paper-with-me

홈 › Papers

Combining Transformers with Natural Language Explanations

2021-09-02 · Federico Ruggeri, Marco Lippi, Paolo Torroni

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.

📄 PDF Abstract BibTeX arXiv:2110.00125

Code (1)

lt-nlp-lab-unibo/bert-natural-explanations 공식 구현

Tasks

Argument Mining

Similar Papers 제목 키워드 기반

Towards Explainable Strategy Templates using NLP Transformers

2023-11-23 · Pallavi Bagga, Kostas Stathis

This paper bridges the gap between mathematical heuristic strategies learned from Deep Reinforcement Learning (DRL) in automated agent negotiation, and comprehensible, natural language explanations. Our aim is to make th…

Deep Reinforcement Learning

Integrating Explanations in Learning LTL Specifications from Demonstrations

2024-04-03 · Ashutosh Gupta, John Komp, Abhay Singh Rajput, Krishna Shankaranarayanan 외

This paper investigates whether recent advances in Large Language Models (LLMs) can assist in translating human explanations into a format that can robustly support learning Linear Temporal Logic (LTL) from demonstration…

Case-Based Abductive Natural Language Inference

2020-09-30 · COLING 2022 10 · Marco Valentino, Mokanarangan Thayaparan, André Freitas

Most of the contemporary approaches for multi-hop Natural Language Inference (NLI) construct explanations considering each test case in isolation. However, this paradigm is known to suffer from semantic drift, a phenomen…

Natural Language InferenceQuestion Answering

e-SNLI-VE: Corrected Visual-Textual Entailment with Natural Language Explanations

2020-04-07 · Virginie Do, Oana-Maria Camburu, Zeynep Akata, Thomas Lukasiewicz

The recently proposed SNLI-VE corpus for recognising visual-textual entailment is a large, real-world dataset for fine-grained multimodal reasoning. However, the automatic way in which SNLI-VE has been assembled (via com…

Multimodal ReasoningNatural Language Inference

To what extent do human explanations of model behavior align with actual model behavior?

2020-12-24 · EMNLP (BlackboxNLP) 2021 11 · Grusha Prasad, Yixin Nie, Mohit Bansal, Robin Jia 외

Given the increasingly prominent role NLP models (will) play in our lives, it is important for human expectations of model behavior to align with actual model behavior. Using Natural Language Inference (NLI) as a case st…

modelNatural Language Inference