SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.08350 · 2024

Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 8 functions out of this paper's own repositories and ran 7 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
pangjh3/llm4mt canonical 7 of 8
FunctionStatusWhere it lives
create_prompt Ran pangjh3/llm4mt/train/inference.py
pointer only (licence: NONE) · get_code("4a62d89cb68ccb26")
create_prompt Ran pangjh3/llm4mt/train/attention_alignment_llama2.py
pointer only (licence: NONE) · get_code("65a7d55fbb2fbdf6")
get_config_class_from_processor_class Ran pangjh3/llm4mt/transformers/utils/create_dummy_models.py
pointer only (licence: NONE) · get_code("3d999b95009c7537")
get_processor_types_from_config_class Ran pangjh3/llm4mt/transformers/utils/create_dummy_models.py
pointer only (licence: NONE) · get_code("0c0b81b081919d8e")
read_input Ran pangjh3/llm4mt/train/attention_alignment_llama2.py
pointer only (licence: NONE) · get_code("2a686c7dfc4f6740")
read_instruct Ran pangjh3/llm4mt/train/inference_acllama2.py
pointer only (licence: NONE) · get_code("1a23d98ad0f9c590")
read_instruct Ran pangjh3/llm4mt/train/attention_alignment_llama2.py
pointer only (licence: NONE) · get_code("341ad8f9aaad0613")
get_architectures_from_config_class Not yet run pangjh3/llm4mt/transformers/utils/create_dummy_models.py
pointer only (licence: NONE) · get_code("4ac2af420b64a13a")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The evolution of Neural Machine Translation (NMT) has been significantly influenced by six core challenges (Koehn and Knowles, 2017), which have acted as benchmarks for progress in this field. This study revisits these challenges, offering insights into their ongoing relevance in the context of advanced Large Language Models (LLMs): domain mismatch, amount of parallel data, rare word prediction, translation of long sentences, attention model as word alignment, and sub-optimal beam search. Our empirical findings indicate that LLMs effectively lessen the reliance on parallel data for major languages in the pretraining phase. Additionally, the LLM-based translation system significantly enhances the translation of long sentences that contain approximately 80 words and shows the capability to translate documents of up to 512 words. However, despite these significant improvements, the challenges of domain mismatch and prediction of rare words persist. While the challenges of word alignment and beam search, specifically associated with NMT, may not apply to LLMs, we identify three new challenges for LLMs in translation tasks: inference efficiency, translation of low-resource languages in the pretraining phase, and human-aligned evaluation. The datasets and models are released at https://github.com/pangjh3/LLM4MT.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2401.08350")
get_code_for_paper("2401.08350")
have("2401.08350")

Connect an agent — have() is free.