MétaCan
Menu
Back to cohort
Record W4285288434 · doi:10.18653/v1/2022.acl-long.233

LAGr: Label Aligned Graphs for Better Systematic Generalization in Semantic Parsing

2022· article· en· W4285288434 on OpenAlexafffund
Dora Jambor, Dzmitry Bahdanau

Bibliographic record

VenueProceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2022
Typearticle
Languageen
FieldComputer Science
TopicNatural Language Processing Techniques
Canadian institutionsMila - Quebec Artificial Intelligence InstituteMcGill UniversityCanadian Institute for Advanced Research
FundersSamsungCanadian Institute for Advanced ResearchMicrosoft Research
KeywordsComputer scienceParsingGeneralizationArtificial intelligenceNatural language processingInferenceGraphSequence (biology)Theoretical computer scienceMathematics

Abstract

fetched live from OpenAlex

Semantic parsing is the task of producing structured meaning representations for natural language sentences.Recent research has pointed out that the commonly-used sequenceto-sequence (seq2seq) semantic parsers struggle to generalize systematically, i.e. to handle examples that require recombining known knowledge in novel settings.In this work, we show that better systematic generalization can be achieved by producing the meaning representation directly as a graph and not as a sequence.To this end we propose LAGr (Label Aligned Graphs), a general framework to produce semantic parses by independently predicting node and edge labels for a complete multi-layer input-aligned graph.The strongly-supervised LAGr algorithm requires aligned graphs as inputs, whereas weaklysupervised LAGr infers alignments for originally unaligned target graphs using approximate maximum-a-posteriori inference.Experiments demonstrate that LAGr achieves significant improvements in systematic generalization upon the baseline seq2seq parsers in both strongly-and weakly-supervised settings.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.013
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.007
Threshold uncertainty score0.024

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0030.013
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0010.002
Bibliometrics0.0020.002
Science and technology studies0.0010.002
Scholarly communication0.0020.007
Open science0.0030.004
Research integrity0.0030.005
Insufficient payload (model declined to judge)0.0070.004

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.008
GPT teacher head0.242
Teacher spread0.234 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations7
Published2022
Admission routes2
Has abstractyes

Explore more

Same venueProceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)Same topicNatural Language Processing TechniquesFrench-language works237,207