AMRICA: an AMR Inspector for Cross-language Alignments
نویسندگان
چکیده
Abstract Meaning Representation (AMR), an annotation scheme for natural language semantics, has drawn attention for its simplicity and representational power. Because AMR annotations are not designed for human readability, we present AMRICA, a visual aid for exploration of AMR annotations. AMRICA can visualize an AMR or the difference between two AMRs to help users diagnose interannotator disagreement or errors from an AMR parser. AMRICA can also automatically align and visualize the AMRs of a sentence and its translation in a parallel text. We believe AMRICA will simplify and streamline exploratory research on cross-lingual AMR corpora.Meaning Representation (AMR), an annotation scheme for natural language semantics, has drawn attention for its simplicity and representational power. Because AMR annotations are not designed for human readability, we present AMRICA, a visual aid for exploration of AMR annotations. AMRICA can visualize an AMR or the difference between two AMRs to help users diagnose interannotator disagreement or errors from an AMR parser. AMRICA can also automatically align and visualize the AMRs of a sentence and its translation in a parallel text. We believe AMRICA will simplify and streamline exploratory research on cross-lingual AMR corpora.
منابع مشابه
What's Hot in Human Language Technology: Highlights from NAACL HLT 2015
Meaning Representation (AMR) is a semantic representation language which intends to assign the same graph representation to capture the semantics from sentences with the same basic meaning. This representation has received increasing attention in the NLP community because of its simplicity and expressive power. Vanderwende and colleagues (Vanderwende, Menezes, and Quirk 2015) have demonstrated ...
متن کاملRobust Incremental Neural Semantic Graph Parsing
Parsing sentences to linguisticallyexpressive semantic representations is a key goal of Natural Language Processing. Yet statistical parsing has focussed almost exclusively on bilexical dependencies or domain-specific logical forms. We propose a neural encoder-decoder transition-based parser which is the first full-coverage semantic graph parser for Minimal Recursion Semantics (MRS). The model ...
متن کاملVerification of Programs with Inspector Methods
Most classes in an object-oriented program provide access to an object’s state through methods, so that client code does not depend on and cannot interfere with the object’s internal representation composed of fields and internal component objects. Methods used for this purpose are sometimes called inspector methods. In order to extend the benefits of inspector methods to specifications, the me...
متن کاملAn Autoencoder Approach to Learning Bilingual Word Representations
Cross-language learning allows one to use training data from one language to build models for a different language. Many approaches to bilingual learning require that we have word-level alignment of sentences from parallel corpora. In this work we explore the use of autoencoder-based methods for cross-language learning of vectorial word representations that are coherent between two languages, w...
متن کاملAn Approach for Proving the Correctness of Inspector/Executor Transformations
To take advantage of multicore parallelism, programmers and compilers rewrite, or transform, programs to expose loop-level parallelism. Showing the correctness, or legality, of such program transformations enables their incorporation into compilers. However, the correctness of inspector/executor strategies, which develop parallel schedules at runtime for computations with nonaffine array access...
متن کامل