1 |
Towards the Early Detection of Child Predators in Chat Rooms: A BERT-based Approach ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
To what extent do human explanations of model behavior align with actual model behavior? ...
|
|
|
|
Abstract:
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 study, we investigate the extent to which human-generated explanations of models' inference decisions align with how models actually make these decisions. More specifically, we define three alignment metrics that quantify how well natural language explanations align with model sensitivity to input words, as measured by integrated gradients. Then, we evaluate eight different models (the base and large versions of BERT, RoBERTa and ELECTRA, as well as anRNN and bag-of-words model), and find that the BERT-base model has the highest alignment with human-generated explanations, for all alignment metrics. Focusing in on transformers, we find that the base versions tend to have higher alignment with human-generated explanations than their larger counterparts, suggesting that increasing the number of ...
|
|
Keyword:
Computational Linguistics; Language Models; Machine Learning; Machine Learning and Data Mining; Natural Language Processing; Neural Network
|
|
URL: https://dx.doi.org/10.48448/r05t-rn44 https://underline.io/lecture/39893-to-what-extent-do-human-explanations-of-model-behavior-align-with-actual-model-behaviorquestion
|
|
BASE
|
|
Hide details
|
|
3 |
Elementary-Level Math Word Problem Generation using Pre-Trained Transformers ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
What Models Know About Their Attackers: Deriving Attacker Information From Latent Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Segment, Mask, and Predict: Augmenting Chinese Word Segmentation with Self-Supervision ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Coral: An Approach for Conversational Agents in Mental Health Applications ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
#WhyDidTheyStay: An NLP-driven approach to analyzing the factors that affect domestic violence victims ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
SciBERT-based Multitasking Deep Neural Architecture to identify Contribution Statements from Scientific articles ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
"I don't know who she is": Discourse and Knowledge Driven Coreference Resolution ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Certified Robustness to Programmable Transformations in LSTMs ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Sinhala-English Code-mixed and Code-switched Data Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Adverse Drug Reaction Classification of Tweets with Fusion of Text and Drug Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Learning Cross-lingual Representations for Event Coreference Resolution with Multi-view Alignment and Optimal Transport ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
VisualSem: a high-quality knowledge graph for vision and language ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Specializing Multilingual Language Models: An Empirical Study ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
On the Language-specificity of Multilingual BERT and the Impact of Fine-tuning ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
One-Shot Lexicon Learning for Low-Resource Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|