Combining Transformers with Natural Language Explanations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ruggeri, Federico, Lippi, Marco, Torroni, Paolo
Format: Preprint
Published: 2021
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917629057302528
author Ruggeri, Federico
Lippi, Marco
Torroni, Paolo
author_facet Ruggeri, Federico
Lippi, Marco
Torroni, Paolo
contents Many NLP applications require models to be interpretable. However, many successful neural architectures, including transformers, still lack effective interpretation methods. A possible solution could rely on building explanations from domain knowledge, which is often available as plain, natural language text. We thus propose an extension to transformer models that makes use of external memories to store natural language explanations and use them to explain classification outputs. We conduct an experimental evaluation on two domains, legal text analysis and argument mining, to show that our approach can produce relevant explanations while retaining or even improving classification performance.
format Preprint
id arxiv_https___arxiv_org_abs_2110_00125
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Combining Transformers with Natural Language Explanations
Ruggeri, Federico
Lippi, Marco
Torroni, Paolo
Computation and Language
Artificial Intelligence
Many NLP applications require models to be interpretable. However, many successful neural architectures, including transformers, still lack effective interpretation methods. A possible solution could rely on building explanations from domain knowledge, which is often available as plain, natural language text. We thus propose an extension to transformer models that makes use of external memories to store natural language explanations and use them to explain classification outputs. We conduct an experimental evaluation on two domains, legal text analysis and argument mining, to show that our approach can produce relevant explanations while retaining or even improving classification performance.
title Combining Transformers with Natural Language Explanations
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2110.00125