GEN Encoder learns query intent embeddings from click logs as weak supervision and multi-task paraphrase training, outperforming prior methods on intent similarity and using nearest-neighbor search to cover half of unseen queries.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2019 4verdicts
UNVERDICTED 4representative citing papers
BERT activations show strongest correlation with MEG data for simple sentences; DNN representations generate synthetic brain data that improves stimuli decoding accuracy.
Word deletion impact on BERT embeddings is measured to estimate syntactic reducibility of words and n-grams, then applied to induce dependency trees.
Introduces a weakly-supervised framework partitioning CTA transcript parsing into sequence labeling and text span-pair relation extraction using distant supervision from protocols and neighbor sentences for long-range context.
citing papers explorer
-
Generic Intent Representation in Web Search
GEN Encoder learns query intent embeddings from click logs as weak supervision and multi-task paraphrase training, outperforming prior methods on intent similarity and using nearest-neighbor search to cover half of unseen queries.
-
Relating Simple Sentence Representations in Deep Neural Networks and the Brain
BERT activations show strongest correlation with MEG data for simple sentences; DNN representations generate synthetic brain data that improves stimuli decoding accuracy.
-
Inducing Syntactic Trees from BERT Representations
Word deletion impact on BERT embeddings is measured to estimate syntactic reducibility of words and n-grams, then applied to induce dependency trees.
-
Eliciting Knowledge from Experts:Automatic Transcript Parsing for Cognitive Task Analysis
Introduces a weakly-supervised framework partitioning CTA transcript parsing into sequence labeling and text span-pair relation extraction using distant supervision from protocols and neighbor sentences for long-range context.