---
title: "Mova: Main list — papers it applies — Elamur Research"
description: "The 105 papers of Mova's own list, by the stage of its pipeline"
canonical: "https://research.elamur.ai/free/en/projects/mova/main/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/projects/mova/main/)

[home](https://md.research.elamur.ai/free/en/) / [projects](https://md.research.elamur.ai/free/en/projects/) / [Mova](https://md.research.elamur.ai/free/en/projects/mova/) / Main list

Mova · papers

# Main list

The 105 works of [Mova](https://mova.elamur.ai/free/en/)'s own list, with their effect and the stage of the pipeline that uses them. measured marks a work whose effect Mova measured in its own experiments — 30 of them, including ideas that did not help; the others are rule sources, designs or background. Each stage has its page.

- [text → tokens](https://md.research.elamur.ai/free/en/projects/mova/tokens/) — Splitting the text into words with their part of speech, lemma and features: the tagger and its lexicon. · 3 papers · 1 measured
- [tokens → tree](https://md.research.elamur.ai/free/en/projects/mova/tree/) — Building the Universal Dependencies tree: the transition parser, the treebanks, the grammars of English as rule sources. · 50 papers · 3 measured
- [tree → frames](https://md.research.elamur.ai/free/en/projects/mova/frames/) — Reading the tree into frames — who did what to whom — with speech acts, hedges and coreference. · 20 papers · 8 measured
- [frames → world](https://md.research.elamur.ai/free/en/projects/mova/world/) — Keeping the world of the text: entities, their states, quantities and compiled commonsense. · 9 papers · 5 measured
- [world → answer](https://md.research.elamur.ai/free/en/projects/mova/answer/) — Answering from the world, with a reason: school tests, reading questions, word problems. · 11 papers · 6 measured
- [and back, byte for byte](https://md.research.elamur.ai/free/en/projects/mova/back/) — Giving the text back exactly: round trips and converters between dialects of UD. · 2 papers · 0 measured
- [how it learns](https://md.research.elamur.ai/free/en/projects/mova/learn/) — How the parsers learn: perceptrons, instance-based learning, bootstrapping and the teacher loop. · 10 papers · 7 measured