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 linguistic features influencing the RE form are learnt and captured by state-of-the-art RFS models. The results of 8 probing tasks show that all the defined features were learnt to some extent. The probing tasks pertaining to referential status and syntactic position exhibited the highest performance. The lowest performance was achieved by the probing models designed to predict discourse structure properties beyond the sentence level.
Code (0)
등록된 구현이 없습니다.
Tasks
FormPositionReferring ExpressionReferring expression generationSentenceSimilar Papers 제목 키워드 기반
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 dat…
FormReferring ExpressionReferring expression generationDecomposing Queries into Tool Calls for Long-Video Keyframe Retrieval
Keyframe selection is a direct way to provide verifiable visual evidence for long-video question answering (QA). Queries differ in what they require, and finding the right frames depends on knowing what to look for. Exis…
Video Question AnsweringFocus on What's Informative and Ignore What's not: Communication Strategies in a Referential Game
Research in multi-agent cooperation has shown that artificial agents are able to learn to play a simple referential game while developing a shared lexicon. This lexicon is not easy to analyze, as it does not show many pr…
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…
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…