conftrace_

2018 EMNLP EMNLP 2018

Limitations in learning an interpreted language with recurrent models

Abstract

AbstractIn this submission I report work in progress on learning simplified interpreted languages by means of recurrent models. The data is constructed to reflect core properties of natural language as modeled in formal syntax and semantics. Preliminary results suggest that LSTM networks do generalise to compositional interpretation, albeit only in the most favorable learning setting.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Interdisciplinary and Natural Language Processing

Authors

Denis Paperno

Topics

Machine Learning > Optimization & Theory > Learning Theory Interdisciplinary > Linguistics > Computational Linguistics Deep Learning > Architectures > Recurrent Neural Networks Natural Language Processing > Understanding > Semantics

Keywords

recurrent neural network recurrent model lstm network formal semantics formal syntax compositional interpretation

More from EMNLP 2018

All EMNLP 2018 papers →

Does Syntactic Knowledge in Multilingual Language Models Transfer Across Languages?

Exploiting Attention to Reveal Shortcomings in Memory Models

End-to-end Image Captioning Exploits Distributional Similarity in Multimodal Space

The Fact Extraction and VERification (FEVER) Shared Task

The Data Challenge in Misinformation Detection: Source Reputation vs. Content Veracity

Crowdsourcing Semantic Label Propagation in Relation Classification