Mova0.5 pre-release⌕
☰
home / docs / papers / authors / Nathan Schneider

Nathan Schneider

28 paper cards in Mova's library · 2012–2026

Nathan Schneider wrote 28 of the papers Mova reads, in 2012–2026, most of them on Machine translation, Universal Dependencies, Treebanks; often with Noah A. Smith, Omri Abend, Jena D. Hwang.

OpenAlex · ORCID · h-index 28 · 6684 citations · 159 works — openalex, 2026-10-18

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology · ORCID

Topics: Machine translation 9 · Universal Dependencies 5 · Treebanks 3 · Dependency parsing 2 · Coreference resolution 1 · Semantic role labeling 1 · Part-of-speech tagging 1

Papers

  1. CAIT: A Syntactic Parsing Toolkit for Child–Adult InTeractions (2026)
    The authors train a biaffine dependency parser (SuPar, with RoBERTa-large) on the gold part of UD-English-CHILDES, about 48k manually corrected sentences, and add a POS tagger and an utterance-level construction tagger.
  2. UD-English-CHILDES: A Collected Resource of Gold and Silver Universal Dependencies Trees for Child Language Interactions (2025)
    The authors collect several earlier dependency-annotated CHILDES corpora, harmonise them to one set of UD v2 principles and release the first official UD treebank of child-adult speech.
  3. Assessing the Cross-linguistic Utility of Abstract Meaning Representation (2024)
    The article tests whether AMR, which was built for English, can serve as a cross-lingual meaning representation.
  4. Lost in Translationese? Reducing Translation Effect Using Abstract Meaning Representation (2024)
    Translated English has statistical habits that original English lacks, which the field calls translationese.
  5. Are UD Treebanks Getting More Consistent? A Report Card for English UD (2023)
    The paper checks whether the two largest English UD treebanks, EWT and GUM, which have different origins and conversion histories, are converging, and whether it makes sense to train joint models on them.
  6. Meaning Representation of English Prepositional Phrase Roles: SNACS Supersenses vs. Tectogrammatical Functors (2023)
    The paper compares two inventories for the meaning of prepositional phrases: SNACS supersenses (52 labels in three branches — circumstance: Locus, Time, Duration, Source, Goal, Direction, Manner, Purpose…; participant: Agent, Theme, Recipient, Beneficiary, Instrument, Ancillary, Cost…; configuration: relations…
  7. Measuring Fine-Grained Semantic Equivalence with Abstract Meaning Representation (2023)
    Sentence-level judgments of cross-lingual divergence miss small meaning differences. The paper parses both sides of a parallel sentence pair into AMR, aligns their words with fast_align, translates the concept and role labels into English, and runs Smatch. A score of 1 means the two graphs are the same, and any other…
  8. Unified Syntactic Annotation of English in the CGEL Framework (2023)
    The authors test whether the Cambridge Grammar of the English Language (CGEL) can serve as a corpus annotation scheme.
  9. DocAMR: Multi-Sentence AMR Representation and Evaluation (2022)
    AMR was built for single sentences, so a document needs one graph that joins sentences through their coreference links.
  10. Putting Context in SNACS: A 5-Way Classification of Adpositional Pragmatic Markers (2022)
    SNACS labels the meaning of prepositions with supersenses but sent pragmatic uses to a catch-all «discourse» tag.
  11. Universal Dependencies and Semantics for English and Hebrew Child-directed Speech (2022)
    The authors annotate child-directed speech in English (the Adam corpus of CHILDES, 18,113 utterances) and Hebrew (the Hagar corpus, 24,172 utterances) with UD, and then convert the UD trees into logical forms, a meaning representation for acquisition models.
  12. Mischievous nominal constructions in Universal Dependencies (2021)
    The paper looks at noun phrases that do not fit the usual UD picture: descriptors before names (titles such as Mr., role labels like "French actor"), company names with suffixes, numbered designations, dates, times and similar constructions.
  13. Referenceless Parsing-Based Evaluation of AMR-to-English Generation (2021)
    Reference-based metrics such as BLEU compare a generated sentence with one human sentence, which is a poor fit for a meaning representation that many sentences can express.
  14. Cross-linguistically Consistent Semantic and Syntactic Annotation of Child-directed Speech (2021)
    The paper proposes a two-step method for annotating child-directed speech (CDS) in CHILDES. First, the utterances get Universal Dependencies (UD) trees, starting from the existing dependency annotation and then hand-corrected. Second, sentential logical forms (LFs) are produced from the UD trees by unlexicalised…
  15. A Human Evaluation of AMR-to-English Generation Systems (2020)
    Most AMR-to-English systems had been scored only with automatic metrics such as BLEU. The paper runs a new human evaluation of five systems on 100 sentences per system, with 100 human references for comparison. Annotators gave fluency scores (without the input) and adequacy scores (with the AMR), each on a 0–100…
  16. Comparison by Conversion: Reverse-Engineering UCCA from Syntax and Lexical Semantics (2020)
    The paper asks how much of UCCA can be recovered from simpler layers: Universal Dependencies syntax and STREUSLE lexical semantics.
  17. Cross-lingual Semantic Representation for NLP with UCCA (2020)
    A tutorial abstract on UCCA (Universal Conceptual Cognitive Annotation), a meaning scheme meant to apply across languages without language-specific lexical resources.
  18. Parsing Tweets into Universal Dependencies (2018)
    The authors extend the UD guidelines to tweets: emoticons and retweet markers become non-syntactic or discourse tokens, abbreviations such as "idc" stay unnormalized as single words, multiword expressions can be merged, and tweets can have several roots.
  19. Annotation of Tense and Aspect Semantics for Sentential AMR (2018)
    AMR leaves out tense and aspect, because their marks are inflections and articles, which the design deliberately skips.
  20. A Structured Syntax-Semantics Interface for English-AMR Alignment (2018)
    The paper tests a common assumption, that AMR closely mirrors dependency syntax. The authors design an alignment framework from AMR graphs to enhanced Universal Dependencies graphs. Each AMR node or edge can be evoked by words, by syntactic structure, or by both. They hand-annotate 200 AMRs in this framework. Their…
  21. Adposition and Case Supersenses v2.6: Guidelines for English (2017)
    This is the annotation manual for SNACS, a scheme that labels English prepositions, case markers and possessives with "supersenses", a small set of semantic classes.
  22. A Corpus of Preposition Supersenses (2016)
    The paper presents the first English corpus in which every preposition token is annotated with a hierarchical supersense, and each token is annotated twice to measure agreement.
  23. A Corpus and Model Integrating Multiword Expressions and Supersenses (2015)
    The paper defines one task: find lexical expressions in running text, single- or multi-word, and label the noun and verb ones with a supersense (41 coarse classes).
  24. A Hierarchy with, of, and for Preposition Supersenses (2015)
    English prepositions are frequent and very polysemous, and in many uses they mark a role rather than a place or time.
  25. A Dependency Parser for Tweets (2014)
    Tweets break the assumptions of newswire parsers: many tokens (retweet markers, usernames, hashtags, URLs, punctuation) have no syntactic role, a tweet can hold several utterances with their own roots, and multiword names and idioms are common.
  26. Comprehensive Annotation of Multiword Expressions in a Social Web Corpus (2014)
    The authors annotate every multiword expression (MWE) in a web corpus of about 55,000 words, sentence by sentence, without limiting the kinds of MWE.
  27. Abstract Meaning Representation for Sembanking (2013)
    The paper presents Abstract Meaning Representation (AMR), a rooted, labelled graph for the meaning of whole sentences, meant to be easy for people to read and for programs to traverse.
  28. Coarse Lexical Semantic Annotation with Supersenses: An Arabic Case Study (2012)
    The authors reuse WordNet's supersense labels (the coarse lexicographer classes) as a light scheme for lexical semantics, and apply it to Arabic.

Co-authors (73)

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/authors/nathan-schneider/