Are Mutually Intelligible Languages Easier to Translate?
Two languages are considered mutually intelligible if their native speakers can communicate with each other, while using their own mother tongue. How does the fact that humans perceive a language pair as mutually intelligible affect the ability to learn a translation model between them? We hypothesize that the amount of data needed to train a neural ma-chine translation model is anti-proportional to the languages' mutual intelligibility. Experiments on the Romance language group reveal that there is indeed strong correlation between the area under a model's learning curve and mutual intelligibility scores obtained by studying human speakers.
Code (0)
등록된 구현이 없습니다.
Tasks
TranslationSimilar Papers 제목 키워드 기반
Machine Translation Evaluation Benchmark for Wu Chinese: Workflow and Analysis
We introduce a FLORES+ dataset as an evaluation benchmark for modern Wu Chinese machine translation models and showcase its compatibility with existing Wu data. Wu Chinese is mutually unintelligible with other Sinitic la…
Machine TranslationTranslationKurdish Interdialect Machine Translation
This research suggests a method for machine translation among two Kurdish dialects. We chose the two widely spoken dialects, Kurmanji and Sorani, which are considered to be mutually unintelligible. Also, despite being sp…
Machine TranslationTranslationTajik-Farsi Persian Transliteration Using Statistical Machine Translation
Tajik Persian is a dialect of Persian spoken primarily in Tajikistan and written with a modified Cyrillic alphabet. Iranian Persian, or Farsi, as it is natively called, is the lingua franca of Iran and is written with th…
Machine TranslationTranslationTransliterationMapping Phonology to Semantics: A Computational Model of Cross-Lingual Spoken-Word Recognition
Closely related languages are often mutually intelligible to various degrees. Therefore, speakers of closely related languages are usually capable of (partially) comprehending each other’s speech without explicitly learn…
Emergent Linguistic Phenomena in Multi-Agent Communication Games
In this work, we propose a computational framework in which agents equipped with communication capabilities simultaneously play a series of referential games, where agents are trained using deep reinforcement learning. W…
Deep Reinforcement LearningReinforcement LearningReinforcement Learning (RL)