Search Results for author:
Found 17 papers, 14 papers with code
Multi-Granularity Guided Fusion-in-Decoder
In Open-domain Question Answering (ODQA), it is essential to discern relevant contexts as evidence and avoid spurious ones among retrieved results.
GLEN: Generative Retrieval via Lexical Index Learning
For training, GLEN effectively exploits a dynamic lexical identifier using a two-phase index learning strategy, enabling it to learn meaningful lexical identifiers and relevance signals between queries and documents.
Forgetting-aware Linear Bias for Attentive Knowledge Tracing
This problem arises from the bias that overprioritizes the correlation of questions while inadvertently ignoring the impact of forgetting behavior.
Toward a Better Understanding of Loss Functions for Collaborative Filtering
Inspired by this analysis, we propose a novel loss function that improves the design of alignment and uniformity considering the unique patterns of datasets called Margin-aware Alignment and Weighted Uniformity (MAWU).
uCTRL: Unbiased Contrastive Representation Learning via Alignment and Uniformity for Collaborative Filtering
In this paper, we propose Unbiased ConTrastive Representation Learning (uCTRL), optimizing alignment and uniformity functions derived from the InfoNCE loss function for CF models.
ConQueR: Contextualized Query Reduction using Search Logs
One extracts core terms from an original query at the term level, and the other determines whether a sub-query is a suitable reduction for the original query at the sequence level.
It's Enough: Relaxing Diagonal Constraints in Linear Autoencoders for Recommendation
Inspired by this analysis, we propose simple-yet-effective linear autoencoder models using diagonal inequality constraints, called Relaxed Linear AutoEncoder (RLAE) and Relaxed Denoising Linear AutoEncoder (RDLAE).
SpaDE: Improving Sparse Representations using a Dual Document Encoder for First-stage Retrieval
Sparse document representations have been widely used to retrieve relevant documents via exact lexical matching.
Bilateral Self-unbiased Learning from Biased Implicit Feedback
Implicit feedback has been widely used to build commercial recommender systems.
S-Walk: Accurate and Scalable Session-based Recommendationwith Random Walks
Session-based recommendation (SR) predicts the next items from a sequence of previous items consumed by an anonymous user.
TailMix: Overcoming the Label Sparsity for Extreme Multi-label Classification
Extreme multi-label classification (XMC) aims at finding the most relevant labels from a huge label set at the industrial scale.
Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation
Existing studies in weakly-supervised semantic segmentation (WSSS) using image-level weak supervision have several limitations: sparse object coverage, inaccurate object boundaries, and co-occurring pixels from non-target objects.
Ranked #22 on
Weakly-Supervised Semantic Segmentation
on PASCAL VOC 2012 test
(using extra training data)
MelBERT: Metaphor Detection via Contextualized Late Interaction using Metaphorical Identification Theories
Automated metaphor detection is a challenging task to identify metaphorical expressions of words in a sentence.
Local Collaborative Autoencoders
Top-N recommendation is a challenging problem because complex and sparse user-item interactions should be adequately addressed to achieve high-quality recommendation results.
Session-aware Linear Item-Item Models for Session-based Recommendation
Session-based recommendation aims at predicting the next item given a sequence of previous items consumed in the session, e. g., on e-commerce or multimedia streaming services.
Waste not, Want not: All-Alive Pruning for Extremely Sparse Networks
We demonstrate that AAP equipped with existing pruning methods (i. e., iterative pruning, one-shot pruning, and dynamic pruning) consistently improves the accuracy of original methods at 128× - 4096× compression ratios on three benchmark datasets.
Collaborative Distillation for Top-N Recommendation
Knowledge distillation (KD) is a well-known method to reduce inference latency by compressing a cumbersome teacher model to a small student model.
