Searcharxiv⌕ Search

arXiv subjects

Nathan Schneider

Publications and source records attributed to Nathan Schneider.

At least 55 records · Page 3Linked to original sources
arXiv2021

Modular Politics: Toward a Governance Layer for Online Communities

Governance in online communities is an increasingly high-stakes challenge, and yet many basic features of offline governance legacies--juries, political parties, term limits, and formal debates, to name a few--are not in the feature-sets of the software most community platforms use. Drawing on the paradigm of Institutional Analysis and Development, this paper proposes a strategy for addressing this lapse by specifying basic features of a generalizable paradigm for online governance called Modular Politics. Whereas classical governance typologies tend to present a choice among wholesale ideologies, such as democracy or oligarchy, Modular Politics would enable platform operators and their users to build bottom-up governance processes from computational components that are modular and composable, highly versatile in their expressiveness, portable from one context to another, and interoperable across platforms. This kind of approach could implement pre-digital governance systems as well as accelerate innovation in uniquely digital techniques. As diverse communities share and connect their components and data, governance could occur through a ubiquitous network layer. To that end, this paper proposes the development of an open standard for networked governance.

cs.CY↗
arXiv2021

Hindi-Urdu Adposition and Case Supersenses v1.0

These are the guidelines for the application of SNACS (Semantic Network of Adposition and Case Supersenses; Schneider et al. 2018) to Modern Standard Hindi of Delhi. SNACS is an inventory of 50 supersenses (semantic labels) for labelling the use of adpositions and case markers with respect to both lexical-semantic function and relation to the underlying context. The English guidelines (Schneider et al., 2020) were used as a model for this document. Besides the case system, Hindi has an extremely rich adpositional system built on the oblique genitive, with productive incorporation of loanwords even in present-day Hinglish. This document is aligned with version 2.5 of the English guidelines.

cs.CL↗
arXiv2021

Effective Voice: Beyond Exit and Affect in Online Communities

Online communities provide ample opportunities for user self-expression but generally lack the means for average users to exercise direct control over community policies. This paper sets out to identify a set of strategies and techniques through which the voices of participants might be better heard through defined mechanisms for institutional governance. Drawing on Albert O. Hirschman's distinction between "exit" and "voice" in institutional life, it introduces a further distinction between two kinds of participation: effective voice, as opposed to the far more widespread practices of affective voice. Effective voice is a form of individual or collective speech that brings about a binding effect according to transparent processes. Platform developers and researchers might explore this neglected form of voice by introducing mechanisms for authority and accountability, collective action, and community evolution.

cs.CY↗
arXiv2020

UCCA's Foundational Layer: Annotation Guidelines v2.1

This is the annotation manual for Universal Conceptual Cognitive Annotation (UCCA; Abend and Rappoport, 2013), specifically the Foundational Layer. UCCA is a graph-based semantic annotation scheme based on typological linguistic principles. It has been applied to several languages; for ease of exposition these guidelines give examples mainly in English. New annotators may wish to start with the tutorial on the UCCA framework (Abend et al., 2020). Further resources are available at the project homepage: https://universalconceptualcognitiveannotation.github.io

cs.CL↗
arXiv2020

Supertagging the Long Tail with Tree-Structured Decoding of Complex Categories

Although current CCG supertaggers achieve high accuracy on the standard WSJ test set, few systems make use of the categories' internal structure that will drive the syntactic derivation during parsing. The tagset is traditionally truncated, discarding the many rare and complex category types in the long tail. However, supertags are themselves trees. Rather than give up on rare tags, we investigate constructive models that account for their internal structure, including novel methods for tree-structured prediction. Our best tagger is capable of recovering a sizeable fraction of the long-tail supertags and even generates CCG categories that have never been seen in training, while approximating the prior state of the art in overall tag accuracy with fewer parameters. We further investigate how well different approaches generalize to out-of-domain evaluation sets.

cs.CL↗
arXiv2020

A Human Evaluation of AMR-to-English Generation Systems

Most current state-of-the art systems for generating English text from Abstract Meaning Representation (AMR) have been evaluated only using automated metrics, such as BLEU, which are known to be problematic for natural language generation. In this work, we present the results of a new human evaluation which collects fluency and adequacy scores, as well as categorization of error types, for several recent AMR generation systems. We discuss the relative quality of these systems and how our results compare to those of automatic metrics, finding that while the metrics are mostly successful in ranking systems overall, collecting human judgments allows for more nuanced comparisons. We also analyze common errors made by these systems.

cs.CL↗
arXiv2020

Comparison by Conversion: Reverse-Engineering UCCA from Syntax and Lexical Semantics

Building robust natural language understanding systems will require a clear characterization of whether and how various linguistic meaning representations complement each other. To perform a systematic comparative analysis, we evaluate the mapping between meaning representations from different frameworks using two complementary methods: (i) a rule-based converter, and (ii) a supervised delexicalized parser that parses to one framework using only information from the other as features. We apply these methods to convert the STREUSLE corpus (with syntactic and lexical semantic annotations) to UCCA (a graph-structured full-sentence meaning representation). Both methods yield surprisingly accurate target representations, close to fully supervised UCCA parser quality---indicating that UCCA annotations are partially redundant with STREUSLE annotations. Despite this substantial convergence between frameworks, we find several important areas of divergence.

cs.CL↗
arXiv2020

(Re)construing Meaning in NLP

Human speakers have an extensive toolkit of ways to express themselves. In this paper, we engage with an idea largely absent from discussions of meaning in natural language understanding--namely, that the way something is expressed reflects different ways of conceptualizing or construing the information being conveyed. We first define this phenomenon more precisely, drawing on considerable prior work in theoretical cognitive semantics and psycholinguistics. We then survey some dimensions of construed meaning and show how insights from construal could inform theoretical and practical work in NLP.

cs.CL↗
arXiv2020

Supervised Grapheme-to-Phoneme Conversion of Orthographic Schwas in Hindi and Punjabi

Hindi grapheme-to-phoneme (G2P) conversion is mostly trivial, with one exception: whether a schwa represented in the orthography is pronounced or unpronounced (deleted). Previous work has attempted to predict schwa deletion in a rule-based fashion using prosodic or phonetic analysis. We present the first statistical schwa deletion classifier for Hindi, which relies solely on the orthography as the input and outperforms previous approaches. We trained our model on a newly-compiled pronunciation lexicon extracted from various online dictionaries. Our best Hindi model achieves state of the art performance, and also achieves good performance on a closely related language, Punjabi, without modification.

cs.CL↗
arXiv2020

A Corpus of Adpositional Supersenses for Mandarin Chinese

Adpositions are frequent markers of semantic relations, but they are highly ambiguous and vary significantly from language to language. Moreover, there is a dearth of annotated corpora for investigating the cross-linguistic variation of adposition semantics, or for building multilingual disambiguation systems. This paper presents a corpus in which all adpositions have been semantically annotated in Mandarin Chinese; to the best of our knowledge, this is the first Chinese corpus to be broadly annotated with adposition semantics. Our approach adapts a framework that defined a general set of supersenses according to ostensibly language-independent semantic criteria, though its development focused primarily on English prepositions (Schneider et al., 2018). We find that the supersense categories are well-suited to Chinese adpositions despite syntactic differences from English. On a Mandarin translation of The Little Prince, we achieve high inter-annotator agreement and analyze semantic correspondences of adposition tokens in bitext.

cs.DL↗
arXiv2019

Made for Each Other: Broad-coverage Semantic Structures Meet Preposition Supersenses

Universal Conceptual Cognitive Annotation (UCCA; Abend and Rappoport, 2013) is a typologically-informed, broad-coverage semantic annotation scheme that describes coarse-grained predicate-argument structure but currently lacks semantic roles. We argue that lexicon-free annotation of the semantic roles marked by prepositions, as formulated by Schneider et al. (2018b), is complementary and suitable for integration within UCCA. We show empirically for English that the schemes, though annotated independently, are compatible and can be combined in a single semantic graph. A comparison of several approaches to parsing the integrated representation lays the groundwork for future research on this task.

cs.CL↗
arXiv2019

Semantically Constrained Multilayer Annotation: The Case of Coreference

We propose a coreference annotation scheme as a layer on top of the Universal Conceptual Cognitive Annotation foundational layer, treating units in predicate-argument structure as a basis for entity and event mentions. We argue that this allows coreference annotators to sidestep some of the challenges faced in other schemes, which do not enforce consistency with predicate-argument structure and vary widely in what kinds of mentions they annotate and how. The proposed approach is examined with a pilot annotation study and compared with annotations from other schemes.

cs.CL↗
arXiv2019

An Improved Approach for Semantic Graph Composition with CCG

This paper builds on previous work using Combinatory Categorial Grammar (CCG) to derive a transparent syntax-semantics interface for Abstract Meaning Representation (AMR) parsing. We define new semantics for the CCG combinators that is better suited to deriving AMR graphs. In particular, we define relation-wise alternatives for the application and composition combinators: these require that the two constituents being combined overlap in one AMR relation. We also provide a new semantics for type raising, which is necessary for certain constructions. Using these mechanisms, we suggest an analysis of eventive nouns, which present a challenge for deriving AMR graphs. Our theoretical analysis will facilitate future work on robust and transparent AMR parsing using CCG.

cs.CL↗
arXiv2018

Adpositional Supersenses for Mandarin Chinese

This study adapts Semantic Network of Adposition and Case Supersenses (SNACS) annotation to Mandarin Chinese and demonstrates that the same supersense categories are appropriate for Chinese adposition semantics. We annotated 15 chapters of The Little Prince, with high interannotator agreement. The parallel corpus gives insight into differences in construal between the two languages' adpositions, namely a number of construals that are frequent in Chinese but rare or unattested in the English corpus. The annotated corpus can further support automatic disambiguation of adpositions in Chinese, and the common inventory of supersenses between the two languages can potentially serve cross-linguistic tasks such as machine translation.

cs.CL↗
arXiv2018

Comprehensive Supersense Disambiguation of English Prepositions and Possessives

Semantic relations are often signaled with prepositional or possessive marking--but extreme polysemy bedevils their analysis and automatic interpretation. We introduce a new annotation scheme, corpus, and task for the disambiguation of prepositions and possessives in English. Unlike previous approaches, our annotations are comprehensive with respect to types and tokens of these markers; use broadly applicable supersense classes rather than fine-grained dictionary definitions; unite prepositions and possessives under the same class inventory; and distinguish between a marker's lexical contribution and the role it marks in the context of a predicate or scene. Strong interannotator agreement rates, as well as encouraging disambiguation results with established supervised methods, speak to the viability of the scheme and task.

cs.CL↗
arXiv2018

Parsing Tweets into Universal Dependencies

We study the problem of analyzing tweets with Universal Dependencies. We extend the UD guidelines to cover special constructions in tweets that affect tokenization, part-of-speech tagging, and labeled dependencies. Using the extended guidelines, we create a new tweet treebank for English (Tweebank v2) that is four times larger than the (unlabeled) Tweebank v1 introduced by Kong et al. (2014). We characterize the disagreements between our annotators and show that it is challenging to deliver consistent annotation due to ambiguity in understanding and explaining tweets. Nonetheless, using the new treebank, we build a pipeline system to parse raw tweets into UD. To overcome annotation noise without sacrificing computational efficiency, we propose a new method to distill an ensemble of 20 transition-based parsers into a single one. Our parser achieves an improvement of 2.2 in LAS over the un-ensembled baseline and outperforms parsers that are state-of-the-art on other treebanks in both accuracy and speed.

cs.CL↗
arXiv2017

Coping with Construals in Broad-Coverage Semantic Annotation of Adpositions

We consider the semantics of prepositions, revisiting a broad-coverage annotation scheme used for annotating all 4,250 preposition tokens in a 55,000 word corpus of English. Attempts to apply the scheme to adpositions and case markers in other languages, as well as some problematic cases in English, have led us to reconsider the assumption that a preposition's lexical contribution is equivalent to the role/relation that it mediates. Our proposal is to embrace the potential for construal in adposition use, expressing such phenomena directly at the token level to manage complexity and avoid sense proliferation. We suggest a framework to represent both the scene role and the adposition's lexical function so they can be annotated at scale---supporting automatic, statistical processing of domain-general language---and sketch how this representation would inform a constructional analysis.

cs.CL↗