Questions tagged [doc2vec]

Doc2vec (aka paragraph2vec, aka sentence embeddings) modifies the word2vec algorithm to unsupervised learning of continuous representations for larger blocks of text, such as sentences, paragraphs or entire documents.

Filter by
Sorted by
Tagged with
0
votes
0answers
11 views

Doc2Vec model training using arbitrary document index or classification category

I'm using gensim's doc2vec to classify news articles into 3 categories(positive, negative, and neutral). I saw a few examples on the web, but I don't quite understand how the document tagging should ...
1
vote
1answer
48 views

Generating Sentence Vectors from Word2Vec

I know that I can use doc2Wec and other resources to get sentence vectors. But I am very curious to generate sentence vectors using Word2Vec. I read lot of materials and found that Averaging the ...
0
votes
0answers
16 views

Can I use LDA with 1 topic? I clustered my documents using doc2vec then DBSCAN. How can I visualize the topic of each cluster?

I did a doc2vec model then clustered the results using DBSCAN. Now that I have satisfactory results, how can I take these clusters into topics? Should i run LDA on each and make it give out 1 topic? ...
0
votes
0answers
10 views

Doc2Vec score keep getting worse

I'm using Doc2Vec on kaggle with XGB and MLPClassifier but i noticed that for five times in a row the roc scorse got worse without me changing the code (from 90 to 87). I set a fixed random state for ...
4
votes
0answers
162 views

Understanding Object2Vec

AWS released an interesting feature as part of the SageMaker service called Object2Vec that lets you make an embedding for search out of pretty much anything: documents, users, products, ...
0
votes
0answers
30 views

What to make of high R-squared and non-significant p-value of a linear model?

I am using doc2vec to produce $\mathbb{R}^{50}$ vector representations of short bits of text. I am then using those vectors in a linear model to predict a continuous outcome variable. The R^2 is .25 ...
0
votes
1answer
128 views

High Precision and low recall score for TF-IDF when using KNN algorithm

I have twitter data which is labelled with the sentiment(Postive, Negative, Neutral) and I have evaluated the performance of Tf-Idf and Doc2Vec feature extractor using the KNN algorithm and logistic ...
2
votes
1answer
371 views

Pre-processing: lemmatizing and stemming make a better doc2vec?

I have a project which I will turn documents of a corpus into doc2vec. I was reading that when people convert a document to bag of words they try to improve the bag of words by removing stopwords, ...
0
votes
1answer
2k views

how to improve doc2vec model

I would like to do some sentence embedding on around 500 sentences. The purpose is to find for new sentences, the most similar ones within the 500 sentences. Unfortunately, for now its definitely not ...
0
votes
1answer
176 views

Different accuracy scores for the vectors generated by Doc2Vec model trained on same hyper parameters

I am using doc2vec to generate vectors for sentences in training and testing datasets. The generated vectors are used to classify sentences using ensemble classifiers. The classifier is showing two ...
1
vote
1answer
288 views

How should I formalize Doc2Vec Matrix Dimension?

Below, I have a simple diagram explaining the matrix dimension of word2vec. My goal is to expand this graph to incorporate document vectors for doc2vec. However, I'm having trouble understanding the ...
2
votes
1answer
2k views

How to train sentence/paragraph/document embeddings?

I'm well aware of word embeddings (word2vec or Glove) and I know of four papers treating the subject of more general embeddings : Distributed Representations of Sentences and Documents - Quoc V. Le,...
5
votes
1answer
392 views

Why have a tanh layer, max pooling layer and then another tanh layer

I have been reading a Facebook paper, read here, and am confused about certain features of the architecture. I do not understand why they have a tanh layer, max-pooling layer, and then another tanh ...
0
votes
0answers
1k views

Clustering using doc2vec

is it okay to cluster documents by learned document vectors?. I think similar documents should have similar vectors. from this fact it is okay to cluster documents using for instance k-means. However, ...
0
votes
1answer
757 views

Can any one give explanation on LSA and what is different from NMF?

LSA is better way for extracted new concepts from large text documents collections .. in the following example : i have spend lot of time in Google to get explanation about the following My ...
4
votes
2answers
3k views

Doc2Vec for large documents

I have about 7000000 patents that I would like to do find the document similarity of. Obviously with a sample set that big it will take a long time to run. I am just taking a small sample of about ...