found when we were trying to analyze its excellent performance on the IMDB dataset. We further show that the previously reported test accuracy of 97.42\% is invalid and should be corrected to 93.68\%. We also analyze the model performance with different amounts of training data (subsets of the IMDB dataset) and compare it to the Transformer-based RoBERTa model. The results show that while RoBERTa has a clear advantage for larger training sets, the DV-ngrams-cosine performs better than RoBERTa when the labelled training set is very small (10 or 20 documents). Finally, we introduce a sub-sampling scheme based on Naive Bayesian weights for the training process of the DV-ngrams-cosine, which leads to faster training and better quality.

📄 PDF Abstract BibTeX arXiv:2205.13357

Code (1)

bgzh/dv_cosine_revisited 공식 구현 pytorch

Tasks

Sentiment Analysis

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Weight Decay 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Adam 설명 없음
WordPiece 설명 없음

Similar Papers 제목 키워드 기반

Text Similarity Estimation Based on Word Embeddings and Matrix Norms for Targeted Marketing

2019-06-01 · NAACL 2019 6 · Tim vor der Br{\"u}ck, Marc Pouly

The prevalent way to estimate the similarity of two documents based on word embeddings is to apply the cosine similarity measure to the two centroids obtained from the embedding vectors associated with the words in each …

Marketingtext similarityWord Embeddings

COS-Mix: Cosine Similarity and Distance Fusion for Improved Information Retrieval

2024-06-02 · Kush Juvekar, Anupam Purwar

This study proposes a novel hybrid retrieval strategy for Retrieval-Augmented Generation (RAG) that integrates cosine similarity and cosine distance measures to improve retrieval performance, particularly for sparse data…

Information RetrievalRAGRetrievalRetrieval-augmented Generation

Semantic Document Clustering on Named Entity Features

2018-07-20 · Cao Tru H., Ngo Vuong M., Hong Dung T., Quan Tho T.

Keyword-based information processing has limitations due to simple treatment of words. In this paper, we introduce named entities as objectives into document clustering, which are the key elements defining document seman…

Clustering

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

Textual Spatial Cosine Similarity

2015-05-15 · Crocetti Giancarlo

When dealing with document similarity many methods exist today, like cosine similarity. More complex methods are also available based on the semantic analysis of textual information, which are computationally expensive a…