Work

Emergent Predication Structure in Hidden State Vectors of Neural Readers

Year: 2017

Type: conference-paper

Abstract: A significant number of neural architectures for reading comprehension have recently been developed and evaluated on large cloze-style datasets.We present experiments supporting the emergence of "predication structure" in the hidden state vectors of these readers.More specifically, we provide evidence that the hidden state vectors represent atomic formulas Φ[c] where Φ is a semantic property (predicate) and c is a constant symbol entity identifier.

Source: Workshop on Representation Learning for NLP (RepL4NLP)

DOI: 10.18653/v1/w17-2604

Authors: Hai Wang, Takeshi Onishi, Kevin Gimpel, David McAllester

Institution: Toyota Technological Institute at Chicago

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: Nvidia

OpenAlex ID: W2962828804