pub.chive.eprint.submission
Samples
210 randomly sampled records from the AT Protocol firehose
pub.chive.eprint.submission (100 samples)
{
"$type": "pub.chive.eprint.submission",
"abstract": [
{
"$type": "pub.chive.richtext.defs#textItem",
"content": "Some words are harder to learn than others. For instance, action verbs like run and hit are learned earlier than propositional attitude verbs like think and want. One reason think and want might be learned later is that, whereas we can see and hear running and hitting, we can’t see or hear thinking and wanting. Children nevertheless learn these verbs, so a route other than the senses must exist. There is mounting evidence that this route involves, in large part, inferences based on the distribution of syntactic contexts a propositional attitude verb occurs in—a process known as syntactic bootstrapping. This fact makes the domain of propositional attitude verbs a prime proving ground for models of syntactic bootstrapping. With this in mind, this dissertation has two goals: on the one hand, it aims to construct a computational model of syntactic bootstrapping; on the other, it aims to use this model to investigate the limits on the amount of information about propositional attitude verb meanings that can be gleaned from syntactic distributions. I show throughout the dissertation that these goals are mutually supportive. In Chapter 1, I set out the main problems that drive the investigation. In Chapters 2 and 3, I use both psycholinguistic experiments and computational modeling to establish that there is a significant amount of semantic information carried in both participants’ syntactic acceptability judgments and syntactic distributions in corpora. To investigate the nature of this relationship I develop two computational models: (i) a nonnegative model of (semantic-to-syntactic) projection and (ii) a nonnegative model of syntactic bootstrapping. In Chapter 4, I use a novel variant of the Human Simulation Paradigm to show that the information carried in syntactic distribution is actually utilized by (simulated) learners. In Chapter 5, I present a proposal for how to solve a standing problem in how syntactic bootstrapping accounts for certain kinds of cross-linguistic variation. And in Chapter 6, I conclude with some future directions for this work.",
"type": "text"
}
],
"abstractPlainText": "Some words are harder to learn than others. For instance, action verbs like run and hit are learned earlier than propositional attitude verbs like think and want. One reason think and want might be learned later is that, whereas we can see and hear running and hitting, we can’t see or hear thinking and wanting. Children nevertheless learn these verbs, so a route other than the senses must exist. There is mounting evidence that this route involves, in large part, inferences based on the distribution of syntactic contexts a propositional attitude verb occurs in—a process known as syntactic bootstrapping. This fact makes the domain of propositional attitude verbs a prime proving ground for models of syntactic bootstrapping. With this in mind, this dissertation has two goals: on the one hand, it aims to construct a computational model of syntactic bootstrapping; on the other, it aims to use this model to investigate the limits on the amount of information about propositional attitude verb meanings that can be gleaned from syntactic distributions. I show throughout the dissertation that these goals are mutually supportive. In Chapter 1, I set out the main problems that drive the investigation. In Chapters 2 and 3, I use both psycholinguistic experiments and computational modeling to establish that there is a significant amount of semantic information carried in both participants’ syntactic acceptability judgments and syntactic distributions in corpora. To investigate the nature of this relationship I develop two computational models: (i) a nonnegative model of (semantic-to-syntactic) projection and (ii) a nonnegative model of syntactic bootstrapping. In Chapter 4, I use a novel variant of the Human Simulation Paradigm to show that the information carried in syntactic distribution is actually utilized by (simulated) learners. In Chapter 5, I present a proposal for how to solve a standing problem in how syntactic bootstrapping accounts for certain kinds of cross-linguistic variation. And in Chapter 6, I conclude with some future directions for this work.",
"authors": [
{
"affiliations": [
{
"children": [
{
"name": "Department of Linguistics"
}
],
"name": "University of Maryland, College Park",
"rorId": "https://ror.org/047s2c258"
}
],
"did": "did:plc:34mbm5v3umztwvvgnttvcz6e",
"handle": "aaronstevenwhite.io",
"name": "Aaron Steven White",
"orcid": "0000-0003-0057-9246",
"order": 1
}
],
"createdAt": "2015-01-01T12:00:00.000Z",
"document": {
"$type": "blob",
"mimeType": "application/pdf",
"ref": {
"$link": "bafkreihs32e6jwnyapbdlej7ykxubjfyl7kh6xx26e2u36c6lumiealoj4"
},
"size": 1919120
},
"documentFormatSlug": "pdf",
"documentFormatUri": "at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/3f96bd05-e848-5465-aca9-0a959f778396",
"fieldUris": [
"at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/5bc44344-ffaf-5109-a8d3-b085e1d59a67",
"at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/9cfe6371-0a2c-5aee-8302-f7b170b0d2d8",
"at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/57ad99fd-8f7c-58f9-b9eb-f8f644290336",
"at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/6fe7359e-8b24-5fce-8bd4-0225a10c899e"
],
"keywords": [
"Language Acquisition",
"Semantic Theory",
"Computational Psycholinguistics"
],
"licenseSlug": "all-rights-reserved",
"licenseUri": "at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/435ddb5c-9517-51f1-bedd-3d6968ba4678",
"paperTypeSlug": "thesis",
"paperTypeUri": "at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/c1cbeda1-24d1-56b3-9fa0-830bf913b339",
"publicationStatusSlug": "published",
"publicationStatusUri": "at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/3262e011-81ca-52f3-8b68-7d4c012ef9b7",
"publishedVersion": {
"doi": "10.13016/M2X938",
"journal": "University of Maryland, College Park",
"publishedAt": "2015-01-01T12:00:00.000Z",
"publisher": "Digital Repository at the University of Maryland"
},
"schemaRevision": 3,
"submittedBy": "did:plc:34mbm5v3umztwvvgnttvcz6e",
"title": "Information and Incrementality in Syntactic Bootstrapping",
"version": {
"major": 1,
"minor": 0,
"patch": 0
}
}did:plc:34mbm5v3umztwvvgnttvcz6e | at://did:plc:34mbm5v3umztwvvgnttvcz6e/pub.chive.eprint.submission/3mufmda46eg2t
pub.chive.richtext.defs (nested within pub.chive.eprint.submission) (100 samples)
{
"$type": "pub.chive.eprint.submission",
"abstract": [
{
"$type": "pub.chive.richtext.defs#textItem",
"content": "While numerous attempts have been made to jointly parse syntax and semantics, high performance in one domain typically comes at the price of performance in the other. This trade-off contradicts the large body of research focusing on the rich interactions at the syntax–semantics interface. We explore multiple model architectures that allow us to exploit the rich syntactic and semantic annotations contained in the Universal Decompositional Semantics (UDS) dataset, jointly parsing Universal Dependencies and UDS to obtain state-of-the-art results in both formalisms. We analyze the behavior of a joint model of syntax and semantics, finding patterns supported by linguistic theory at the syntax–semantics interface. We then investigate to what degree joint modeling generalizes to a multilingual setting, where we find similar trends across 8 languages.",
"type": "text"
}
],
"abstractPlainText": "While numerous attempts have been made to jointly parse syntax and semantics, high performance in one domain typically comes at the price of performance in the other. This trade-off contradicts the large body of research focusing on the rich interactions at the syntax–semantics interface. We explore multiple model architectures that allow us to exploit the rich syntactic and semantic annotations contained in the Universal Decompositional Semantics (UDS) dataset, jointly parsing Universal Dependencies and UDS to obtain state-of-the-art results in both formalisms. We analyze the behavior of a joint model of syntax and semantics, finding patterns supported by linguistic theory at the syntax–semantics interface. We then investigate to what degree joint modeling generalizes to a multilingual setting, where we find similar trends across 8 languages.",
"authors": [
{
"affiliations": [
{
"name": "Johns Hopkins University",
"rorId": "https://ror.org/00za53h95"
}
],
"did": "did:plc:drvtnoosdjozr7dmv5a4stwt",
"handle": "esteng.bsky.social",
"name": "Elias Stengel-Eskin",
"order": 1
},
{
"affiliations": [
{
"name": "Johns Hopkins University",
"rorId": "https://ror.org/00za53h95"
}
],
"name": "Kenton Murray",
"order": 2
},
{
"affiliations": [
{
"name": "Microsoft Research"
}
],
"name": "Sheng Zhang",
"order": 3
},
{
"affiliations": [
{
"name": "University of Rochester",
"rorId": "https://ror.org/022kthw22"
}
],
"did": "did:plc:34mbm5v3umztwvvgnttvcz6e",
"handle": "aaronstevenwhite.io",
"name": "Aaron Steven White",
"orcid": "0000-0003-0057-9246",
"order": 4
},
{
"affiliations": [
{
"name": "Johns Hopkins University",
"rorId": "https://ror.org/00za53h95"
}
],
"name": "Benjamin Van Durme",
"order": 5
}
],
"createdAt": "2021-08-02T12:00:00.000Z",
"document": {
"$type": "blob",
"mimeType": "application/pdf",
"ref": {
"$link": "bafkreicmuomvqbhlcbd7i66tqbkxjbdlpubqidhzg4exhtmu6e44aqawtm"
},
"size": 749974
},
"documentFormatSlug": "pdf",
"documentFormatUri": "at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/3f96bd05-e848-5465-aca9-0a959f778396",
"externalIds": {
"arxivId": "2104.05696"
},
"fieldUris": [
"at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/6fe7359e-8b24-5fce-8bd4-0225a10c899e",
"at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/c6ed82a1-7702-5773-92c5-4d25a9336c92",
"at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/a1a96689-b027-53d4-a546-6da7716abfd8"
],
"keywords": [
"Syntactic & Semantic Parsing",
"Information Extraction"
],
"licenseSlug": "CC-BY-4.0",
"licenseUri": "at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/fc58b045-e186-5081-b7eb-abc5c47ea8a3",
"paperTypeSlug": "original-research",
"paperTypeUri": "at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/2d0024ca-0097-5f87-b031-3fa14c950c92",
"publicationStatusSlug": "published",
"publicationStatusUri": "at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/3262e011-81ca-52f3-8b68-7d4c012ef9b7",
"publishedVersion": {
"accessType": "open_access",
"doi": "10.1162/tacl_a_00396",
"journal": "Transactions of the Association for Computational Linguistics",
"journalIssn": "2307-387X",
"pages": "756-773",
"publishedAt": "2021-08-02T12:00:00.000Z",
"url": "https://doi.org/10.1162/tacl_a_00396",
"volume": "9"
},
"repositories": {
"code": [
{
"label": "code",
"platformSlug": "github",
"url": "https://github.com/esteng/miso_uds"
}
]
},
"schemaRevision": 3,
"submittedBy": "did:plc:34mbm5v3umztwvvgnttvcz6e",
"title": "Joint Universal Syntactic and Semantic Parsing",
"version": {
"major": 1,
"minor": 0,
"patch": 0
}
}did:plc:34mbm5v3umztwvvgnttvcz6e | at://did:plc:34mbm5v3umztwvvgnttvcz6e/pub.chive.eprint.submission/3mufmbf4zzv2a
pub.chive.richtext.facets (nested within pub.chive.eprint.submission) (8 samples)
{
"$type": "pub.chive.eprint.submission",
"abstract": [
{
"$type": "pub.chive.richtext.defs#textItem",
"content": "We introduce event-keyed summarization (EKS), a novel task that marries traditional summarization and document-level event extraction, with the goal of generating a contextualized summary for a specific event, given a document and an extracted event structure. We introduce a dataset for this task, MUCSUM, consisting of summaries of all events in the classic MUC-4 dataset, along with a set of baselines that comprises both pretrained LM standards in the summarization literature, as well as larger frontier models. We show that ablations that reduce EKS to traditional summarization or structure-to-text yield inferior summaries of target events and that MUCSUM is a robust benchmark for this task. Lastly, we conduct a human evaluation of both reference and model summaries, and provide some detailed analysis of the results.",
"facets": [
{
"features": [
{
"$type": "pub.chive.richtext.facets#italic"
}
],
"index": {
"byteEnd": 38,
"byteStart": 13
}
}
],
"type": "text"
}
],
"abstractPlainText": "We introduce event-keyed summarization (EKS), a novel task that marries traditional summarization and document-level event extraction, with the goal of generating a contextualized summary for a specific event, given a document and an extracted event structure. We introduce a dataset for this task, MUCSUM, consisting of summaries of all events in the classic MUC-4 dataset, along with a set of baselines that comprises both pretrained LM standards in the summarization literature, as well as larger frontier models. We show that ablations that reduce EKS to traditional summarization or structure-to-text yield inferior summaries of target events and that MUCSUM is a robust benchmark for this task. Lastly, we conduct a human evaluation of both reference and model summaries, and provide some detailed analysis of the results.",
"authors": [
{
"name": "William Gantt",
"order": 1
},
{
"did": "did:plc:sc3nswzryepptw5vdn2aq3uf",
"handle": "alexmartin314.bsky.social",
"name": "Alexander Martin",
"order": 2
},
{
"name": "Pavlo Kuchmiichuk",
"order": 3
},
{
"affiliations": [
{
"children": [
{
"name": "Department of Linguistics"
}
],
"name": "University of Rochester",
"rorId": "https://ror.org/022kthw22"
}
],
"did": "did:plc:34mbm5v3umztwvvgnttvcz6e",
"handle": "aaronstevenwhite.io",
"name": "Aaron Steven White",
"orcid": "0000-0003-0057-9246",
"order": 4
}
],
"conferencePresentation": {
"conferenceLocation": "Miami, Florida, USA",
"conferenceName": "Findings of the Association for Computational Linguistics: EMNLP 2024"
},
"createdAt": "2024-11-01T00:00:00.000Z",
"document": {
"$type": "blob",
"mimeType": "application/pdf",
"ref": {
"$link": "bafkreid47tx753rb5vtjttvaor6tgw7pkx2y2sijl4n2ycz57bnsem5i6y"
},
"size": 348268
},
"documentFormatSlug": "pdf",
"documentFormatUri": "at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/3f96bd05-e848-5465-aca9-0a959f778396",
"fieldUris": [
"at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/a1a96689-b027-53d4-a546-6da7716abfd8",
"at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/f3482b65-fadc-5464-a84f-9bfd6168b291",
"at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/e5fe0691-fa46-5094-b6bc-a31763d7b94a"
],
"keywords": [
"Information Extraction",
"Natural Language Understanding",
"Datasets & Evaluation"
],
"licenseSlug": "CC-BY-4.0",
"licenseUri": "at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/fc58b045-e186-5081-b7eb-abc5c47ea8a3",
"paperTypeSlug": "conference-paper",
"paperTypeUri": "at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/2ab4132d-8c17-59a6-9d15-8317e01784d4",
"publicationStatusSlug": "published",
"publicationStatusUri": "at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/3262e011-81ca-52f3-8b68-7d4c012ef9b7",
"publishedVersion": {
"accessType": "open_access",
"journal": "Findings of the Association for Computational Linguistics: EMNLP 2024",
"pages": "7333–7345",
"publishedAt": "2024-11-01T00:00:00.000Z",
"publisher": "Association for Computational Linguistics",
"url": "https://aclanthology.org/2024.findings-emnlp.431"
},
"repositories": {
"data": [
{
"label": "data",
"platformSlug": "other",
"url": "https://github.com/wgantt/eks"
}
]
},
"schemaRevision": 3,
"submittedBy": "did:plc:34mbm5v3umztwvvgnttvcz6e",
"title": "Event-Keyed Summarization",
"version": {
"major": 1,
"minor": 0,
"patch": 0
}
}did:plc:34mbm5v3umztwvvgnttvcz6e | at://did:plc:34mbm5v3umztwvvgnttvcz6e/pub.chive.eprint.submission/3mufmarej2q2r
pub.chive.richtext.text (nested within pub.chive.eprint.submission) (2 samples)
{
"$type": "pub.chive.eprint.submission",
"abstract": [
{
"$type": "pub.chive.richtext.text",
"content": "A throwaway eprint used to verify that records from other atproto services attach to a paper and render on it. Safe to delete.",
"type": "text"
}
],
"authors": [
{
"did": "did:plc:34mbm5v3umztwvvgnttvcz6e",
"name": "Aaron Steven White",
"order": 1
}
],
"createdAt": "2026-09-04T20:46:45.493081Z",
"document": {
"$type": "blob",
"mimeType": "application/pdf",
"ref": {
"$link": "bafkreidnq2ogmxfudpim4jgg5oneuowmo47odk6zhaxjbgqn5y4qnywjfe"
},
"size": 404
},
"licenseSlug": "CC-BY-4.0",
"licenseUri": "at://did:plc:chive-governance/pub.chive.graph.node/fc58b045-e186-5081-b7eb-abc5c47ea8a3",
"repositories": {
"code": [
{
"label": "Chive on GitHub",
"platformSlug": "github",
"url": "https://github.com/chive-pub/chive"
},
{
"label": "Probe repo on Tangled",
"platformSlug": "tangled",
"recordUri": "at://did:plc:34mbm5v3umztwvvgnttvcz6e/sh.tangled.repo/interop-probe"
}
],
"data": [
{
"label": "MegaIntensionality",
"platformSlug": "other",
"url": "at://did:plc:y4ussuvobbph4mpieqiszqr6/pub.layers.catalog.collection/2c69416698e7bdd5b2ffc9f7"
}
]
},
"submittedBy": "did:plc:34mbm5v3umztwvvgnttvcz6e",
"title": "[TEST] Interop verification probe — safe to delete"
}did:plc:34mbm5v3umztwvvgnttvcz6e | at://did:plc:34mbm5v3umztwvvgnttvcz6e/pub.chive.eprint.submission/3muptixquo527