Papers by Nathan Schneider
Comprehensive Supersense Disambiguation of English Prepositions and Possessives (P18-1)
Copied to clipboard
Nathan Schneider, Jena D. Hwang, Vivek Srikumar, Jakob Prange, Austin Blodgett, Sarah R. Moeller, Aviram Stern, Adi Bitan, Omri Abend
| Challenge: | Frequent prepositions like for are maddeningly polysemous, their interpretation depends especially on the object of the preposition. |
| Approach: | They propose a new annotation scheme, corpus, and task for the disambiguation of prepositions and possessives in English. |
| Outcome: | The proposed annotations are comprehensive with respect to types and tokens of these markers and use broadly applicable supersense classes rather than fine-grained dictionary definitions. |
Semantic Supersenses for English Possessives (L18-1)
Copied to clipboard
| Challenge: | Existing semantic categories for possessive constructions are limited to nominals and s-genitives. |
| Approach: | They propose to use a supersense inventory to annotate English possessives . they show existing supersensor categories are readily applicable to possessives. |
| Outcome: | The proposed annotations are applied to English possessives in a corpus of web reviews. |
To Ask LLMs about English Grammaticality, Prompt Them in a Different Language (2024.findings-emnlp)
Copied to clipboard
| Challenge: | a study focuses on questions about grammar and fluency in multilingual LLMs . english is the dominant training language for all three models, but prompting in a different language often yields better results. |
| Approach: | They ask three multilingual language models in multiple languages to test their model's grammatical accuracy. |
| Outcome: | The language of the prompt can significantly affect model performance, the study finds . english is the dominant training language for all three models, the researchers show . |
Unpacking Let Alone: Human-Scale Models Generalize to a Rare Construction in Form but not Meaning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent evidence suggests that language models with human-scale pretraining data may possess a similar generalization ability by generalizing from frequent to rare constructions. |
| Approach: | They construct a synthetic benchmark that targets syntactic and semantic properties of the English Let-Alone construction and compare it with a human-scale transformer language model. |
| Outcome: | The proposed model can generalize from frequent to rare constructions, but human-scale models do not make correct generalizations about Let-Alone’s meaning. |
UCxn: Typologically-Informed Annotation of Constructions Atop Universal Dependencies (2024.lrec-main)
Copied to clipboard
Leonie Weissweiler, Nina Böbel, Kirian Guiller, Santiago Herrera, Wesley Samuel Scivetti, Arthur Lorenzi, Nurit Melnik, Archna Bhatia, Hinrich Schütze, Lori Levin, Amir Zeldes, Joakim Nivre, William Croft, Nathan Schneider
| Challenge: | Grammatical constructions that convey meaning through a particular combination of several morphosyntactic elements are not labeled holistically. |
| Approach: | They propose to augment UD annotations with a ‘UCxn’ annotation layer for such meaning-bearing grammatical constructions and to approach this in a typologically informed way so that morphosyntactic strategies can be compared across languages. |
| Outcome: | The proposed annotation layer could be used to annotate meaning-bearing constructions across languages and to compare them across languages. |
Cross-lingual Semantic Representation for NLP with UCCA (2020.coling-tutorials)
Copied to clipboard
| Challenge: | introductory tutorial to UCCA, a symbolic meaning representation for semantic representations. |
| Approach: | This tutorial introduces UCCA, a cross-linguistically applicable framework for semantic representation . it will provide a detailed introduction to the UCca annotation guidelines, design philosophy and available resources . |
| Outcome: | The tutorial will provide a detailed introduction to the UCCA framework and compare it to other meaning representations. |
Probabilistic, Structure-Aware Algorithms for Improved Variety, Accuracy, and Coverage of AMR Alignments (2021.acl-long)
Copied to clipboard
| Challenge: | Current algorithms for AMR parsing suffer from limited coverage and less-than-ideal accuracy . a new algorithm for AML uses unsupervised learning and heuristics to align components of AMR graphs to spans in English sentences . |
| Approach: | They propose algorithms for aligning components of Abstract Meaning Representation graphs to spans in English sentences. |
| Outcome: | The proposed approach covers a wider variety of AMR substructures than previously considered . it achieves higher coverage of nodes and edges, and does so with higher accuracy. |
Probe-Less Probing of BERT’s Layer-Wise Linguistic Knowledge with Masked Word Prediction (2022.naacl-srw)
Copied to clipboard
| Challenge: | Among studies on localization of linguistic knowledge, it is unclear what information is encoded in each layer. |
| Approach: | They analyze BERT’s layer-wise masked word prediction on an English corpus and find syntactic and semantic information is encoded at different layers for words of different syntaktic categories. |
| Outcome: | The proposed model outperforms state-of-the-art models in many downstream tasks. |
A Human Evaluation of AMR-to-English Generation Systems (2020.coling-main)
Copied to clipboard
| Challenge: | a recent human evaluation of AMR generation systems is compared to automated metrics. |
| Approach: | They propose a human evaluation which collects fluency and adequacy scores and categorization of error types for AMR generation systems. |
| Outcome: | The results show that human evaluations are more nuanced than automated metrics. |
ELQA: A Corpus of Metalinguistic Questions and Answers about English (2023.acl-long)
Copied to clipboard
| Challenge: | ELQA corpus is metalinguistic—it consists of language about language. |
| Approach: | They present a corpus of questions and answers in and about the English language . they use a free-form question answering task and multiple LLMs to analyze their capacity . |
| Outcome: | The ELQA corpus covers grammar, meaning, fluency, and etymology . the results can be used to investigate metalinguistic capabilities of NLU models . |
Making Heads and Tails of Models with Marginal Calibration for Sparse Tagsets (2021.findings-emnlp)
Copied to clipboard
| Challenge: | despite high accuracy, modern neural networks can still suffer from severe miscalibration. |
| Approach: | They propose to use tag frequency grouping to measure calibration error in different frequency bands to reduce error. |
| Outcome: | The proposed techniques reduce calibration error across the marginal distribution for two existing sequence taggers. |
DocAMR: Multi-Sentence AMR Representation and Evaluation (2022.naacl-main)
Copied to clipboard
Tahira Naseem, Austin Blodgett, Sadhana Kumaravel, Tim O’Gorman, Young-Suk Lee, Jeffrey Flanigan, Ramón Astudillo, Radu Florian, Salim Roukos, Nathan Schneider
| Challenge: | Abstract Meaning Representation (AMR) graphs are compared to gold graphs by the Smatch metric, but lack a well-defined representation and evaluation. |
| Approach: | They propose an algorithm for deriving a unified graph representation using a super-sentential annotation method. |
| Outcome: | The proposed algorithm avoids the pitfalls of over-merging and lacks coherence from under merging. |
MASALA: Modelling and Analysing the Semantics of Adpositions in Linguistic Annotation of Hindi (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing work on SNACS annotation for a variety of typologically diverse languages focuses on semantic role labelling and upstream applications in related languages. |
| Approach: | They propose to use the multilingual SNACS annotation scheme to attempt automatic labelling of SNAC supersenses in Hindi. |
| Outcome: | The proposed method is competitive with previous work on English and Gujarati. |
Xposition: An Online Multilingual Database of Adpositional Semantics (2022.lrec-1)
Copied to clipboard
| Challenge: | Xposition is an online platform for documenting adpositional semantics across languages . SNACS provides a unified metalanguage for characterizing the major classes of meanings expressed with appositions . |
| Approach: | They propose to use Xposition to document adpositional semantics across languages . Xpos houses annotation guidelines, structured lexicographic documentation, annotated corpora . |
| Outcome: | The proposed platform houses annotation guidelines, structured lexicographic documentation, and annotated corpora. |
Accounting for Language Effect in the Evaluation of Cross-lingual AMR Parsers (2022.coling-1)
Copied to clipboard
| Challenge: | Existing multilingual AMR evaluation metrics are not available for cross-lingual parsers . existing studies show that source language has a dramatic effect on cross-linguistic AMRs . |
| Approach: | They propose to use three multilingual adaptations of monolingual AMR evaluation metrics to evaluate cross-lingual AML parsers. |
| Outcome: | The proposed metric is the most highly correlated to english AMRs, while the most correlated is S2match. |
Comparison by Conversion: Reverse-Engineering UCCA from Syntax and Lexical Semantics (2020.coling-main)
Copied to clipboard
| Challenge: | a systematic comparative analysis of linguistic meaning representations from different frameworks is needed. |
| Approach: | They compare a rule-based converter and a supervised delexicalized parser to map meaning representations from different frameworks. |
| Outcome: | The proposed method yields surprisingly accurate representations close to fully supervised UCCA parser quality. |
Putting Words in BERT’s Mouth: Navigating Contextualized Vector Spaces with Pseudowords (2021.emnlp-main)
Copied to clipboard
| Challenge: | a new technique for exploring contextualized vector space is proposed . masked prediction of a word in a sentence allows controlled exploration of the space . |
| Approach: | They propose a method for exploring regions around individual points in a contextualized vector space . they use a static embedding to induce a "pseudoword" vector and masked prediction of a word . |
| Outcome: | The proposed method investigates the geometry of the contextualized space around individual instances of a word . it uses a static embedding to induce a contextualized "pseudoword" vector . |
Multilingual Supervision Improves Semantic Disambiguation of Adpositions (2025.coling-main)
Copied to clipboard
| Challenge: | a corpus-based cross-linguistic investigation into the lexical semantics of adpositions is conducted . a significant amount of ambiguity and flexibility in their meanings are present in a variety of languages . |
| Approach: | They conduct a corpus-based corpus analysis of adpositions using SNACS . they find distributional differences in a language's adequacy and disambiguation performance . |
| Outcome: | The proposed framework is suited for analyzing adpositions across languages . it provides a framework for a wide-coverage corpus annotation of high-level senses . |
Abstract Meaning Representation of Constructions: The More We Include, the Better the Representation (L18-1)
Copied to clipboard
Claire Bonial, Bianca Badarau, Kira Griffitt, Ulf Hermjakob, Kevin Knight, Tim O’Gorman, Martha Palmer, Nathan Schneider
| Challenge: | Abstract Meaning Representation (AMR) uses a flexible pattern or template of multiple lexical items to provide semantic representation of certain constructions. |
| Approach: | They propose to expand the AMR project's lexicon of predicate senses to include entries for a growing set of constructions. |
| Outcome: | The proposed approach provides coverage for the annotation of certain types of constructions. |
Discourse Coherence: Concurrent Explicit and Implicit Relations (P18-1)
Copied to clipboard
| Challenge: | Existing studies on discourse coherence show that multiple discourse relations can be operative between two segments for reasons not predicted by the literature. |
| Approach: | They show that people endorse seemingly divergent conjunctions to express the link they see between two segments in a crowdsourced conjunctioninsertion experiment. |
| Outcome: | The proposed results can inform future work on discourse coherence and lead to higher levels of performance in discourse parsing. |
J-SNACS: Adposition and Case Supersenses for Japanese Joshi (2024.lrec-main)
Copied to clipboard
| Challenge: | adpositions are used to mark a variety of semantic relations in languages such as English and Korean. |
| Approach: | They propose a Japanese extension of the SNACS framework for annotating adpositions in corpora from several languages. |
| Outcome: | The proposed framework captures similarities not seen in multilingual embedding space. |
Supervised Grapheme-to-Phoneme Conversion of Orthographic Schwas in Hindi and Punjabi (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods to predict schwa deletion in Hindi are based on prosodic or phonetic analysis. |
| Approach: | They propose to use Hindi grapheme-to-phoneme (G2P) conversion to predict whether a schwa represented in the orthography is pronounced or unpronounced (deleted). |
| Outcome: | The proposed model outperforms existing models on a newly-compiled pronunciation lexicon extracted from various online dictionaries. |
(Re)construing Meaning in NLP (2020.acl-main)
Copied to clipboard
| Challenge: | a new paper explores the role of linguistic choices in interpreting information in natural language . linguistic choice is a way of expressing information, but it is not the meaning of an utterance, authors argue . |
| Approach: | They propose to define construal as a way of conceptualizing or construing information . they propose to use this concept to develop theoretical and practical work in NLP . |
| Outcome: | The proposed study explores how construal can inform theoretical and practical work in NLP. |
CuRIAM: Corpus Re Interpretation and Metalanguage in U.S. Supreme Court Opinions (2024.lrec-main)
Copied to clipboard
| Challenge: | judicial opinions use language to comment on or draw attention to other language . a recent case involving a federal anti-discrimination law requires that justices determine the meaning of just one word or phrase in a specific context. |
| Approach: | They identify 9 categories prominent in metalinguistic discussions, including key terms, definitions, and different kinds of sources. |
| Outcome: | The results show that the annotated concepts are well-defined and frequent, and that they differ between majority, concurring, and dissenting opinions. |
Apertus: Democratizing Open and Compliant LLMs for Global Language Environments (2026.acl-long)
Copied to clipboard
Alejandro Hernández-Cano, Alexander Hägele, Allen Hao Huang, Angelika Romanou, Antoni-Joan Solergibert, Barna Pásztor, Bettina Messmer, Dhia Garbaya, Eduard Frank Ďurech, Ido Hakimi, Juan Garcia Giraldo, Mete Ismayilzada, Negar Foroutan, Skander Moalla, Tiancheng Chen, Vinko Sabolčec, Yixuan Xu, Michael Aerni, Badr AlKhamissi, Inés Altemir Marinas, Mohammad Hossein Amani, Matin Ansaripour, Ilia Badanin, Harold Benoit, Emanuela Boros, Nicholas John Browning, Fabian Bösch, Maximilian Böther, Niklas Canova, Camille Challier, Clément Charmillot, Jonathan Coles, Jan Milan Deriu, Arnout Devos, Lukas Drescher, Daniil Dzenhaliou, Maud Ehrmann, Dongyang Fan, Simin Fan, Silin Gao, Miguel Gila, María Grandury, Diba Hashemi, Alexander Miserlis Hoyle, Jiaming Jiang, Mark Klein, Andrei Kucharavy, Anastasiia Kucherenko, Frederike Lübeck, Roman Machacek, Theofilos Ioannis Manitaras, Andreas Marfurt, Kyle Matoba, Simon Matrenok, Henrique Mendonça, Fawzi Roberto Mohamed, Syrielle Montariol, Luca Mouchel, Sven Najem-Meyer, Jingwei Ni, Gennaro Oliva, Matteo Pagliardini, Elia Palme, Andrei Panferov, Léo Paoletti, Marco Passerini, Ivan Pavlov, Auguste Poiroux, Kaustubh Ponkshe, Nathan Ranchin, Javier Rando, Mathieu Sauser, Jakhongir Saydaliev, Mukhammadali Sayfiddinov, Marian Schneider, Stefano Schuppli, Marco Scialanga, Andrei Semenov, Kumar Shridhar, Raghav Singhal, Anna Sotnikova, Alexander Sternfeld, Ayush Kumar Tarun, Paul Teiletche, Jannis Vamvas, Xiaozhe Yao, Hao Zhao, Alexander Ilic, Ana Klimovic, Andreas Krause, Caglar Gulcehre, David Rosenthal, Elliott Ash, Florian Tramèr, Joost VandeVondele, Livio Veraldi, Martin Rajman, Thomas C. Schulthess, Torsten Hoefler, Antoine Bosselut, Martin Jaggi, Imanol Schlag
| Challenge: | Apertus is a fully open suite of large language models (LLMs) designed to address responsibility shortcomings in today’s open model ecosystem, namely data responsibility and global representation. |
| Approach: | They propose to release a fully open suite of large language models (LLMs) that address data responsibility and global representation shortcomings in today’s open model ecosystem. |
| Outcome: | The proposed model is pretrained on openly available data and suppresses verbatim recall of data while retaining task performance. |
Linguistic Frameworks Go Toe-to-Toe at Neuro-Symbolic Language Modeling (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing models of language understanding are based on explicit representations of hierarchical structure, but there are good reasons to doubt that they can be said to understand language in any meaningful way. |
| Approach: | They examine whether syntactic and semantic graph representations can complement and improve neural language modeling. |
| Outcome: | The proposed model outperforms pretrained models on English WSJ in perplexity and other metrics. |
A Corpus of Adpositional Supersenses for Mandarin Chinese (2020.lrec-1)
Copied to clipboard
| Challenge: | Adpositions are frequent markers of semantic relations, but they are highly ambiguous and vary significantly from language to language. |
| Approach: | They propose to annotate Chinese adpositions in a corpus with all aforementioned supersenses . they adapt a framework that defined a set of supersens according to ostensibly language-independent criteria . |
| Outcome: | The proposed corpus is the first to be broadly annotated with adposition semantics in Chinese . it shows that the supersense categories are well-suited to Chinese adepositions despite syntactic differences from English . |
Lost in Translationese? Reducing Translation Effect Using Abstract Meaning Representation (2024.eacl-long)
Copied to clipboard
| Challenge: | Abstract Meaning Representation (AMR) can be used to reduce translationese in text . if translationeses are not addressed in training or test sets, evaluation scores can be overinflated . |
| Approach: | They propose to use Abstract Meaning Representation (AMR) to reduce translationese in translated texts. |
| Outcome: | The proposed approach outperforms other methods based on machine translation and paraphrase generation. |
A Structured Syntax-Semantics Interface for English-AMR Alignment (N18-1)
Copied to clipboard
| Challenge: | Abstract Meaning Representation (AMR) annotations do not require explicit mapping between elements of an AMR and the corresponding elements of the sentence that evoke them. |
| Approach: | They devised an expressive framework to align AMR graphs to dependency graphs . their framework explains how 97% of AMR edges are evoked by words or syntax . |
| Outcome: | The proposed framework explains how 97% of AMR edges are evoked by words or syntax. |
Parsing Tweets into Universal Dependencies (N18-1)
Copied to clipboard
| Challenge: | a new tweet treebank for English is designed to analyze tweets with universal dependencies (UD). |
| Approach: | They extend the universal dependencies guidelines to include special constructions in tweets that affect tokenization, part-of-speech tagging, and labeled dependencies. |
| Outcome: | The proposed method outperforms state-of-the-art parsers on other treebanks in accuracy and speed. |
Supertagging the Long Tail with Tree-Structured Decoding of Complex Categories (2021.tacl-1)
Copied to clipboard
| Challenge: | Combinatory Categorial Grammar (CCG) parsers operate as a pipeline with a large search space of complex 'supertags' . |
| Approach: | They propose to use CCG supertags to generate CCG categories that have never been seen in training and to use tree-structured prediction to account for their internal structure. |
| Outcome: | The proposed model recovers a fraction of the long-tail supertags while approximating the state of the art in overall tag accuracy with fewer parameters. |
Modeling Nonnative Sentence Processing with L2 Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Experimental results show that while all of the LMs’ word surprisals improve prediction of L2 reading times, there is no reliable effect of the choice of L1’s L1. |
| Approach: | They pretrain GPT2 on 6 different first languages, followed by English as the second language (L2). |
| Outcome: | The pretraining of L1 improves prediction of L2 reading times, but there is no reliable effect of the pretraining L1 on the model's performance on English speakers. |