Rephrase detection is used to identify the rephrases and has long been treated as a task with pairwise input, which does not fully utilize the contextual information (e. g. users’ implicit feedback).
In this work, we go beyond the existing paradigms and propose a novel approach to generate high-quality paraphrases with weak supervision data.
The paper considers a Mixture Multilayer Stochastic Block Model (MMLSBM), where layers can be partitioned into groups of similar networks, and networks in each group are equipped with a distinct Stochastic Block Model.
Query rewriting (QR) systems are widely used to reduce the friction caused by errors in a spoken language understanding pipeline.
Another challenge of RGB-infrared ReID is that the intra-person (images from the same person) discrepancy is often larger than the inter-person (images from different persons) discrepancy, so a dual-subspace pairing strategy is proposed to alleviate this problem.
Then, inspired by the wide success of pre-trained contextual language embeddings, and also as a way to compensate for insufficient QR training data, we propose a language-modeling (LM) based approach to pre-train query embeddings on historical user conversation data with a voice assistant.
In this paper, we propose to distill the internal representations of a large model such as BERT into a simplified version of it.
Competition (or confrontation) is observed between the STN module and the ReID module, and two-stage training is applied to acquire a strong STNReID for partial ReID.
The anchored segment refers to the wake-up word part of an audio stream, which contains valuable speaker information that can be used to suppress interfering speech and background noise.
Holistic person re-identification (ReID) has received extensive study in the past few years and achieves impressive progress.
In this paper, we use a modified softmax function, termed Sphere Softmax, to solve the classification problem and learn a hypersphere manifold embedding simultaneously.
In this paper, we propose a novel method called AlignedReID that extracts a global feature which is jointly learned with local features.
Ranked #1 on Person Re-Identification on CUHK-SYSU
The goal of semantic parsing is to map natural language to a machine interpretable meaning representation language (MRL).