# Which implementation of Parallel LDA is applied in the Topic Extractor node?

**URL:** <https://forum.knime.com/t/which-implementation-of-parallel-lda-is-applied-in-the-topic-extractor-node/37741>\
**Category:** KNIME Extensions\
**Tags:** text-processing\
**Created:** [December 1, 2021, 4:37pm UTC](https://forum.knime.com/t/which-implementation-of-parallel-lda-is-applied-in-the-topic-extractor-node/37741 "2021-12-01T16:37:50Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![b0raas](https://forum-cdn.knime.com/letter_avatar_proxy/v4/letter/b/e99b99/32.png) [@b0raas](https://forum.knime.com/u/b0raas)\
**Post date:** [December 1, 2021, 4:37pm UTC](https://forum.knime.com/t/which-implementation-of-parallel-lda-is-applied-in-the-topic-extractor-node/37741/1 "2021-12-01T16:37:50Z")

</div>

For the node [Topic Extractor (Parallel LDA)](https://hub.knime.com/knime/extensions/org.knime.features.ext.textprocessing/latest/org.knime.ext.textprocessing.nodes.mining.topic.ParallelTopicExtractorNodeFactory) I am wondering which of the two papers is now implemented?

[Newman09](https://www.jmlr.org/papers/volume10/newman09a/newman09a.pdf) or [Yao09](https://dl-acm-org.uaccess.univie.ac.at/doi/abs/10.1145/1557019.1557121)? Both papers are mentioned in the description of the node and both use some Bayesian classifier to learn the topics in contrast to traditional LDA.

---

<div class="post-metadata">

**Author:** ![julian.bunzel](https://forum-cdn.knime.com/letter_avatar_proxy/v4/letter/j/35a633/32.png) [@julian.bunzel](https://forum.knime.com/u/julian.bunzel)\
**Post date:** [December 7, 2021, 10:17am UTC](https://forum.knime.com/t/which-implementation-of-parallel-lda-is-applied-in-the-topic-extractor-node/37741/2 "2021-12-07T10:17:58Z")

</div>

Hi @b0raas,

we are using the [MALLET library](https://mimno.github.io/Mallet/) for the Parallel LDA.  
[The code](https://github.com/mimno/Mallet/blob/master/src/cc/mallet/topics/ParallelTopicModel.java) says that the implementation is following Newman but a particular data structure developed by Yao is being used as well.

Best regards,  
Julian

---

<div class="post-metadata">

**Author:** ![b0raas](https://forum-cdn.knime.com/letter_avatar_proxy/v4/letter/b/e99b99/32.png) [@b0raas](https://forum.knime.com/u/b0raas)\
**Post date:** [December 7, 2021, 2:57pm UTC](https://forum.knime.com/t/which-implementation-of-parallel-lda-is-applied-in-the-topic-extractor-node/37741/3 "2021-12-07T14:57:27Z")

</div>

Thank you very much for the clarification.  
It would be great if you could update the description, because the description in MALLET does not say anything about the paper.

---

<div class="post-metadata">

**Author:** ![system](https://forum-cdn.knime.com/uploads/default/original/1X/ab3ccf34482a0329361734a18199390177204f15.png) [@system](https://forum.knime.com/u/system)\
**Post date:** [June 2, 2023, 9:39pm UTC](https://forum.knime.com/t/which-implementation-of-parallel-lda-is-applied-in-the-topic-extractor-node/37741/4 "2023-06-02T21:39:21Z")

</div>

This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.