Towards explainable evaluation metrics for machine translation
Unlike classical lexical overlap metrics such as BLEU, most current evaluation metrics for
machine translation (for example, COMET or BERTScore) are based on black-box large …
machine translation (for example, COMET or BERTScore) are based on black-box large …
Recent Developments on Accountability and Explainability for Complex Reasoning Tasks
P Atanasova - Accountable and Explainable Methods for Complex …, 2024 - Springer
This chapter delves into the recent accountability tools tailored for the evolving landscape of
machine learning models for complex reasoning tasks. With the increasing integration of …
machine learning models for complex reasoning tasks. With the increasing integration of …
Towards explainable evaluation metrics for natural language generation
Unlike classical lexical overlap metrics such as BLEU, most current evaluation metrics (such
as BERTScore or MoverScore) are based on black-box language models such as BERT or …
as BERTScore or MoverScore) are based on black-box language models such as BERT or …
A comparison of explainable artificial intelligence methods in the phase classification of multi-principal element alloys
We demonstrate the capabilities of two model-agnostic local post-hoc model interpretability
methods, namely breakDown (BD) and shapley (SHAP), to explain the predictions of a black …
methods, namely breakDown (BD) and shapley (SHAP), to explain the predictions of a black …
Thermostat: A large collection of NLP model explanations and analysis tools
In the language domain, as in other domains, neural explainability takes an ever more
important role, with feature attribution methods on the forefront. Many such methods require …
important role, with feature attribution methods on the forefront. Many such methods require …
Improve interpretability of neural networks via sparse contrastive coding
Although explainable artificial intelligence (XAI) has achieved remarkable developments in
recent years, there are few efforts have been devoted to the following problems, namely, i) …
recent years, there are few efforts have been devoted to the following problems, namely, i) …
Local explanation of dialogue response generation
In comparison to the interpretation of classification models, the explanation of sequence
generation models is also an important problem, however it has seen little attention. In this …
generation models is also an important problem, however it has seen little attention. In this …
REV: information-theoretic evaluation of free-text rationales
Generating free-text rationales is a promising step towards explainable NLP, yet evaluating
such rationales remains a challenge. Existing metrics have mostly focused on measuring the …
such rationales remains a challenge. Existing metrics have mostly focused on measuring the …
A multi-facet analysis of BERT-based entity matching models
State-of-the-art Entity Matching approaches rely on transformer architectures, such as BERT,
for generating highly contextualized embeddings of terms. The embeddings are then used to …
for generating highly contextualized embeddings of terms. The embeddings are then used to …
Explaining interactions between text spans
Reasoning over spans of tokens from different parts of the input is essential for natural
language understanding (NLU) tasks such as fact-checking (FC), machine reading …
language understanding (NLU) tasks such as fact-checking (FC), machine reading …