Multilingual Grammar Induction with Continuous Language Identification
The key to multilingual grammar induction is to couple grammar parameters of different languages together by exploiting the similarity between languages. Previous work relies on linguistic phylogenetic knowledge to specify similarity between languages. In this work, we propose a novel universal grammar induction approach that represents language identities with continuous vectors and employs a neural network to predict grammar parameters based on the representation. Without any prior linguistic phylogenetic knowledge, we automatically capture similarity between languages with the vector representations and softly tie the grammar parameters of different languages. In our experiments, we apply our approach to 15 languages across 8 language families and subfamilies in the Universal Dependency Treebank dataset, and we observe substantial performance gain on average over monolingual and multilingual baselines.
Code (0)
등록된 구현이 없습니다.
Tasks
Language IdentificationSimilar Papers 제목 키워드 기반
A Regularization-based Framework for Bilingual Grammar Induction
Grammar induction aims to discover syntactic structures from unannotated sentences. In this paper, we propose a framework in which the learning process of the grammar model of one language is influenced by knowledge from…
The Importance of Category Labels in Grammar Induction with Child-directed Utterances
Recent progress in grammar induction has shown that grammar induction is possible without explicit assumptions of language-specific knowledge. However, evaluation of induced grammars usually has ignored phrasal labels, a…
Variance of Average Surprisal: A Better Predictor for Quality of Grammar from Unsupervised PCFG Induction
In unsupervised grammar induction, data likelihood is known to be only weakly correlated with parsing accuracy, especially at convergence after multiple runs. In order to find a better indicator for quality of induced gr…
Model SelectionCharacter-based PCFG Induction for Modeling the Syntactic Acquisition of Morphologically Rich Languages
Unsupervised PCFG induction models, which build syntactic structures from raw text, can be used to evaluate the extent to which syntactic knowledge can be acquired from distributional information alone. However, many sta…
Shared Logistic Normal Distributions for Soft Parameter Tying in Unsupervised Grammar Induction
We present a family of priors over probabilistic grammar weights, called the shared logistic normal distribution. This family extends the partitioned logistic normal distribution, enabling factored covariance between the…
Dependency Grammar InductionUnsupervised Dependency Parsing