Learning Monolingual Compositional Representations via Bilingual Supervision
نویسندگان
چکیده
Bilingual models that capture the semantics of sentences are typically only evaluated on cross-lingual transfer tasks such as cross-lingual document categorization or machine translation. In this work, we evaluate the quality of the monolingual representations learned with a variant of the bilingual compositional model of Hermann and Blunsom (2014), when viewing translations in a second language as a semantic annotation as the original language text. We show that compositional objectives based on phrase translation pairs outperform compositional objectives based on bilingual sentences and on monolingual paraphrases.
منابع مشابه
Transduction Recursive Auto-Associative Memory: Learning Bilingual Compositional Distributed Vector Representations of Inversion Transduction Grammars
We introduce TRAAM, or Transduction RAAM, a fully bilingual generalization of Pollack’s (1990) monolingual Recursive Auto-Associative Memory neural network model, in which each distributed vector represents a bilingual constituent—i.e., an instance of a transduction rule, which specifies a relation between two monolingual constituents and how their subconstituents should be permuted. Bilingual ...
متن کاملMetalinguistic Awareness and Bilingual vs. Monolingual EFL Learners: Evidence from a Diagonal Bilingual Context
This paper reports a study of 85 Iranian EFL learners in the English Language Department of Urmia University. It explores the possible differences between performance of 38 Persian monolingual and 47 Turkish-Persian bilingual EFL learners on metalinguistic tasks of ungrammatical structures and translation. The underlying hypothesis is that bilinguals in diagonal bilingual contexts experience a ...
متن کاملBilBOWA: Fast Bilingual Distributed Representations without Word Alignments
We introduce BilBOWA (Bilingual Bag-ofWords without Alignments), a simple and computationally-efficient model for learning bilingual distributed representations of words which can scale to large monolingual datasets and does not require word-aligned parallel training data. Instead it trains directly on monolingual data and extracts a bilingual signal from a smaller set of raw-text sentence-alig...
متن کاملLearning a second language and working memory: the role of bilinguali
the purpose of the present study was to evaluate the function of working memory in bilingual, monolingual children and children with learning disorder. The research project was of comparative causality type. Participants included 60 monolingual children, 34 children with learning disabilities and 62 bilingual children. Which completed the Wechsler Intelligence Scale and preschool children's Wec...
متن کاملBilingual Word Representations with Monolingual Quality in Mind
Recent work in learning bilingual representations tend to tailor towards achieving good performance on bilingual tasks, most often the crosslingual document classification (CLDC) evaluation, but to the detriment of preserving clustering structures of word representations monolingually. In this work, we propose a joint model to learn word representations from scratch that utilizes both the conte...
متن کامل