Combining Transformers with Natural Language Explanations
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.
Code (1)
Tasks
Argument MiningSimilar Papers 제목 키워드 기반
Towards Explainable Strategy Templates using NLP Transformers
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 LearningIntegrating Explanations in Learning LTL Specifications from Demonstrations
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
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 Answeringe-SNLI-VE: Corrected Visual-Textual Entailment with Natural Language Explanations
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 InferenceTo what extent do human explanations of model behavior align with actual model behavior?
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