41 |
Learning with Different Amounts of Annotation: From Zero to Many Labels ...
|
|
|
|
BASE
|
|
Show details
|
|
42 |
Extracting Event Temporal Relations via Hyperbolic Geometry ...
|
|
|
|
BASE
|
|
Show details
|
|
43 |
FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging ...
|
|
|
|
BASE
|
|
Show details
|
|
44 |
Contrastive Explanations for Model Interpretability ...
|
|
|
|
Abstract:
Anthology paper link: https://aclanthology.org/2021.emnlp-main.120/ Abstract: Contrastive explanations clarify why an event occurred in contrast to another. They are more inherently intuitive to humans to both produce and comprehend. We propose a methodology to produce contrastive explanations for classification models by modifying the representation to disregard non-contrastive information, and modifying model behavior to only be based on contrastive reasoning. Our method is based on projecting model representation to a latent space that captures only the features that are useful (to the model) to differentiate two potential decisions. We demonstrate the value of contrastive explanations by analyzing two different scenarios, using both high-level abstract concept attribution and low-level input token/span attribution, on two widely used text classification tasks. Specifically, we produce explanations for answering: for which label, and against which alternative label, is some aspect of the input useful? And ...
|
|
Keyword:
Computational Linguistics; Machine Learning; Machine Learning and Data Mining; Natural Language Processing
|
|
URL: https://dx.doi.org/10.48448/z2dq-8918 https://underline.io/lecture/37855-contrastive-explanations-for-model-interpretability
|
|
BASE
|
|
Hide details
|
|
45 |
Open Aspect Target Sentiment Classification with Natural Language Prompts ...
|
|
|
|
BASE
|
|
Show details
|
|
46 |
Stepmothers are mean and academics are pretentious: What do pretrained language models learn about you? ...
|
|
|
|
BASE
|
|
Show details
|
|
47 |
We've had this conversation before: A Novel Approach to Measuring Dialog Similarity ...
|
|
|
|
BASE
|
|
Show details
|
|
48 |
ESTER: A Machine Reading Comprehension Dataset for Reasoning about Event Semantic Relations ...
|
|
|
|
BASE
|
|
Show details
|
|
50 |
CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization ...
|
|
|
|
BASE
|
|
Show details
|
|
53 |
Partially Supervised Named Entity Recognition via the Expected Entity Ratio Loss ...
|
|
|
|
BASE
|
|
Show details
|
|
54 |
Honey or Poison? Solving the Trigger Curse in Few-shot Event Detection via Causal Intervention ...
|
|
|
|
BASE
|
|
Show details
|
|
55 |
Analyzing the Surprising Variability in Word Embedding Stability Across Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
56 |
Neural Machine Translation with Heterogeneous Topic Knowledge Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
57 |
Towards Zero-Shot Knowledge Distillation for Natural Language Processing ...
|
|
|
|
BASE
|
|
Show details
|
|
59 |
SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations ...
|
|
|
|
BASE
|
|
Show details
|
|
60 |
Automatic Text Evaluation through the Lens of Wasserstein Barycenters ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|