Explicitly modeling case improves neural dependency parsing
Neural dependency parsing models that compose word representations from characters can presumably exploit morphosyntax when making attachment decisions. How much do they know about morphology? We investigate how well they handle morphological case, which is important for parsing. Our experiments on Czech, German and Russian suggest that adding explicit morphological case{---}either oracle or predicted{---}improves neural dependency parsing, indicating that the learned representations in these models do not fully encode the morphological knowledge that they need, and can still benefit from targeted forms of explicit linguistic modeling.
Code (0)
등록된 구현이 없습니다.
Tasks
Dependency ParsingMulti-Task LearningSimilar Papers 제목 키워드 기반
What do character-level models learn about morphology? The case of dependency parsing
When parsing morphologically-rich languages with neural models, it is beneficial to model input at the character level, and it has been claimed that this is because character-level models learn morphology. We test these …
Dependency ParsingMorphological AnalysisA* CCG Parsing with a Supertag and Dependency Factored Model
We propose a new A* CCG parsing model in which the probability of a tree is decomposed into factors of CCG categories and its syntactic dependencies both defined on bi-directional LSTMs. Our factored model allows the pre…
SentenceImprovements to Dependency Parsing Using Automatic Simplification of Data
In dependency parsing, much effort is devoted to the development of new methods of language modeling and better feature settings. Less attention is paid to actual linguistic data and how appropriate they are for automati…
Dependency ParsingLanguage ModelingLanguage ModellingText SimplificationSparse Fuzzy Attention for Structured Sentiment Analysis
Attention scorers have achieved success in parsing tasks like semantic and syntactic dependency parsing. However, in tasks modeled into parsing, like structured sentiment analysis, "dependency edges" are very sparse whic…
Dependency ParsingSentiment AnalysisA Higher-Order Semantic Dependency Parser
Higher-order features bring significant accuracy gains in semantic dependency parsing. However, modeling higher-order features with exact inference is NP-hard. Graph neural networks (GNNs) have been demonstrated to be an…
Dependency ParsingGraph LearningSemantic Dependency Parsing