CLAILGSep 1, 2022

Distilling Multi-Scale Knowledge for Event Temporal Relation Extraction

CMU
arXiv:2209.00568v38 citationsh-index: 56
AI Analysis

This addresses the problem of improving temporal relation extraction for natural language processing applications, but it appears incremental as it builds on existing methods to handle multiple proximity bands.

The paper tackled the challenge of Event Temporal Relation Extraction (ETRE) where models struggle with event pairs at different proximity bands, and it introduced MulCo, a knowledge co-distillation approach that achieved new state-of-the-art results on several benchmark datasets.

Event Temporal Relation Extraction (ETRE) is paramount but challenging. Within a discourse, event pairs are situated at different distances or the so-called proximity bands. The temporal ordering communicated about event pairs where at more remote (i.e., ``long'') or less remote (i.e., ``short'') proximity bands are encoded differently. SOTA models have tended to perform well on events situated at either short or long proximity bands, but not both. Nonetheless, real-world, natural texts contain all types of temporal event-pairs. In this paper, we present MulCo: Distilling Multi-Scale Knowledge via Contrastive Learning, a knowledge co-distillation approach that shares knowledge across multiple event pair proximity bands to improve performance on all types of temporal datasets. Our experimental results show that MulCo successfully integrates linguistic cues pertaining to temporal reasoning across both short and long proximity bands and achieves new state-of-the-art results on several ETRE benchmark datasets.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes