atlas

Research map / Large language models / Language, safety and interpretability

Semantic Parsing with Neural Hybrid Trees

AAAI 2017 · Large language models › Language, safety and interpretability · approach: Linguistic encoding in LLM representations · 16 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add neural window features to discriminative hybrid tree (J=2)DISCHT+ · GeoQuery Englishaccuracy: 86.8 -> 90.0Helped
add neural features with J=0 (dense embedding replaces sparse words) (ablation)DISCHT+ · GeoQuery Englishaccuracy: 86.8 -> 87.9Helped
increase window size from 1 to 2 (ablation)Neural hybrid tree · GeoQuery Germanaccuracy: 76.8 -> 73.9Hurt
increase window size from 1 to 2 (ablation)Neural hybrid tree · GeoQuery Chineseaccuracy: 75.4 -> 81.1Helped
increase window size from 1 to 2 (ablation)Neural hybrid tree · GeoQuery Thaiaccuracy: 84.6 -> 82.1Hurt
add neural features (best J per language)DISCHT+ · GeoQuery additional languagesaccuracy: 76.1 -> 81.1 (Chinese)Helped
add neural features under synonym replacementDISCHT+ · GeoQuery synonym (avg over 8 languages)F1 drop: -1.6 -> -1.2Helped

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy