Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,932 papers · 148 categories

Trend · papers per month

count% of corpus
0111 · Mar 201919922001200920172026
3 results for “XMTC”
Label-aware Document Representation via Hybrid Attention for Extreme Multi-Label Text Classificationcs.LG

Paper proposes LAHA to improve XMTC by integrating document content and label correlation.

problem Challenges in tagging documents with most relevant labels from a large label set.
method Hybrid attention deep neural network model (LAHA) that combines multi-label self-attention and adaptive fusion strategies.
result LAHA outperforms state-of-the-art methods, especially on tail labels.
XMTCHybrid AttentionDeep Neural NetworkLabel-aware RepresentationTail Labels
2019-05-24abs ↗pdf ↗
Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text Classificationcs.LG

APLC-XLNet improves XMTC by clustering labels and reducing computational time.

problem Efficiently tagging texts with many labels from a large set.
method Fine-tunes XLNet with APLC to approximate cross entropy loss.
result Achieved state-of-the-art results on XMTC benchmarks.
Extreme Multi-Label ClassificationXLNetAPLCLabel ClusteringDeep Learning
2020-07-05abs ↗pdf ↗