Handling non-compositionality in multilingual CNLs
In this paper, we describe methods for handling multilingual non-compositional constructions in the framework of GF. We specifically look at methods to detect and extract non-compositional phrases from parallel texts and propose methods to handle such constructions in GF grammars. We expect that the methods to handle non-compositional constructions will enrich CNLs by providing more flexibility in the design of controlled languages. We look at two specific use cases of non-compositional constructions: a general-purpose method to detect and extract multilingual multiword expressions and a procedure to identify nominal compounds in German. We evaluate our procedure for multiword expressions by performing a qualitative analysis of the results. For the experiments on nominal compounds, we incorporate the detected compounds in a full SMT pipeline and evaluate the impact of our method in machine translation process.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationTranslationSimilar Papers 제목 키워드 기반
Controlled Natural Languages and Default Reasoning
Controlled natural languages (CNLs) are effective languages for knowledge representation and reasoning. They are designed based on certain natural languages with restricted lexicon and grammar. CNLs are unambiguous and s…
ImplicaturesLogical ReasoningQuestion AnsweringA Brief State of the Art for Ontology Authoring
One of the main challenges for building the Semantic web is Ontology Authoring. Controlled Natural Languages CNLs offer a user friendly means for non-experts to author ontologies. This paper provides a snapshot of the st…
A Challenge Proposal for Narrative Generation Using CNLs
How Naked is the Naked Truth? A Multilingual Lexicon of Nominal Compound Compositionality
The Impact of Positional Encodings on Multilingual Compression
In order to preserve word-order information in a non-autoregressive setting, transformer architectures tend to include positional knowledge, by (for instance) adding positional encodings to token embeddings. Several modi…
Inductive Bias