Software Framework for Topic Modelling with Large Corpora

By Radim Rehurek, Petr Sojka. 2010

4,952 citations recorded by the source corpus.

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

Inductive Representation Learning on Large Graphs (2017, neutral): “Lastly, we see that the performance of unsupervised GraphSAGE is reasonably competitive with the fully supervised version, indicating that our framework can achieve strong performance without task-speciﬁc ﬁne-tuning.”
Fair Is Better than Sensational: Man Is to Doctor as Woman Is to Doctor (2019, methodology): “For both word2vec (Mikolov et al. 2013a) and gensim (Řehůřek and Sojka 2010) we adapted the code so that the input terms of the analogy query are allowed to be returned.”
Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs (2016, methodology): “ Wiki-128, Wiki-8 consisting of 2 million dense vectors of topic histograms created from sparse TF-IDF vectors of the wiki-sparse dataset (created via GENSIM [53]).”
Continual learning of context-dependent processing in neural networks (2018, background): “The contextual information was the embedding vectors [33] of the corresponding task names, which were projected to control the rotation of the sensory inputs.”
GuessWhat?! Visual Object Discovery through Multi-modal Dialogue (2016, methodology): “We applied Data Topic Models (DTM) [8] with the python framework [34] on our dataset.”
Neural Document Summarization by Jointly Learning to Score and Select Sentences (2018, methodology): “CRSUM Ren et al. (2017) propose an extractive summarization system which considers the contextual information of a sentence.”
Deep Sentence Embedding Using Long Short-Term Memory Networks: Analysis and Application to Information Retrieval (2015, methodology): “ i.e., words used for negative sampling as explained in [2]. We used 30 epochs of training. We ran an experiment with 100 epochs but did not observe much difference in the results. We used gensim [40] to perform experiments. To make sure that a meaningful model is trained, we used the trained doc2”
Women’s Syntactic Resilience and Men’s Grammatical Luck: Gender-Bias in Part-of-Speech Tagging and Dependency Parsing (2019, methodology): “We use the LDA implementation included with the Python Gensim library (Řehůřek and Sojka, 2010) with 10 topics.”
Phrase-level Quality Estimation for Machine Translation (2015, methodology): “• The word vector representations were computed with gensim [25] — Python implementation of word2vec models.”
SEF@UHH at SemEval-2017 Task 1: Unsupervised Knowledge-Free Semantic Textual Similarity via Paragraph Vector (2017, methodology): “The models are trained using the Gensim library (Řehůřek and Sojka, 2010).”
Large-Scale Visual Relationship Understanding (2018, methodology): “For the word vectors, we used the gensim library [28] for both word2vec and node2vec † [12].”
CVBed: Structuring CVs usingWord Embeddings (2017, methodology): “Singh et al. (2010) and Marjit et al.”
Pre-trained Contextual Embedding of Source Code (2019, methodology): “We train both CBOW and Skipgram models using GenSim (Řehůřek & Sojka, 2010).”