DeepAI AI Chat
Log In Sign Up

Target Word Masking for Location Metonymy Resolution

by   Haonan Li, et al.

Existing metonymy resolution approaches rely on features extracted from external resources like dictionaries and hand-crafted lexical resources. In this paper, we propose an end-to-end word-level classification approach based only on BERT, without dependencies on taggers, parsers, curated dictionaries of place names, or other external resources. We show that our approach achieves the state-of-the-art on 5 datasets, surpassing conventional BERT models and benchmarks by a large margin. We also show that our approach generalises well to unseen data.


page 1

page 2

page 3

page 4


Creating Reverse Bilingual Dictionaries

Bilingual dictionaries are expensive resources and not many are availabl...

End-to-End Neural Event Coreference Resolution

Traditional event coreference systems usually rely on pipeline framework...

LexSubCon: Integrating Knowledge from Lexical Resources into Contextual Embeddings for Lexical Substitution

Lexical substitution is the task of generating meaningful substitutes fo...

Lexical-semantic resources: yet powerful resources for automatic personality classification

In this paper, we aim to reveal the impact of lexical-semantic resources...

Word Sense Disambiguation using a Bidirectional LSTM

In this paper we present a clean, yet effective, model for word sense di...

Automatic Lexical Simplification for Turkish

In this paper, we present the first automatic lexical simplification sys...

Deep encoding of etymological information in TEI

This paper aims to provide a comprehensive modeling and representation o...