diff --git a/2024.eamt-1.13.pdf b/2024.eamt-1.13.pdf new file mode 100644 index 0000000000000000000000000000000000000000..76b175e65cee866396a062e7751589231b2d4c45 Binary files /dev/null and b/2024.eamt-1.13.pdf differ diff --git a/amu-literature.bib b/amu-literature.bib index 3c4c9fc84c034ce5bf88107f9166e65bd1209a08..b46c4e4ed398e9dd4f1cbdf23260a1e41a1968a9 100644 --- a/amu-literature.bib +++ b/amu-literature.bib @@ -1628,7 +1628,80 @@ title = {A benchmark for learning to translate a new language from one grammar book}, year = {2023}, file = {:tanzer2023benchmark - A Benchmark for Learning to Translate a New Language from One Grammar Book.pdf:PDF:http\://arxiv.org/pdf/2309.16575v2}, - groups = {read-asap}, + groups = {read-asap, low-resource}, +} + +@InProceedings{zhang2024hire, + author = {Zhang, Kexun and Choi, Yee and Song, Zhenqiao and He, Taiqi and Wang, William Yang and Li, Lei}, + booktitle = {Findings of the Association for Computational Linguistics ACL 2024}, + title = {Hire a linguist!: Learning endangered languages in LLMs with in-context linguistic descriptions}, + year = {2024}, + pages = {15654--15669}, + file = {:zhang2024hire - Hire a Linguist!_ Learning Endangered Languages in LLMs with in Context Linguistic Descriptions.pdf:PDF:https\://aclanthology.org/2024.findings-acl.925.pdf}, + groups = {low-resource}, +} + +@InProceedings{mcgill-etal-2024-bootstrapping, + author = {McGill, Euan and Chiruzzo, Luis and Saggion, Horacio}, + booktitle = {Proceedings of the 25th Annual Conference of the European Association for Machine Translation (Volume 1)}, + title = {Bootstrapping Pre-trained Word Embedding Models for Sign Language Gloss Translation}, + year = {2024}, + address = {Sheffield, UK}, + editor = {Scarton, Carolina and Prescott, Charlotte and Bayliss, Chris and Oakley, Chris and Wright, Joanna and Wrigley, Stuart and Song, Xingyi and Gow-Smith, Edward and Bawden, Rachel and S{\'a}nchez-Cartagena, V{\'i}ctor M and Cadwell, Patrick and Lapshinova-Koltunski, Ekaterina and Cabarr{\~a}o, Vera and Chatzitheodorou, Konstantinos and Nurminen, Mary and Kanojia, Diptesh and Moniz, Helena}, + month = jun, + pages = {116--132}, + publisher = {European Association for Machine Translation (EAMT)}, + abstract = {This paper explores a novel method to modify existing pre-trained word embedding models of spoken languages for Sign Language glosses. These newly-generated embeddings are described, visualised, and then used in the encoder and/or decoder of models for the Text2Gloss and Gloss2Text task of machine translation. In two translation settings (one including data augmentation-based pre-training and a baseline), we find that bootstrapped word embeddings for glosses improve translation across four Signed/spoken language pairs. Many improvements are statistically significant, including those where the bootstrapped gloss embedding models are used.Languages included: American Sign Language, Finnish Sign Language, Spanish Sign Language, Sign Language of The Netherlands.}, + file = {:2024.eamt-1.13.pdf:PDF}, + groups = {low-resource}, + url = {https://aclanthology.org/2024.eamt-1.13/}, +} + +@Misc{spencer2024llmshelpcreategrammar, + author = {Piyapath T Spencer and Nanthipat Kongborrirak}, + title = {Can LLMs Help Create Grammar?: Automating Grammar Creation for Endangered Languages with In-Context Learning}, + year = {2024}, + archiveprefix = {arXiv}, + eprint = {2412.10960}, + file = {:spencer2024llmshelpcreategrammar - Can LLMs Help Create Grammar__ Automating Grammar Creation for Endangered Languages with in Context Learning.pdf:PDF:http\://arxiv.org/pdf/2412.10960v1}, + groups = {low-resource}, + primaryclass = {cs.CL}, + url = {https://arxiv.org/abs/2412.10960}, +} + +@Misc{tekgurler2025llmstranslationhistoricallowresourced, + author = {Merve Tekgurler}, + title = {LLMs for Translation: Historical, Low-Resourced Languages and Contemporary AI Models}, + year = {2025}, + archiveprefix = {arXiv}, + eprint = {2503.11898}, + file = {:tekgurler2025llmstranslationhistoricallowresourced - LLMs for Translation_ Historical, Low Resourced Languages and Contemporary AI Models.pdf:PDF:http\://arxiv.org/pdf/2503.11898v1}, + groups = {low-resource}, + primaryclass = {cs.CL}, + url = {https://arxiv.org/abs/2503.11898}, +} + +@Misc{merx2024lowresourcemachinetranslationretrievalaugmented, + author = {Raphaël Merx and Aso Mahmudi and Katrina Langford and Leo Alberto de Araujo and Ekaterina Vylomova}, + title = {Low-Resource Machine Translation through Retrieval-Augmented LLM Prompting: A Study on the Mambai Language}, + year = {2024}, + archiveprefix = {arXiv}, + eprint = {2404.04809}, + file = {:merx2024lowresourcemachinetranslationretrievalaugmented - Low Resource Machine Translation through Retrieval Augmented LLM Prompting_ a Study on the Mambai Language.pdf:PDF:http\://arxiv.org/pdf/2404.04809v1}, + groups = {low-resource}, + primaryclass = {cs.CL}, + url = {https://arxiv.org/abs/2404.04809}, +} + +@Article{opitz2025natural, + author = {Opitz, Juri and Wein, Shira and Schneider, Nathan}, + journal = {Computational Linguistics}, + title = {Natural language processing relies on linguistics}, + year = {2025}, + pages = {1--23}, + file = {:coli_a_00560.pdf:PDF}, + groups = {low-resource}, + publisher = {MIT Press 255 Main Street, 9th Floor, Cambridge, Massachusetts 02142, USA~…}, } @Comment{jabref-meta: databaseType:bibtex;} @@ -1648,4 +1721,5 @@ 1 StaticGroup:misc\;0\;0\;0xb3e6b3ff\;\;\;; 1 StaticGroup:Groupe de lecture\;0\;1\;0x00ffffff\;\;\;; 1 StaticGroup:Tokenization\;0\;1\;0xd74ecbff\;\;\;; +1 StaticGroup:low-resource\;0\;1\;0xe64d4dff\;\;\;; } diff --git a/coli_a_00560.pdf b/coli_a_00560.pdf new file mode 100644 index 0000000000000000000000000000000000000000..a09d96376787e14668cfee25f369bfc249b809da Binary files /dev/null and b/coli_a_00560.pdf differ diff --git a/merx2024lowresourcemachinetranslationretrievalaugmented - Low Resource Machine Translation through Retrieval Augmented LLM Prompting_ a Study on the Mambai Language.pdf b/merx2024lowresourcemachinetranslationretrievalaugmented - Low Resource Machine Translation through Retrieval Augmented LLM Prompting_ a Study on the Mambai Language.pdf new file mode 100644 index 0000000000000000000000000000000000000000..b71e3e4659d373ba11fcd4d9d65553689a32cc7d Binary files /dev/null and b/merx2024lowresourcemachinetranslationretrievalaugmented - Low Resource Machine Translation through Retrieval Augmented LLM Prompting_ a Study on the Mambai Language.pdf differ diff --git a/spencer2024llmshelpcreategrammar - Can LLMs Help Create Grammar__ Automating Grammar Creation for Endangered Languages with in Context Learning.pdf b/spencer2024llmshelpcreategrammar - Can LLMs Help Create Grammar__ Automating Grammar Creation for Endangered Languages with in Context Learning.pdf new file mode 100644 index 0000000000000000000000000000000000000000..32e031ce5f42e67394ca96a6efb485ebfea1bbcb Binary files /dev/null and b/spencer2024llmshelpcreategrammar - Can LLMs Help Create Grammar__ Automating Grammar Creation for Endangered Languages with in Context Learning.pdf differ diff --git a/tekgurler2025llmstranslationhistoricallowresourced - LLMs for Translation_ Historical, Low Resourced Languages and Contemporary AI Models.pdf b/tekgurler2025llmstranslationhistoricallowresourced - LLMs for Translation_ Historical, Low Resourced Languages and Contemporary AI Models.pdf new file mode 100644 index 0000000000000000000000000000000000000000..52ee859a36a772a00171180ef9c4225aa5685365 Binary files /dev/null and b/tekgurler2025llmstranslationhistoricallowresourced - LLMs for Translation_ Historical, Low Resourced Languages and Contemporary AI Models.pdf differ diff --git a/zhang2024hire - Hire a Linguist!_ Learning Endangered Languages in LLMs with in Context Linguistic Descriptions.pdf b/zhang2024hire - Hire a Linguist!_ Learning Endangered Languages in LLMs with in Context Linguistic Descriptions.pdf new file mode 100644 index 0000000000000000000000000000000000000000..46ce96ef5bde04f7a8b470e31f55c5077b6f665e Binary files /dev/null and b/zhang2024hire - Hire a Linguist!_ Learning Endangered Languages in LLMs with in Context Linguistic Descriptions.pdf differ