Comparative reconstruction updates

_bibliography/drmpubs.bib

@@ -1,21 +1,21 @@
-@misc{sohn2024zeroshotcrosslingualnerusing,
-      title={Zero-Shot Cross-Lingual NER Using Phonemic Representations for Low-Resource Languages}, 
-      author={Jimin Sohn and Haeji Jung and Alex Cheng and Jooeon Kang and Yilin Du and David R. Mortensen},
+@misc{naik2024largelanguagemodelscode,
+      title={Can Large Language Models Code Like a Linguist?: A Case Study in Low Resource Sound Law Induction},
+      author={Naik, Atharva and Zhang, Kexun and Robinson, Nathaniel and Mysore, Aravind and Marr, Clayton and Sng, Hong and Byrnes, Rebecca and Cai, Anna and Chang, Kalvin and Mortensen, David},
       year={2024},
-      eprint={2406.16030},
+      eprint={2406.12725},
       archivePrefix={arXiv},
       primaryClass={cs.CL},
-      url={https://arxiv.org/abs/2406.16030}, 
+      url={https://arxiv.org/abs/2406.12725},
 }
 
-@misc{naik2024largelanguagemodelscode,
-      title={Can Large Language Models Code Like a Linguist?: A Case Study in Low Resource Sound Law Induction}, 
-      author={Atharva Naik and Kexun Zhang and Nathaniel Robinson and Aravind Mysore and Clayton Marr and Hong Sng Rebecca Byrnes and Anna Cai and Kalvin Chang and David Mortensen},
+@misc{sohn2024zeroshotcrosslingualnerusing,
+      title={Zero-Shot Cross-Lingual NER Using Phonemic Representations for Low-Resource Languages}, 
+      author={Jimin Sohn and Haeji Jung and Alex Cheng and Jooeon Kang and Yilin Du and David R. Mortensen},
       year={2024},
-      eprint={2406.12725},
+      eprint={2406.16030},
       archivePrefix={arXiv},
       primaryClass={cs.CL},
-      url={https://arxiv.org/abs/2406.12725}, 
+      url={https://arxiv.org/abs/2406.16030},
 }
 
 @misc{lu2024semisupervisedneuralprotolanguagereconstruction,

_projects/1_automating.md

@@ -19,6 +19,7 @@ In this research, we build upon past research in this area.
 
 - In {% cite chang2022wikihan %}, we propose a new resource for Chinese historical phonology (including Middle Chinese and modern Chinese varieties). This data is foundational to our later papers.
 - In {% cite kim2023transformed %}, we show that Transformer-based models can perform better than RNN (e.g., GRU) based models for supervised protoform reconstruction.
+- In {% cite chang2023automating %}, we semi-automate intermediate sound change prediction (AISCP) for Tukanoan phylogenetic inference (the process of determining how languages branched off from its relatives). Traditionally, linguists have manually predicted the intermediate stages of sounds that proto-sounds go through, which are then used to group different varieties.
 - In {% cite lu-etal-2024-improved %}, we further improve automatic comparative reconstruction by using reflex prediction to perform reranking on the beam search results from protoform prediction, emulating the methodology of practicing historical linguists.
 - In {% cite cui2024neuralprotolanguagereconstruction %}, we explored VAEs for supervised comparative reconstruction.
 - Finally. in {% cite lu2024semisupervisedneuralprotolanguagereconstruction %}, we showed that it is possible to achieve strong performance on the protoform reconstruction task using only a fraction of the number of labeled data by using the Proto-Daughter-Proto architecture, an end-to-end architecture that favors protoforms that can be derived from cognate sets and from which cognate sets can be derived.