On Learning Language-Invariant Representations for Universal Machine Translation
12. července 2020
Řečníci
O prezentaci
The goal of universal machine translation is to learn to translate between any pair of languages, given pairs of translated documents for some of these languages. Despite impressive empirical results and an increasing interest in massively multilingual models, theoretical analysis on translation errors made by such universal machine translation models is only nascent. In this paper, we take one step towards better understanding of universal machine translation by first proving an impossibility theorem in the general case. In particular, we derive a lower bound on the translation error in the many-to-one translation setting, which shows that any algorithm aiming to learn shared sentence representations among multiple language pairs has to make a large translation error on at least one of the translation tasks, if no assumption on the structure of the languages is made. On the positive side, we show that if the documents follow a natural encoder-decoder generative process, then we can expect a natural notion of “generalization”: a linear number of pairs, rather than quadratic, suffices. Our theory also explains what kinds of connection graphs between pairs of languages are better suited: ones with longer paths result in worse sample complexity in terms of the total number of documents per language pair needed.The goal of universal machine translation is to learn to translate between any pair of languages, given pairs of translated documents for some of these languages. Despite impressive empirical results and an increasing interest in massively multilingual models, theoretical analysis on translation errors made by such universal machine translation models is only nascent. In this paper, we take one step towards better understanding of universal machine translation by first proving an impossibility t…
Kategorie
Lingvistika a filologie
Kategorie · 88 prezentací
O organizátorovi (ICML 2020)
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
Online Learning with Imperfect Hints
Zhlédnout později
Circuit-Based Intrinsic Methods to Detect Overfitting
Zhlédnout později
Model-Based Methods in Reinforcement Learning - Part 2: Model-based Control
Zhlédnout později
Neuro-Symbolic Visual Reasoning: Disentangling "Visual" from "Reasoning"
Zhlédnout později
