# New paper citing MedCAT

**URL:** <https://discourse.cogstack.org/t/new-paper-citing-medcat/97>\
**Category:** MedCAT\
**Created:** [October 17, 2022, 12:56am UTC](https://discourse.cogstack.org/t/new-paper-citing-medcat/97 "2022-10-17T00:56:34Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![plandes](https://dub1.discourse-cdn.com/flex017/user_avatar/discourse.cogstack.org/plandes/32/26_2.png) [@plandes](https://discourse.cogstack.org/u/plandes)\
**Post date:** [October 17, 2022, 12:56am UTC](https://discourse.cogstack.org/t/new-paper-citing-medcat/97/1 "2022-10-17T00:56:34Z")

</div>

We published a paper that was accepted to COLING, which just ended. If you want to add this to the list of papers that cite MedCAT, [here](https://aclanthology.org/2022.coling-1.326.pdf) the paper. [Here](https://github.com/plandes/mimicsid) is the repo that uses it.

Here’s the citation:

```nohighlight
@inproceedings{landes-etal-2022-new,
    title = "A New Public Corpus for Clinical Section Identification: {M}ed{S}ec{I}d",
    author = "Landes, Paul and
      Patel, Kunal and
      Huang, Sean S. and
      Webb, Adam and
      Di Eugenio, Barbara and
      Caragea, Cornelia",
    booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
    month = oct,
    year = "2022",
    address = "Gyeongju, Republic of Korea",
    publisher = "International Committee on Computational Linguistics",
    url = "https://aclanthology.org/2022.coling-1.326",
    pages = "3709--3721"
}

```

---

<div class="post-metadata">

**Author:** ![Jthteo](https://avatars.discourse-cdn.com/v4/letter/j/898d66/32.png) [@Jthteo](https://discourse.cogstack.org/u/Jthteo)\
**Post date:** [October 18, 2022, 7:36am UTC](https://discourse.cogstack.org/t/new-paper-citing-medcat/97/2 "2022-10-18T07:36:18Z")

</div>

Very interesting use of cui2vec.

---

<div class="post-metadata">

**Author:** ![tomolopolis](https://avatars.discourse-cdn.com/v4/letter/t/6de8d8/32.png) [@tomolopolis](https://discourse.cogstack.org/u/tomolopolis)\
**Post date:** [October 18, 2022, 8:55am UTC](https://discourse.cogstack.org/t/new-paper-citing-medcat/97/3 "2022-10-18T08:55:43Z")

</div>

Thanks @plandes - nice work and congrats for the paper acceptance! Added to the readme and media.md

---

<div class="post-metadata">

**Author:** ![plandes](https://dub1.discourse-cdn.com/flex017/user_avatar/discourse.cogstack.org/plandes/32/26_2.png) [@plandes](https://discourse.cogstack.org/u/plandes)\
**Post date:** [October 19, 2022, 1:32am UTC](https://discourse.cogstack.org/t/new-paper-citing-medcat/97/4 "2022-10-19T01:32:30Z")

</div>

Yes, incidentally we also used cui2vec as concatenated embeddings to the word embeddings (after the publication of the paper, so this wasn’t mentioned). While performance did increase, it didn’t by much so I haven’t performed any ANOVA etc for statistical significance. This might be because while the cui2vec dimensional is high, the vocabulary is somewhat limited compared to other embeddings, especially relative to the size of UMLS.

---

<div class="post-metadata">

**Author:** ![zeljko](https://avatars.discourse-cdn.com/v4/letter/z/7ab992/32.png) [@zeljko](https://discourse.cogstack.org/u/zeljko)\
**Post date:** [October 21, 2022, 4:45pm UTC](https://discourse.cogstack.org/t/new-paper-citing-medcat/97/5 "2022-10-21T16:45:03Z")

</div>

Hi @plandes, paper added to the repo. Really interesting work, thanks for letting us know.