A Universal Dependencies Corpora Maintenance Methodology Using Downstream Application

no code implementations • NAACL (SIGTYP) 2021 • Ran Iwamoto, Hiroshi Kanayama, Alexandre Rademaker, Takuya Ohko

This paper investigates updates of Universal Dependencies (UD) treebanks in 23 languages and their impact on a downstream application.

POS

Polar Embedding

no code implementations • CoNLL (EMNLP) 2021 • Ran Iwamoto, Ryosuke Kohita, Akifumi Wachi

Particularly, the latest approaches such as hyperbolic embeddings showed significant performance by representing essential meanings in a hierarchy (generality and similarity of objects) with spatial properties (distance from the origin and difference of angles).

Link Prediction

RIJP at SemEval-2020 Task 1: Gaussian-based Embeddings for Semantic Change Detection

no code implementations • SEMEVAL 2020 • Ran Iwamoto, Masahiro Yukawa

This paper describes the model proposed and submitted by our RIJP team to SemEval 2020 Task1: Unsupervised Lexical Semantic Change Detection.

Change Detection

How Universal are Universal Dependencies? Exploiting Syntax for Multilingual Clause-level Sentiment Detection

no code implementations • LREC 2020 • Hiroshi Kanayama, Ran Iwamoto

This paper investigates clause-level sentiment detection in a multilingual scenario.

Benchmarking BIG-bench Machine Learning