English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Semantic representations are central in many NLP tasks that requirehuman-interpretable data. The conjunctivist framework - primarily developed byPietroski (2005, 2018) - obtains expressive representations with only a fewbasic semantic types and relations systematically linked to syntacticpositions. While representational simplicity is crucial for computationalapplications, such findings have not yet had major influence on NLP. We presentthe first generic semantic representation format for NLP directly based onthese insights. We name the format EAT due to its basis in the Event-, Agent-,and Theme arguments in Neo-Davidsonian logical forms. It builds on the ideathat similar tripartite argument relations are ubiquitous across categories,and can be constructed from grammatical structure without additional lexicalinformation. We present a detailed exposition of EAT and how it relates toother prevalent formats used in prior work, such as Abstract MeaningRepresentation (AMR) and Minimal Recursion Semantics (MRS). EAT stands out intwo respects: simplicity and versatility. Uniquely, EAT discards semanticmetapredicates, and instead represents semantic roles entirely via positionalencoding. This is made possible by limiting the number of roles to only three;a major decrease from the many dozens recognized in e.g. AMR and MRS. EAT'ssimplicity makes it exceptionally versatile in application. First, we show thatdrastically reducing semantic roles based on EAT benefits text generation fromMRS in the test settings of Hajdik et al. (2019). Second, we implement thederivation of EAT from a syntactic parse, and apply this for parallel corpusgeneration between grammatical classes. Third, we train an encoder-decoder LSTMnetwork to map EAT to English. Finally, we use both the encoder-decoder networkand a rule-based alternative to conduct grammatical transformation fromEAT-input.

EAT: a simple and versatile semantic representation format for multi-purpose NLP