The Source-Target Domain Mismatch Problem in Machine Translation
| Autor: | Jiatao Gu, Jiajun Shen, Junxian He, Michael Auli, Peng-Jen Chen, Matthew Le, Marc'Aurelio Ranzato, Myle Ott |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Computation and Language Machine translation Computer science Context (language use) computer.software_genre Domain (software engineering) Empirical research Human–computer interaction Metric (mathematics) Affect (linguistics) Empirical evidence computer Computation and Language (cs.CL) Degradation (telecommunications) |
| Zdroj: | EACL |
| Popis: | While we live in an increasingly interconnected world, different places still exhibit strikingly different cultures and many events we experience in our every day life pertain only to the specific place we live in. As a result, people often talk about different things in different parts of the world. In this work we study the effect of local context in machine translation and postulate that particularly in low resource settings this causes the domains of the source and target language to greatly mismatch, as the two languages are often spoken in further apart regions of the world with more distinctive cultural traits and unrelated local events. We first formalize the concept of source-target domain mismatch, propose a metric to quantify it, and provide empirical evidence corroborating our intuition that organic text produced by people speaking very different languages exhibits the most dramatic differences. We conclude with an empirical study of how source-target domain mismatch affects training of machine translation systems for low resource language pairs. In particular, we find that it severely affects back-translation, but the degradation can be alleviated by combining back-translation with self-training and by increasing the relative amount of target side monolingual data. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|