Assessing Neural Referential Form Selectors on a Realistic Multilingual Dataset
Previous work on Neural Referring Expression Generation (REG) all uses WebNLG, an English dataset that has been shown to reflect a very limited range of referring expression (RE) use. To tackle this issue, we build a dataset based on the OntoNotes corpus that contains a broader range of RE use in both English and Chinese (a language that uses zero pronouns). We build neural Referential Form Selection (RFS) models accordingly, assess them on the dataset and conduct probing experiments. The experiments suggest that, compared to WebNLG, OntoNotes is better for assessing REG/RFS models. We compare English and Chinese RFS and confirm that, in line with linguistic theories, Chinese RFS depends more on discourse context than English.
Code (0)
등록된 구현이 없습니다.
Tasks
FormReferring ExpressionReferring expression generationSimilar Papers 제목 키워드 기반
What can Neural Referential Form Selectors Learn?
Despite achieving encouraging results, neural Referring Expression Generation models are often thought to lack transparency. We probed neural Referential Form Selection (RFS) models to find out to what extent the linguis…
FormPositionReferring ExpressionReferring expression generation+1Emergence of Multilingualism in Population based Referential Games
The ability of agents to learn to communicate by interaction has been studied through emergent communication tasks. Inspired by previous work in this domain, we extend the referential game setup to a population of spatia…
Wow! What a Useful Extension! Introducing Non-Referential Concepts to Wordnet
In this paper we present the ongoing efforts to expand the depth and breath of the Open Multilingual Wordnet coverage by introducing two new classes of non-referential concepts to wordnet hierarchies: interjections and n…
Reference-Limited Compositional Learning: A Realistic Assessment for Human-level Compositional Generalization
To narrow the considerable gap between artificial and human intelligence, we propose a new task, namely reference-limited compositional learning (RLCL), which reproduces three core challenges to mimic human perception: c…
Fast Estimation Method for the Stability of Ensemble Feature Selectors
It is preferred that feature selectors be \textit{stable} for better interpretabity and robust prediction. Ensembling is known to be effective for improving the stability of feature selectors. Since ensembling is time-co…