Differences

This shows you the differences between two versions of the page.

--- nlp:scientific_text_processing [2022/05/11 00:29] – [Resources] jmflanig
+++ nlp:scientific_text_processing [2025/06/01 21:02] (current) – jmflanig
@@ Line 7: / Line 7: @@
   * [[https://www.aclweb.org/anthology/N13-1067.pdf|2013 - Purpose and Polarity of Citation: Towards NLP-based Bibliometrics]]
   * [[http://lrec-conf.org/workshops/lrec2018/W24/pdf/5_W24.pdf|2018 - Goal-Oriented Representation of Scientific Papers]]
+  * **Predicting Co-authors**
-==== Predicting Co-authors ====
+  * **Graph Structure**
+    * [[https://benty-fields.com/static/include/files/Arxiv_Citation_Graph.pdf|Vedak 2022 - ArXiv Citation Graph]]
-==== Citation Processing ====
+  * **Citation Processing**
-  * [[https://www.aclweb.org/anthology/N12-1009.pdf|2012 - Reference Scope Identification in Citing Sentences]]
+    * [[https://www.aclweb.org/anthology/N12-1009.pdf|2012 - Reference Scope Identification in Citing Sentences]]
+  * **Knowledge Base Construction**
-==== Knowledge Base Construction ====
+    * [[https://arxiv.org/pdf/2010.03824.pdf|Hope et al 2021 - Extracting a Knowledge Base of Mechanisms from COVID-19 Papers]]
-  * [[https://arxiv.org/pdf/2010.03824.pdf|Hope et al 2021 - Extracting a Knowledge Base of Mechanisms from COVID-19 Papers]]
+  * **Summarization**
+    * [[https://arxiv.org/pdf/2004.15011.pdf|Cachola et al 2021 - TLDR: Extreme Summarization of Scientific Documents]]
-==== Summarization ====
+  * **Generating Papers**
-  * [[https://arxiv.org/pdf/2004.15011.pdf|Cachola et al 2021 - TLDR: Extreme Summarization of Scientific Documents]]
+    * [[https://arxiv.org/pdf/1905.07870.pdf|Wang et al 2019 - PaperRobot: Incremental Draft Generation of Scientific Ideas]]
+    * [[https://arxiv.org/pdf/2110.10774.pdf|Chen et al 2021 - SciXGen: A Scientific Paper Dataset for Context-Aware Text Generation]]
-==== Generating Papers ====
+  * **Generating Hypotheses**
-  * [[https://arxiv.org/pdf/1905.07870.pdf|Wang et al 2019 - PaperRobot: Incremental Draft Generation of Scientific Ideas]]
+    * [[https://arxiv.org/pdf/2309.02726.pdf|Yang et al 2023 - Large Language Models for Automated Open-domain Scientific Hypotheses Discovery]]
-  * [[https://arxiv.org/pdf/2110.10774.pdf|Chen et al 2021 - SciXGen: A Scientific Paper Dataset for Context-Aware Text Generation]]
 ===== Datasets =====
   * [[https://allenai.org/data/cord-19|CORD-19: Covid-19 Dataset]] [[https://arxiv.org/pdf/2004.10706.pdf|paper]]
   * [[https://amr.isi.edu/download.html|Bio AMR Corpus]]
+===== Tools =====
+  * [[https://arxiv.org/pdf/2310.01206.pdf|Yamaguchi & Morishita 2023 - appjsonify: An Academic Paper PDF-to-JSON Conversion Toolkit]]
+  * See methods section here: [[https://benty-fields.com/static/include/files/Arxiv_Citation_Graph.pdf|Vedak 2022 - ArXiv Citation Graph]]
 ===== Resources =====
@@ Line 34: / Line 37: @@
   * [[https://scholar.google.com/citations?user=vIqWvgwAAAAJ&hl=en|Dragomir Radev]]
   * [[https://scholar.google.com/citations?user=IUZgJogAAAAJ&hl=en|Daniel Weld]]
+===== Related Pages =====
+  * [[Patent Domain NLP]] Some overlap with scientific domain nlp, especially for information extraction for patents