Language Modeling with Syntactic and Semantic Representation for Sentence Acceptability Predictions

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F19%3A10427098" target="_blank" >RIV/00216208:11320/19:10427098 - isvavai.cz</a>

Result on the web

<a href="https://www.aclweb.org/anthology/W19-6108" target="_blank" >https://www.aclweb.org/anthology/W19-6108</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Language Modeling with Syntactic and Semantic Representation for Sentence Acceptability Predictions

Original language description

In this paper, we investigate the effect of enhancing lexical embeddings in LSTM language models (LM) with syntactic and semantic representations. We evaluate the language models using perplexity, and we evaluate the performance of the models on the task of predicting human sentence acceptability judgments. We train LSTM language models on sentences automatically annotated with universal syntactic dependency roles (Nivre, 2016), dependency depth and universal semantic tags (Abzianidze et al., 2017) to predict sentence acceptability judgments. Our experiments indicate that syntactic tags lower perplexity, while semantic tags increase it. Our experiments also show that neither syntactic nor semantic tags improve the performance of LSTM language models on the task of predicting sentence acceptability judgments.

Czech name

—

Czech description

—

Type

O - Miscellaneous

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

—

Publication year

2019

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů