Search Results for author:
Found 5 papers, 3 papers with code
A Simple Contrastive Learning Objective for Alleviating Neural Text Degeneration
The cross-entropy objective has proved to be an all-purpose training objective for autoregressive language models (LMs).
TLDR: Token Loss Dynamic Reweighting for Reducing Repetitive Utterance Generation
We hypothesize that the deeper reason is that in the training corpora, there are hard tokens that are more difficult for a generative model to learn than others and, once learning has finished, hard tokens are still under-learned, so that repetitive generations are more likely to happen.
Improving Neural Response Diversity with Frequency-Aware Cross-Entropy Loss
Specifically, we first analyze the influence of the commonly used Cross-Entropy (CE) loss function, and find that the CE loss function prefers high-frequency tokens, which results in low-diversity responses.
Why are Sequence-to-Sequence Models So Dull? Understanding the Low-Diversity Problem of Chatbots
Sequence-to-sequence (Seq2Seq) models have been shown to be very effective for response generation.
Object Tracking via Dual Linear Structured SVM and Explicit Feature Map
Structured support vector machine (SSVM) based methods has demonstrated encouraging performance in recent object tracking benchmarks.
