AI Paper Atlas

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

Just Add Functions: A Neural-Symbolic Language Model

David Demeter, Doug Downey

AAAI 2020 · Large language models › Language, safety and interpretability · approach: Linguistic encoding in LLM representations · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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 numeric micro-models based on class-specific metrics and PDFsLSTM language model · Wikitext-2 Numbersperplexity: 790.2 -> 475.5Improved
Add numeric micro-models based on class-specific metrics and PDFsLSTM language model · Wikitext-103 Numbersperplexity: 364.6 -> 262.0Improved
Add geographic micro-models using location distanceLSTM language model · Wikitext-2 Locationsperplexity: 4,812.1 -> 1,801.1Improved
Add geographic micro-models using location distanceLSTM language model · Wikitext-103 Locationsperplexity: 585.7 -> 488.6Improved
Add numeric micro-modelsAWD-LSTM · Wikitext-2 Numbersperplexity: 421.1 -> 336.4Improved
Add geographic micro-modelsAWD-LSTM · Wikitext-2 Locationsperplexity: 2,066.3 -> 1,340.7Improved
Initialize word embeddings with GloVe trained on the 6B token corpusNNLM · Wikitext-2 Numbersperplexity: 831.2 -> 640.0Improved
Initialize word embeddings with GloVe trained on the 6B token corpusNNLM · Wikitext-2 Locationsperplexity: 4,969.4 -> 3,888.3Improved
Append numeric values to embeddings and freeze the appended dimensionsNNLM · Wikitext-2 Numbersperplexity: 790.2 -> 717.9Improved
Append longitude and latitude to embeddings and freeze the appended dimensionsNNLM · Wikitext-2 Locationsperplexity: 4,812.1 -> 3,890.2Improved
Add micro-models to the LSTM while monitoring overall language-model performanceLSTM language model · Wikitext-2 globalperplexity: 92.0 -> 89.8Improved

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