Search Results for author:
Found 4 papers, 3 papers with code
Align-to-Distill: Trainable Attention Alignment for Knowledge Distillation in Neural Machine Translation
The Attention Alignment Module in A2D performs a dense head-by-head comparison between student and teacher attention heads across layers, turning the combinatorial mapping heuristics into a learning problem.
HaRiM$^+$: Evaluating Summary Quality with Hallucination Risk
One of the challenges of developing a summarization model arises from the difficulty in measuring the factual inconsistency of the generated text.
Learning to Write with Coherence From Negative Examples
We compare our approach with Unlikelihood (UL) training in a text continuation task on commonsense natural language inference (NLI) corpora to show which method better models the coherence by avoiding unlikely continuations.
GLAC Net: GLocal Attention Cascading Networks for Multi-image Cued Story Generation
The task of multi-image cued story generation, such as visual storytelling dataset (VIST) challenge, is to compose multiple coherent sentences from a given sequence of images.
Ranked #30 on
Visual Storytelling
on VIST
(METEOR metric)
