Nathan Schneider · page 2
Papers
- Lost in Translationese? Reducing Translation Effect Using Abstract Meaning Representation (2024 · 16 citations)
Translated English has statistical habits that original English lacks, which the field calls translationese. - The NLTK FrameNet API: Designing for Discoverability with a Rich Linguistic Resource (2017 · 14 citations)
FrameNet is a large English lexicon built on frame semantics. Researchers use it widely, but its custom XML format is hard to work with, and the website's HTML views hide some details, such as the mappings between frame elements across related frames. The few existing open-source readers are outdated and not widely… - Natural Language Processing RELIES on Linguistics (2025 · 13 citations)
Large language models now write fluent text without any built-in machinery for grammar or compositional meaning. - ELQA: A Corpus of Metalinguistic Questions and Answers about English (2023 · 12 citations)
Metalanguage is language that takes language itself as its topic, for example claims about what a phrase means or which form is grammatical. - Supersense Tagging for Arabic: the MT-in-the-Middle Attack (2013 · 10 citations)
The paper tackles nominal supersense tagging for Arabic: finding noun chunks and assigning each one of the 25 coarse WordNet noun categories. - Referenceless Parsing-Based Evaluation of AMR-to-English Generation (2021 · 9 citations)
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. - Comparison by Conversion: Reverse-Engineering UCCA from Syntax and Lexical Semantics (2020 · 9 citations)
The paper asks how much of UCCA can be recovered from simpler layers: Universal Dependencies syntax and STREUSLE lexical semantics. - Mischievous nominal constructions in Universal Dependencies (2021 · 8 citations)
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. - Are UD Treebanks Getting More Consistent? A Report Card for English UD (2023 · 7 citations)
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. - Cross-lingual Semantic Representation for NLP with UCCA (2020 · 6 citations)
A tutorial abstract on UCCA (Universal Conceptual Cognitive Annotation), a meaning scheme meant to apply across languages without language-specific lexical resources. - UD-English-CHILDES: A Collected Resource of Gold and Silver Universal Dependencies Trees for Child Language Interactions (2025 · 4 citations)
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. - Measuring Fine-Grained Semantic Equivalence with Abstract Meaning Representation (2023 · 4 citations)
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… - Meaning Representation of English Prepositional Phrase Roles: SNACS Supersenses vs. Tectogrammatical Functors (2023 · 3 citations)
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… - Sentence-level Feedback Generation for English Language Learners: Does Data Augmentation Help? (2023 · 3 citations)
The paper addresses feedback comment generation (GenChal 2022: FCG). Given a learner's English sentence and the span containing a preposition error, the system must write a short explanation of what is wrong and how to fix it, not just correct it. The authors fine-tune T5-Large, marking the error span with delimiter… - A corpus of preposition supersenses in English web reviews (2016 · 3 citations)
English prepositions are extremely frequent and highly polysemous, yet earlier annotated resources for their meaning cover only a few dozen common types, sample isolated tokens, or lack inter-annotator agreement figures. - The Relative Clauses AMR Parsers Hate Most (2024 · 2 citations)
Headline Smatch scores for English AMR parsers are high, but they hide how parsers handle specific hard constructions. This paper looks at one frequent long-distance dependency: relative clauses (RCs). In these, the modified noun also fills an argument slot inside the clause. - Unified Syntactic Annotation of English in the CGEL Framework (2023 · 2 citations)
The authors investigate if CGEL (Huddleston and Pullum, 2002), the well-known descriptive grammar of English, is usable in practice as a scheme for annotating corpora. - Cross-linguistically Consistent Semantic and Syntactic Annotation of Child-directed Speech (2021 · 2 citations)
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… - Language Models Learn Constructional Semantics, Not To Mention Syntax: Investigating LM Understanding of Paired-Focus Constructions (2026 · 1 citation)
The paper asks whether open-source language models, and not only the largest prompted LLMs, understand both the form and the meaning of rare English PAIRED-FOCUS constructions: LET-ALONE, MUCH-LESS, NOT-TO-MENTION and NEVER-MIND. - Sense and Sensitivity: “Reasoning” Models are More Robust, but can Diverge from Human Consensus in a Legal Interpretation Task (2026 · 1 citation)
The paper asks whether prompting LLMs can stand in for surveys of ordinary speakers when deciding what legal text means, for example whether an item counts as covered under an insurance definition. - Universal Dependencies and Semantics for English and Hebrew Child-directed Speech (2022 · 1 citation)
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. - Book Review: Design Patterns in Fluid Construction Grammar edited by Luc Steels (2013 · 1 citation)
This is a review by Nathan Schneider and Reut Tsarfaty of a volume edited by Luc Steels on Fluid Construction Grammar (FCG). - A Curious Class of Adpositional Multiword Expressions in Korean (2026)
Korean is poorly covered in cross-lingual multiword expression resources such as PARSEME. Multiword adpositions in particular have no systematic description or annotated data. The authors identify and describe a class they call postpositional verb-based constructions (PVCs). In a PVC, a case postposition combines… - 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. - Speaking of Language: Reflections on Metalanguage Research in NLP (2026)
This position paper argues that NLP should pay much more attention to metalanguage, now that fluent LLM chatbots are widely used.
This page in Markdown → https://md.research.elamur.ai/free/en/authors/nathan-schneider/page/2/