Search Results for author:
Found 5 papers, 3 papers with code
PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneck
CLIP-based classifiers rely on the prompt containing a {class name} that is known to the text encoder.
Semi-supervised Neural Machine Translation with Consistency Regularization for Low-Resource Languages
We also introduce a SentenceBERT-based filter to enhance the quality of augmenting data by retaining semantically similar sentence pairs.
PiC: A Phrase-in-Context Dataset for Phrase Understanding and Semantic Search
While contextualized word embeddings have been a de-facto standard, learning contextualized phrase embeddings is less explored and being hindered by the lack of a human-annotated benchmark that tests machine understanding of phrase semantics given a context sentence or paragraph (instead of phrases alone).
Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models?
We find two reasons why IM is not better than LOO: (1) deleting a single word from the input only marginally reduces a classifier's accuracy; and (2) a highly predictable word is always given near-zero attribution, regardless of its true importance to the classifier.
Out of Order: How Important Is The Sequential Order of Words in a Sentence in Natural Language Understanding Tasks?
Encouraging classifiers to capture word order information improves the performance on most GLUE tasks, SQuAD 2. 0 and out-of-samples.
Natural Language Inference
Natural Language Understanding
+2
