Unverified50% confidenceFactExact time
Coreference resolution is usually modeled as a clustering problem: first extract all mentions, then determine which mentions belong to the same entity cluster.
1
Sources
50%
Confidence
Long-term
Relevance
10/27/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAdvanced implementations of query rewriting include intent recognition, coreference resolution, and multi-intent decomposition.66% similarUnverifiedThe correct approach to preventing data leakage in form extraction scenarios is to perform grouped splits by source entity or template ID, ensuring that all variants of the same template appear on only one side64% similarUnverifiedEntity resolution needs to handle three classes of problems: same name different entity, different name same entity, and regional variants.62% similarUnverifiedThe debugging order is essentially layer-by-layer attribution, breaking an end-to-end failure into four independently verifiable stages: indexing, retrieval, ranking and generation.61% similarUnverifiedIn synthetic data, replacing identifiers, names, section order, and surface wording can create samples that appear different but retain the same underlying phrase templates, which provides shortcuts for the model; exact duplicate detection cannot find this overlap, and finer-grained methods such as n-gram overlap, embedding similarity, or template family tracking are needed.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1102136API
curl https://kongchang.com/api/v1/knowledge/claims/1102136MCP
get_claim(id=1102136)