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 role labeling (SRL) involves extracting propositions (i.e.predicates and their typed arguments) from natural language sentences.State-of-the-art SRL models rely on powerful encoders (e.g., LSTMs) and do notmodel non-local interaction between arguments. We propose a new approach tomodeling these interactions while maintaining efficient inference.Specifically, we use Capsule Networks: each proposition is encoded as a tupleof \textit{capsules}, one capsule per argument type (i.e. role). These tuplesserve as embeddings of entire propositions. In every network layer, thecapsules interact with each other and with representations of words in thesentence. Each iteration results in updated proposition embeddings and updatedpredictions about the SRL structure. Our model substantially outperforms thenon-refinement baseline model on all 7 CoNLL-2019 languages and achievesstate-of-the-art results on 5 languages (including English) for dependency SRL.We analyze the types of mistakes corrected by the refinement procedure. Forexample, each role is typically (but not always) filled with at most oneargument. Whereas enforcing this approximate constraint is not useful with themodern SRL system, iterative procedure corrects the mistakes by capturing thisintuition in a flexible and context-sensitive way.

Capturing Argument Interaction in Semantic Role Labeling with Capsule Networks