Papers

@inproceedings{vashishtha_famus_2024,
    title = "{FAM}u{S}: Frames Across Multiple Sources",
    author = "Vashishtha, Siddharth  and
      Martin, Alexander  and
      Gantt, William  and
      Van Durme, Benjamin  and
      White, Aaron",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.naacl-long.457",
    doi = "10.18653/v1/2024.naacl-long.457",
    pages = "8250--8273",
    abstract = "Understanding event descriptions is a central aspect of language processing, but current approaches focus overwhelmingly on single sentences or documents. Aggregating information about an event across documents can offer a much richer understanding. To this end, we present FAMuS, a new corpus of Wikipedia passages that report on some event, paired with underlying, genre-diverse (non-Wikipedia) source articles for the same event. Events and (cross-sentence) arguments in both report and source are annotated against FrameNet, providing broad coverage of different event types. We present results on two key event understanding tasks enabled by FAMuS: source validation{---}determining whether a document is a valid source for a target report event{---}and cross-document argument extraction{---}full-document argument extraction for a target event from both its report and the correct source article.",
}

Copied!

@inproceedings{gantt_multimuc_2024,
  title = "{M}ulti{MUC}: Multilingual Template Filling on {MUC}-4",
  author = "Gantt, William  and
    Behzad, Shabnam  and
    An, Hannah  and
    Chen, Yunmo  and
    White, Aaron  and
    Van Durme, Benjamin  and
    Yarmohammadi, Mahsa",
  editor = "Graham, Yvette  and
    Purver, Matthew",
  booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)",
  month = mar,
  year = "2024",
  address = "St. Julian{'}s, Malta",
  publisher = "Association for Computational Linguistics",
  url = "https://aclanthology.org/2024.eacl-long.21",
  pages = "349--368",
  abstract = "We introduce MultiMUC, the first multilingual parallel corpus for template filling, comprising translations of the classic MUC-4 template filling benchmark into five languages: Arabic, Chinese, Farsi, Korean, and Russian. We obtain automatic translations from a strong multilingual machine translation system and manually project the original English annotations into each target language. For all languages, we also provide human translations for key portions of the dev and test splits. Finally, we present baselines on MultiMUC both with state-of-the-art template filling models for MUC-4 and with ChatGPT. We release MUC-4 and the supervised baselines to facilitate further work on document-level information extraction in multilingual settings.",
}

Copied!

@inproceedings{gantt_event_2024,
    title = "Event-Keyed Summarization",
    author = "Gantt, William  and
      Martin, Alexander  and
      Kuchmiichuk, Pavlo  and
      White, Aaron",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-emnlp.431",
    pages = "7333--7345",
    abstract = "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.",
}

Copied!

@inproceedings{gantt_event_2023,
  title = "On Event Individuation for Document-Level Information Extraction",
  author = "Gantt, William  and Kriz, Reno and Chen, Yunmo and Vashishtha, Siddharth and White, Aaron",
  editor = "Bouamor, Houda and Pino, Juan and Bali, Kalika",
  booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
  month = dec,
  year = "2023",
  address = "Singapore",
  publisher = "Association for Computational Linguistics",
  url = "https://aclanthology.org/2023.findings-emnlp.862.bib",
  doi = "10.18653/v1/2023.findings-emnlp.862",
  pages = "12938--12958"
}

Copied!

@inproceedings{chen_unified_2023,
  title = "A Unified View of Evaluation Metrics for Structured Prediction",
  author = "Chen, Yunmo  and Gantt, William and Chen, Tongfei  and White, Aaron  and Van Durme, Benjamin",
  editor = "Bouamor, Houda and Pino, Juan and Bali, Kalika",
  booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
  month = dec,
  year = "2023",
  address = "Singapore",
  publisher = "Association for Computational Linguistics",
  url = "https://aclanthology.org/2023.emnlp-main.795",
  doi = "10.18653/v1/2023.emnlp-main.795",
  pages = "12868--12882"
}

Copied!

@misc{barham_megawika_2023,
	title = "MegaWika: Millions of reports and their sources across 50 diverse languages", 
	author = "Samuel Barham and Orion Weller and Michelle Yuan and Kenton Murray and Mahsa Yarmohammadi and Zhengping Jiang and Siddharth Vashishtha and Alexander Martin and Anqi Liu and Aaron Steven White and Jordan Boyd-Graber and Benjamin Van Durme",
	year = "2023",
	eprint = "2307.07049",
	archivePrefix = "arXiv",
	primaryClass = "cs.CL"
}

Copied!

@inproceedings{chen_iterative_2023,
  title = "Iterative Document-level Information Extraction via Imitation Learning",
  author = "Chen, Yunmo  and
    Gantt, William  and
    Gu, Weiwei  and
    Chen, Tongfei  and
    White, Aaron  and
    Van Durme, Benjamin",
  booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics",
  month = may,
  year = "2023",
  address = "Dubrovnik, Croatia",
  publisher = "Association for Computational Linguistics",
  url = "https://aclanthology.org/2023.eacl-main.136.bib",
  pages = "1858--1874",
}

Copied!

@article{gantt_decomposing_2022,
	title = {Decomposing and {Recomposing} {Event} {Structure}},
	volume = {10},
	issn = {2307-387X},
	url = {https://doi.org/10.1162/tacl_a_00445},
	doi = {10.1162/tacl_a_00445},
	urldate = {2022-01-30},
	journal = {Transactions of the Association for Computational Linguistics},
	author = {Gantt, William and Glass, Lelia and White, Aaron Steven},
	month = jan,
	year = {2022},
	pages = {17--34},
}

Copied!

@article{kane_intensional_2022,
	title = {Intensional {Gaps}: {Relating} veridicality, factivity, doxasticity, bouleticity, and neg-raising},
	volume = {31},
	copyright = {Copyright (c) 2022 Benjamin Kane, Will Gantt, Aaron Steven White},
	issn = {2163-5951},
	shorttitle = {Intensional {Gaps}},
	url = {https://journals.linguisticsociety.org/proceedings/index.php/SALT/article/view/31.029},
	doi = {10.3765/salt.v31i0.5137},
	abstract = {We investigate which patterns of lexically triggered doxastic, bouletic, neg(ation)-raising, and veridicality inferences are (un)attested across clause-embedding verbs in English. To carry out this investigation, we use a multiview mixed effects mixture model to discover the inference patterns captured in three lexicon-scale inference judgment datasets: two existing datasets, MegaVeridicality and MegaNegRaising, which capture veridicality and neg-raising inferences across a wide swath of the English clause-embedding lexicon, and a new dataset, MegaIntensionality, which similarly captures doxastic and bouletic inferences. We focus in particular on inference patterns that are correlated with morphosyntactic distribution, as determined by how well those patterns predict the acceptability judgments in the MegaAcceptability dataset. We find that there are 15 such patterns attested. Similarities among these patterns suggest the possibility of underlying lexical semantic components that give rise to them. We use principal component analysis to discover these components and suggest generalizations that can be derived from them.},
	language = {en},
	urldate = {2022-01-13},
	journal = {Semantics and Linguistic Theory},
	author = {Kane, Benjamin and Gantt, Will and White, Aaron Steven},
	month = jan,
	year = {2022},
	pages = {570--605},
}

Copied!

@article{white_believing_2021,
	title = {On believing and hoping whether},
	volume = {14},
	issn = {1937-8912},
	url = {https://semprag.org/index.php/sp/article/view/sp.14.6},
	doi = {10.3765/sp.14.6},
	abstract = {Theories of clause selection that aim to explain the distribution of interrogative and declarative complement clauses often take as a starting point that predicates like think, believe, hope, and fear are incompatible with interrogative complements. After discussing experimental evidence against the generalizations on which these theories rest, I give corpus evidence that even the core data are faulty: think, believe, hope, and fear are in fact compatible with interrogative complements, suggesting that any theory predicting that they should not be must be jettisoned.},
	language = {en},
	number = {6},
	journal = {Semantics and Pragmatics},
	author = {White, Aaron Steven},
	month = jun,
	year = {2021},
	keywords = {clause embedding, interrogative, neg-raising, preferential, selection, veridical},
	pages = {1--18},
}

Copied!

@article{stengel-eskin_joint_2021,
    author = {Stengel-Eskin, Elias and Murray, Kenton and Zhang, Sheng and White, Aaron Steven and Van Durme, Benjamin},
    title = "{Joint Universal Syntactic and Semantic Parsing}",
    journal = {Transactions of the Association for Computational Linguistics},
    volume = {9},
    pages = {756-773},
    year = {2021},
    month = {08},
    issn = {2307-387X},
    doi = {10.1162/tacl_a_00396},
    url = {https://doi.org/10.1162/tacl\_a\_00396},
    eprint = {https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl\_a\_00396/1955190/tacl\_a\_00396.pdf},
}

Copied!

@article{kim_montague_2021,
	title = {Montague Grammar Induction},
	volume = {30},
	doi = {10.3765/salt.v30i0.4816},
	journal = {Semantics and Linguistic Theory},
	author = {Kim, Gene Louis and White, Aaron Steven},
	year = {2021},
	pages = {227--251}
}

Copied!

@inproceedings{yarmohammadi_everything_2021,
    title = "Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction",
    author = "Yarmohammadi, Mahsa  and
      Wu, Shijie  and
      Marone, Marc  and
      Xu, Haoran  and
      Ebner, Seth  and
      Qin, Guanghui  and
      Chen, Yunmo  and
      Guo, Jialiang  and
      Harman, Craig  and
      Murray, Kenton  and
      White, Aaron Steven  and
      Dredze, Mark  and
      Van Durme, Benjamin",
    editor = "Moens, Marie-Francine  and
      Huang, Xuanjing  and
      Specia, Lucia  and
      Yih, Scott Wen-tau",
    booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2021",
    address = "Online and Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.emnlp-main.149",
    doi = "10.18653/v1/2021.emnlp-main.149",
    pages = "1950--1967",
    abstract = "Zero-shot cross-lingual information extraction (IE) describes the construction of an IE model for some target language, given existing annotations exclusively in some other language, typically English. While the advance of pretrained multilingual encoders suggests an easy optimism of {``}train on English, run on any language{''}, we find through a thorough exploration and extension of techniques that a combination of approaches, both new and old, leads to better performance than any one cross-lingual strategy in particular. We explore techniques including data projection and self-training, and how different pretrained encoders impact them. We use English-to-Arabic IE as our initial example, demonstrating strong performance in this setting for event extraction, named entity recognition, part-of-speech tagging, and dependency parsing. We then apply data projection and self-training to three tasks across eight target languages. Because no single set of techniques performs the best across all tasks, we encourage practitioners to explore various configurations of the techniques described in this work when seeking to improve on zero-shot training.",
}

Copied!

@inproceedings{xia_lome_2021,
  title = "{LOME}: Large Ontology Multilingual Extraction",
  author = "Xia, Patrick  and
    Qin, Guanghui  and
    Vashishtha, Siddharth  and
    Chen, Yunmo  and
    Chen, Tongfei  and
    May, Chandler  and
    Harman, Craig  and
    Rawlins, Kyle  and
    White, Aaron Steven  and
    Van Durme, Benjamin",
  editor = "Gkatzia, Dimitra  and
    Seddah, Djam{\'e}",
  booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations",
  month = apr,
  year = "2021",
  address = "Online",
  publisher = "Association for Computational Linguistics",
  url = "https://aclanthology.org/2021.eacl-demos.19",
  doi = "10.18653/v1/2021.eacl-demos.19",
  pages = "149--159",
  abstract = "We present LOME, a system for performing multilingual information extraction. Given a text document as input, our core system identifies spans of textual entity and event mentions with a FrameNet (Baker et al., 1998) parser. It subsequently performs coreference resolution, fine-grained entity typing, and temporal relation prediction between events. By doing so, the system constructs an event and entity focused knowledge graph. We can further apply third-party modules for other types of annotation, like relation extraction. Our (multilingual) first-party modules either outperform or are competitive with the (monolingual) state-of-the-art. We achieve this through the use of multilingual encoders like XLM-R (Conneau et al., 2020) and leveraging multilingual training data. LOME is available as a Docker container on Docker Hub. In addition, a lightweight version of the system is accessible as a web demo.",
}

Copied!

@inproceedings{xu_gradual_2021,
  title = "Gradual Fine-Tuning for Low-Resource Domain Adaptation",
  author = "Xu, Haoran  and
    Ebner, Seth  and
    Yarmohammadi, Mahsa  and
    White, Aaron Steven  and
    Van Durme, Benjamin  and
    Murray, Kenton",
  editor = "Ben-David, Eyal  and
    Cohen, Shay  and
    McDonald, Ryan  and
    Plank, Barbara  and
    Reichart, Roi  and
    Rotman, Guy  and
    Ziser, Yftah",
  booktitle = "Proceedings of the Second Workshop on Domain Adaptation for NLP",
  month = apr,
  year = "2021",
  address = "Kyiv, Ukraine",
  publisher = "Association for Computational Linguistics",
  url = "https://aclanthology.org/2021.adaptnlp-1.22",
  pages = "214--221",
  abstract = "Fine-tuning is known to improve NLP models by adapting an initial model trained on more plentiful but less domain-salient examples to data in a target domain. Such domain adaptation is typically done using one stage of fine-tuning. We demonstrate that gradually fine-tuning in a multi-step process can yield substantial further gains and can be applied without modifying the model or learning objective.",
}

Copied!

@article{white_frequency_2020,
	title = {Frequency, acceptability, and selection: {A} case study of clause-embedding},
	volume = {5},
	copyright = {Authors who publish with this journal agree to the following terms:    Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a  Creative Commons Attribution License  that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.  Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.  Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See  The Effect of Open Access ).  All third-party images reproduced on this journal are shared under Educational Fair Use. For more information on  Educational Fair Use , please see  this useful checklist prepared by Columbia University Libraries .   All copyright  of third-party content posted here for research purposes belongs to its original owners.  Unless otherwise stated all references to characters and comic art presented on this journal are ©, ® or ™ of their respective owners. No challenge to any owner’s rights is intended or should be inferred.},
	issn = {2397-1835},
	shorttitle = {Frequency, acceptability, and selection},
	url = {http://www.glossa-journal.org//article/10.5334/gjgl.1001/},
	doi = {10.5334/gjgl.1001},
	abstract = {Article: Frequency, acceptability, and selection: A case study of clause-embedding},
	language = {en},
	number = {1},
	urldate = {2020-11-04},
	journal = {Glossa: a journal of general linguistics},
	author = {White, Aaron Steven and Rawlins, Kyle},
	month = nov,
	year = {2020},
	note = {Number: 1
Publisher: Ubiquity Press},
	pages = {105},
	file = {Full Text PDF:/home/aaronsteven/snap/zotero-snap/common/Zotero/storage/MNKR3NNA/White and Rawlins - 2020 - Frequency, acceptability, and selection A case st.pdf:application/pdf;Snapshot:/home/aaronsteven/snap/zotero-snap/common/Zotero/storage/Q4S2JYBW/gjgl.1001.html:text/html}
}

Copied!

@inproceedings{white_universal_2020,
  title = "The Universal Decompositional Semantics Dataset and Decomp Toolkit",
  author = "White, Aaron Steven  and
    Stengel-Eskin, Elias  and
    Vashishtha, Siddharth  and
    Govindarajan, Venkata Subrahmanyan  and
    Reisinger, Dee Ann  and
    Vieira, Tim  and
    Sakaguchi, Keisuke  and
    Zhang, Sheng  and
    Ferraro, Francis  and
    Rudinger, Rachel  and
    Rawlins, Kyle  and
    Van Durme, Benjamin",
  editor = "Calzolari, Nicoletta  and
    B{\'e}chet, Fr{\'e}d{\'e}ric  and
    Blache, Philippe  and
    Choukri, Khalid  and
    Cieri, Christopher  and
    Declerck, Thierry  and
    Goggi, Sara  and
    Isahara, Hitoshi  and
    Maegaard, Bente  and
    Mariani, Joseph  and
    Mazo, H{\'e}l{\`e}ne  and
    Moreno, Asuncion  and
    Odijk, Jan  and
    Piperidis, Stelios",
  booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
  month = may,
  year = "2020",
  address = "Marseille, France",
  publisher = "European Language Resources Association",
  url = "https://aclanthology.org/2020.lrec-1.699",
  pages = "5698--5707",
  abstract = "We present the Universal Decompositional Semantics (UDS) dataset (v1.0), which is bundled with the Decomp toolkit (v0.1). UDS1.0 unifies five high-quality, decompositional semantics-aligned annotation sets within a single semantic graph specification{---}with graph structures defined by the predicative patterns produced by the PredPatt tool and real-valued node and edge attributes constructed using sophisticated normalization procedures. The Decomp toolkit provides a suite of Python 3 tools for querying UDS graphs using SPARQL. Both UDS1.0 and Decomp0.1 are publicly available at \url{http://decomp.io}.",
  language = "English",
  ISBN = "979-10-95546-34-4",
}

Copied!

@inproceedings{stengel-eskin_universal_2020,
	address = "Online",
	title = "Universal {Decompositional} {Semantic} {Parsing}",
	url = {https://www.aclweb.org/anthology/2020.acl-main.746},
	doi = "10.18653/v1/2020.acl-main.746",
	abstract = "We introduce a transductive model for parsing into Universal Decompositional Semantics (UDS) representations, which jointly learns to map natural language utterances into UDS graph structures and annotate the graph with decompositional semantic attribute scores. We also introduce a strong pipeline model for parsing into the UDS graph structure, and show that our transductive parser performs comparably while additionally performing attribute prediction. By analyzing the attribute prediction errors, we find the model captures natural relationships between attribute groups.",
	booktitle = "Proceedings of the 58th {Annual} {Meeting} of the {Association} for {Computational} {Linguistics}",
	publisher = "Association for Computational Linguistics",
	author = "Stengel-Eskin, Elias and White, Aaron Steven and Zhang, Sheng and Van Durme, Benjamin",
	month = jul,
	year = "2020",
	pages = "8427--8439"
}

Copied!

@inproceedings{gantt_natural_2020,
  title = "Natural Language Inference with Mixed Effects",
  author = "Gantt, William  and
    Kane, Benjamin  and
    White, Aaron Steven",
  booktitle = "Proceedings of the Ninth Joint Conference on Lexical and Computational Semantics",
  month = dec,
  year = "2020",
  address = "Barcelona, Spain (Online)",
  publisher = "Association for Computational Linguistics",
  url = "https://www.aclweb.org/anthology/2020.starsem-1.9",
  pages = "81--87"
}

Copied!

@inproceedings{vashishtha_temporal_2020,
  title = "Temporal Reasoning in Natural Language Inference",
  author = "Vashishtha, Siddharth  and
    Poliak, Adam  and
    Lal, Yash Kumar  and
    Van Durme, Benjamin  and
    White, Aaron Steven",
  booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
  month = nov,
  year = "2020",
  address = "Online",
  publisher = "Association for Computational Linguistics",
  url = "https://www.aclweb.org/anthology/2020.findings-emnlp.363",
  pages = "4070--4078"
}

Copied!

@article{an_lexical_2020,
	title = "The lexical and grammatical sources of neg-raising inferences",
	volume = "3",
	url = "https://scholarworks.umass.edu/scil/vol3/iss1/23",
	doi = "https://doi.org/10.7275/yts0-q989",
	number = "1",
	journal = "Proceedings of the Society for Computation in Linguistics",
	author = "An, Hannah and White, Aaron",
	month = jan,
	year = "2020",
	pages = "220--233"
}

Copied!

@inproceedings{moon_source_2020,
	address = {Amherst, MA},
	title = {The source of nonfinite temporal interpretation},
	volume = {3},
	booktitle = {Proceedings of the 50th {Annual} {Meeting} of the {North} {East} {Linguistic} {Society}},
	publisher = {GLSA Publications},
	author = {Moon, Ellise and White, Aaron Steven},
	editor = {Mariam Asatryan and Yixiao Song and Ayana Whitmal},
	year = {2020},
	pages = {11--24}
}

Copied!

@inproceedings{chen_reading_2020,
    title = "Reading the Manual: Event Extraction as Definition Comprehension",
    author = "Chen, Yunmo  and
      Chen, Tongfei  and
      Ebner, Seth  and
      White, Aaron Steven  and
      Van Durme, Benjamin",
    booktitle = "Proceedings of the Fourth Workshop on Structured Prediction for NLP",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.spnlp-1.9",
    pages = "74--83"
}

Copied!

@article{govindarajan_decomposing_2019,
	title = "Decomposing {Generalization}: {Models} of {Generic}, {Habitual}, and {Episodic} {Statements}",
	volume = "7",
	url = "https://www.aclweb.org/anthology/Q19-1035",
	doi = "10.1162/tacl_a_00285",
	abstract = "We present a novel semantic framework for modeling linguistic expressions of generalization— generic, habitual, and episodic statements—as combinations of simple, real-valued referential properties of predicates and their arguments. We use this framework to construct a dataset covering the entirety of the Universal Dependencies English Web Treebank. We use this dataset to probe the efficacy of type-level and token-level information—including hand-engineered features and static (GloVe) and contextual (ELMo) word embeddings—for predicting expressions of generalization.",
	journal = "Transactions of the Association for Computational Linguistics",
	author = "Govindarajan, Venkata and Van Durme, Benjamin and White, Aaron Steven",
	month = mar,
	year = "2019",
	pages = "501--517"
}

Copied!

@inproceedings{vashishtha_fine-grained_2019,
	address = "Florence, Italy",
	title = "Fine-{Grained} {Temporal} {Relation} {Extraction}",
	url = "https://www.aclweb.org/anthology/P19-1280",
	abstract = "We present a novel semantic framework for modeling temporal relations and event durations that maps pairs of events to real-valued scales. We use this framework to construct the largest temporal relations dataset to date, covering the entirety of the Universal Dependencies English Web Treebank. We use this dataset to train models for jointly predicting fine-grained temporal relations and event durations. We report strong results on our data and show the efficacy of a transfer-learning approach for predicting categorical relations.",
	booktitle = "Proceedings of the 57th {Annual} {Meeting} of the {Association} for {Computational} {Linguistics}",
	publisher = "Association for Computational Linguistics",
	author = "Vashishtha, Siddharth and Van Durme, Benjamin and White, Aaron Steven",
	month = jul,
	year = "2019",
	pages = "2906--2919"
}

Copied!

@incollection{white_lexically_2019,
	title = {Lexically triggered veridicality inferences},
	volume = {22},
	url = {https://doi.org/10.1075/hop.22.lex4},
	booktitle = {Handbook of {Pragmatics}},
	publisher = {John Benjamins Publishing Company},
	author = {White, Aaron Steven},
	year = {2019},
	pages = {115--148}
}

Copied!

@inproceedings{yan_framework_2019,
	address = "Minneapolis, Minnesota",
	title = "A {Framework} for {Decoding} {Event}-{Related} {Potentials} from {Text}",
	url = "https://www.aclweb.org/anthology/W19-2910",
	doi = "10.18653/v1/W19-2910",
	abstract = "We propose a novel framework for modeling event-related potentials (ERPs) collected during reading that couples pre-trained convolutional decoders with a language model. Using this framework, we compare the abilities of a variety of existing and novel sentence processing models to reconstruct ERPs. We find that modern contextual word embeddings underperform surprisal-based models but that, combined, the two outperform either on its own.",
	booktitle = "Proceedings of the {Workshop} on {Cognitive} {Modeling} and {Computational} {Linguistics}",
	publisher = "Association for Computational Linguistics",
	author = "Yan, Shaorong and White, Aaron Steven",
	month = jun,
	year = "2019",
	pages = "86--92"
}

Copied!

@article{white_semantic_2018,
	title = {Semantic {Information} and the {Syntax} of {Propositional} {Attitude} {Verbs}},
	volume = {42},
	abstract = {Propositional attitude verbs, such as think and want, have long held interest for both theoretical linguists and language acquisitionists because their syntactic, semantic, and pragmatic properties display complex interactions that have proven difficult to fully capture from either perspective. This paper explores the granularity with which these verbs’ semantic and pragmatic properties are recoverable from their syntactic distributions, using three behavioral experiments aimed at explicitly quantifying the relationship between these two sets of properties. Experiment 1 gathers a measure of 30 propositional attitude verbs’ syntactic distributions using an acceptability judgment task. Experiments 2a and 2b gather measures of semantic similarity between those same verbs using a generalized semantic discrimination (triad or “odd man out”) task and an ordinal (Likert) scale task, respectively. Two kinds of analyses are conducted on the data from these experiments. The first compares both the acceptability judgments and the semantic similarity judgments to previous classifications derived from the syntax and semantics literature. The second kind compares the acceptability judgments to the semantic similarity judgments directly. Through these comparisons, we show that there is quite fine-grained information about propositional attitude verbs’ semantics carried in their syntactic distributions—whether one considers the sorts of discrete qualitative classifications that linguists traditionally work with or the sorts of continuous quantitative classifications that can be derived experimentally.},
	number = {2},
	journal = {Cognitive Science},
	author = {White, Aaron Steven and Hacquard, Valentine and Lidz, Jeffrey},
	year = {2018},
	keywords = {Lexical semantics, Projection rules, Propositional attitude verbs, Syntactic bootstrapping, Syntax-semantics interface, Verb learning},
	pages = {416--456},
	file = {Snapshot:/home/aaronsteven/snap/zotero-snap/common/Zotero/storage/XFHP6CM3/cogs.html:text/html}
}

Copied!

@incollection{white_labeling_2018,
	series = {Trends in {Language} {Acquisition} {Research} ({TiLAR})},
	title = {The labeling problem in syntactic bootstrapping: {Main} clause syntax in the acquisition of propositional attitude verbs},
	url = {https://doi.org/10.1075/tilar.24.09whi},
	abstract = {In English, the distinction between belief verbs, such as think, and desire verbs, such as want, is tracked by tense found in the subordinate clauses of those verbs. This suggests that subordinate clause tense might be a useful cue for learning the meanings of these verbs via syntactic bootstrapping. However, the correlation between tense and the belief v. desire distinction is not cross-linguistically robust; yet the acquisition profile of these verbs is similar cross-linguistically. Our proposal in this chapter is that, instead of using concrete cues like subordinate clause tense, learners may utilize more abstract syntactic cues that must be tuned to the syntactic distinctions present in a particular language. We present computational modeling evidence supporting the viability of this proposal.},
	number = {24},
	booktitle = {Semantics in {Acquisition}},
	publisher = {John Benjamins Publishing Company},
	author = {White, Aaron Steven and Hacquard, Valentine and Lidz, Jeffrey},
	editor = {Kristen Syrett and Sudha Arunachalam},
	year = {2018},
	pages = {198--220}
}

Copied!

@inproceedings{poliak_collecting_2018,
	address = "Brussels, Belgium",
	title = "Collecting {Diverse} {Natural} {Language} {Inference} {Problems} for {Sentence} {Representation} {Evaluation}",
	url = "https://www.aclweb.org/anthology/D18-1007",
	doi = "10.18653/v1/D18-1007",
	abstract = "We present a large-scale collection of diverse natural language inference (NLI) datasets that help provide insight into how well a sentence representation captures distinct types of reasoning. The collection results from recasting 13 existing datasets from 7 semantic phenomena into a common NLI structure, resulting in over half a million labeled context-hypothesis pairs in total. We refer to our collection as the DNC: Diverse Natural Language Inference Collection. The DNC is available online at https://www.decomp.net, and will grow over time as additional resources are recast and added from novel sources.",
	booktitle = "Proceedings of the 2018 {Conference} on {Empirical} {Methods} in {Natural} {Language} {Processing}",
	publisher = "Association for Computational Linguistics",
	author = "Poliak, Adam and Haldar, Aparajita and Rudinger, Rachel and Hu, J. Edward and Pavlick, Ellie and White, Aaron Steven and Van Durme, Benjamin",
	month = oct,
	year = "2018",
	pages = "67--81"
}

Copied!

@inproceedings{rudinger_neural_2018,
	address = "New Orleans, Louisiana",
	title = "Neural {Models} of {Factuality}",
	url = "https://www.aclweb.org/anthology/N18-1067",
	doi = "10.18653/v1/N18-1067",
	abstract = "We present two neural models for event factuality prediction, which yield significant performance gains over previous models on three event factuality datasets: FactBank, UW, and MEANTIME. We also present a substantial expansion of the It Happened portion of the Universal Decompositional Semantics dataset, yielding the largest event factuality dataset to date. We report model results on this extended factuality dataset as well.",
	booktitle = "Proceedings of the 2018 {Conference} of the {North} {American} {Chapter} of the {Association} for {Computational} {Linguistics}: {Human} {Language} {Technologies}, {Volume} 1 ({Long} {Papers})",
	publisher = "Association for Computational Linguistics",
	author = "Rudinger, Rachel and White, Aaron Steven and Van Durme, Benjamin",
	month = jun,
	year = "2018",
	pages = "731--744"
}

Copied!

@inproceedings{white_lexicosyntactic_2018,
	address = {Brussels, Belgium},
	title = {Lexicosyntactic {Inference} in {Neural} {Models}},
	url = {https://www.aclweb.org/anthology/D18-1501},
	doi = {10.18653/v1/D18-1501},
	abstract = {We investigate neural models' ability to capture lexicosyntactic inferences: inferences triggered by the interaction of lexical and syntactic information. We take the task of event factuality prediction as a case study and build a factuality judgment dataset for all English clause-embedding verbs in various syntactic contexts. We use this dataset, which we make publicly available, to probe the behavior of current state-of-the-art neural systems, showing that these systems make certain systematic errors that are clearly visible through the lens of factuality prediction.},
	booktitle = {Proceedings of the 2018 {Conference} on {Empirical} {Methods} in {Natural} {Language} {Processing}},
	publisher = {Association for Computational Linguistics},
	author = {White, Aaron Steven and Rudinger, Rachel and Rawlins, Kyle and Van Durme, Benjamin},
	month = oct,
	year = {2018},
	pages = {4717--4724}
}

Copied!

@inproceedings{white_role_2018,
	address = {Amherst, MA},
	title = {The role of veridicality and factivity in clause selection},
	booktitle = {Proceedings of the 48th {Annual} {Meeting} of the {North} {East} {Linguistic} {Society}},
	publisher = {GLSA Publications},
	author = {White, Aaron Steven and Rawlins, Kyle},
	editor = {Hucklebridge, Sherry and Nelson, Max},
	year = {2018},
	pages = {221--234}
}

Copied!

@inproceedings{white_question_2018,
	address = {University of Edinburgh},
	title = {Question agnosticism and change of state},
	booktitle = {Proceedings of {Sinn} und {Bedeutung} 21},
	author = {White, Aaron Steven and Rawlins, Kyle},
	editor = {Truswell, Robert and Cummins, Chris and Heycock, Caroline and Rabern, Brian and Rohde, Hannah},
	year = {2018},
	pages = {1325--1342}
}

Copied!

@article{lidz_role_2017,
	title = {The role of incremental parsing in syntactically conditioned word learning},
	volume = {97},
	issn = {0010-0285},
	url = {http://www.sciencedirect.com/science/article/pii/S0010028516302742},
	doi = {10.1016/j.cogpsych.2017.06.002},
	abstract = {In a series of three experiments, we use children’s noun learning as a probe into their syntactic knowledge as well as their ability to deploy this knowledge, investigating how the predictions children make about upcoming syntactic structure change as their knowledge changes. In the first two experiments, we show that children display a developmental change in their ability to use a noun’s syntactic environment as a cue to its meaning. We argue that this pattern arises from children’s reliance on their knowledge of verbs’ subcategorization frame frequencies to guide parsing, coupled with an inability to revise incremental parsing decisions. We show that this analysis is consistent with the syntactic distributions in child-directed speech. In the third experiment, we show that the change arises from predictions based on verbs’ subcategorization frame frequencies.},
	language = {en},
	urldate = {2020-08-22},
	journal = {Cognitive Psychology},
	author = {Lidz, Jeffrey and White, Aaron Steven and Baier, Rebecca},
	month = sep,
	year = {2017},
	keywords = {Language acquisition, Parsing, Prediction, Thematic roles},
	pages = {62--78},
	file = {ScienceDirect Snapshot:/home/aaronsteven/snap/zotero-snap/common/Zotero/storage/89A8QX4Q/S0010028516302742.html:text/html}
}

Copied!

@inproceedings{white_inference_2017,
	address = "Taipei, Taiwan",
	title = "Inference is {Everything}: {Recasting} {Semantic} {Resources} into a {Unified} {Evaluation} {Framework}",
	url = "https://www.aclweb.org/anthology/I17-1100",
	abstract = "We propose to unify a variety of existing semantic classification tasks, such as semantic role labeling, anaphora resolution, and paraphrase detection, under the heading of Recognizing Textual Entailment (RTE). We present a general strategy to automatically generate one or more sentential hypotheses based on an input sentence and pre-existing manual semantic annotations. The resulting suite of datasets enables us to probe a statistical RTE model's performance on different aspects of semantics. We demonstrate the value of this approach by investigating the behavior of a popular neural network RTE model.",
	booktitle = "Proceedings of the {Eighth} {International} {Joint} {Conference} on {Natural} {Language} {Processing} ({Volume} 1: {Long} {Papers})",
	publisher = "Asian Federation of Natural Language Processing",
	author = "White, Aaron Steven and Rastogi, Pushpendre and Duh, Kevin and Van Durme, Benjamin",
	month = nov,
	year = "2017",
	pages = "996--1005"
}

Copied!

@inproceedings{white_semantic_2017,
	address = "Valencia, Spain",
	title = "The {Semantic} {Proto}-{Role} {Linking} {Model}",
	url = "https://www.aclweb.org/anthology/E17-2015",
	abstract = "We propose the semantic proto-role linking model, which jointly induces both predicate-specific semantic roles and predicate-general semantic proto-roles based on semantic proto-role property likelihood judgments. We use this model to empirically evaluate Dowty's thematic proto-role linking theory.",
	booktitle = "Proceedings of the 15th {Conference} of the {European} {Chapter} of the {Association} for {Computational} {Linguistics}: {Volume} 2, {Short} {Papers}",
	publisher = "Association for Computational Linguistics",
	author = "White, Aaron Steven and Rawlins, Kyle and Van Durme, Benjamin",
	month = apr,
	year = "2017",
	pages = "92--98"
}

Copied!

@inproceedings{fetters_pseudogapping_2017,
	address = {Somerville, MA},
	title = {Pseudogapping does not involve heavy shift},
	booktitle = {Proceedings of the 34th {West} {Coast} {Conference} on {Formal} {Linguistics}},
	author = {Fetters, Michael and White, Aaron Steven},
	editor = {Aaron Kaplan and Abby Kaplan and Miranda K. McCarvel and Edward J. Rubin},
	year = {2017},
	pages = {205--213}
}

Copied!

@inproceedings{white_universal_2016,
	address = {Austin, Texas},
	title = {Universal {Decompositional} {Semantics} on {Universal} {Dependencies}},
	url = {https://www.aclweb.org/anthology/D16-1177},
	doi = {10.18653/v1/D16-1177},
	booktitle = {Proceedings of the 2016 {Conference} on {Empirical} {Methods} in {Natural} {Language} {Processing}},
	publisher = {Association for Computational Linguistics},
	author = {White, Aaron Steven and Reisinger, Drew and Sakaguchi, Keisuke and Vieira, Tim and Zhang, Sheng and Rudinger, Rachel and Rawlins, Kyle and Van Durme, Benjamin},
	month = nov,
	year = {2016},
	pages = {1713--1723}
}

Copied!

@article{white_computational_2016,
	title = {A computational model of {S}-selection},
	volume = {26},
	issn = {2163-5951},
	url = {https://journals.linguisticsociety.org/proceedings/index.php/SALT/article/view/26.641},
	doi = {10.3765/salt.v26i0.3819},
	abstract = {We develop a probabilistic model of S(emantic)-selection that encodes both the notion of systematic mappings from semantic type signature to syntactic distribution—i.e., projection rules—and the notion of selectional noise—e.g., C(ategory)-selection, L(exical)-selection, and/or other independent syntactic processes. We train this model on data from a large-scale judgment study assessing the acceptability of 1,000 English clause-taking verbs in 50 distinct syntactic frames, finding that this model infers coherent semantic type signatures. We focus in on type signatures relevant to interrogative and declarative selection, arguing that our results suggest a principled split between cognitive verbs, which select distinct proposition and question types, and communicative verbs, which select a single hybrid type.},
	language = {en},
	urldate = {2020-08-24},
	journal = {Semantics and Linguistic Theory},
	author = {White, Aaron Steven and Rawlins, Kyle},
	editor = {Mary Moroney and Carol-Rose Little and Jacob Collard and Dan Burgdorf},
	month = oct,
	year = {2016},
	note = {Number: 0},
	pages = {641--663},
	file = {Full Text PDF:/home/aaronsteven/snap/zotero-snap/common/Zotero/storage/HGQIL3Y2/White and Rawlins - 2016 - A computational model of S-selection.pdf:application/pdf;Snapshot:/home/aaronsteven/snap/zotero-snap/common/Zotero/storage/H4KVLSH9/26.html:text/html}
}

Copied!

@phdthesis{white_information_2015,
	address = {College Park, MD},
	type = {PhD {Thesis}},
	title = {Information and {Incrementality} in {Syntactic} {Bootstrapping}},
	school = {University of Maryland},
	author = {White, Aaron Steven},
	year = {2015}
}

Copied!

@article{altshuler_double_2015,
	title = {On double access, cessation and parentheticality},
	volume = {25},
	issn = {2163-5951},
	url = {https://journals.linguisticsociety.org/proceedings/index.php/SALT/article/view/25.18},
	doi = {10.3765/salt.v25i0.3048},
	abstract = {Arguably the biggest challenge in analyzing English tense is to account for the double access interpretation, which arises when a present tensed verb is embedded under a past attitude—e.g. John said that Mary is pregnant. Present-under-past does not always result in a felicitous utterance, however—cf. \#John believed that Mary is pregnant. While such oddity has been noted, the contrast hasnever been explained. In fact, English grammars and manuals generally prohibit present-under-past. Work on double access, on the other hand, has either disregarded the oddity (e.g. Abusch 1997: 39) or treated it as a reflex of a particular dialect (e.g. Kratzer 1998: 14). The goal of the paper is to argue—based on a corpus study—that a present-under-past sentence is grammatical, but modulated by two, interacting pragmatic phenomena: cessation and parentheticality.},
	language = {en},
	urldate = {2020-08-24},
	journal = {Semantics and Linguistic Theory},
	author = {Altshuler, Daniel Gordon and Hacquard, Valentine and Roberts, Thomas and White, Aaron Steven},
	editor = {Sarah D'Antonio and Mary Moroney and Carol Rose Little},
	month = oct,
	year = {2015},
	note = {Number: 0},
	pages = {18--37},
	file = {Full Text PDF:/home/aaronsteven/snap/zotero-snap/common/Zotero/storage/5VTWZTNM/Altshuler et al. - 2015 - On double access, cessation and parentheticality.pdf:application/pdf;Snapshot:/home/aaronsteven/snap/zotero-snap/common/Zotero/storage/UYVM3XHP/25.html:text/html}
}

Copied!

@inproceedings{white_factive-implicatives_2014,
	address = {Amherst, MA},
	title = {Factive-implicatives and modalized complements},
	volume = {2},
	booktitle = {Proceedings of the 44th annual meeting of the {North} {East} {Linguistic} {Society}},
	publisher = {GLSA Publications},
	author = {White, Aaron Steven},
	editor = {Jyoti Iyer and Leland Kusmer},
	year = {2014},
	pages = {267--278}
}

Copied!

@inproceedings{white_experimental_2014,
	title = {An experimental investigation of partial control},
	volume = {18},
	booktitle = {Proceedings of {Sinn} und {Bedeutung}},
	author = {White, Aaron Steven and Grano, Thomas},
	editor = {U. Etxeberria and A. Falaus and A. Irurtzun and B. Leferman},
	year = {2014},
	pages = {469--486}
}

Copied!

@inproceedings{white_discovering_2014,
	address = {Amherst, MA},
	title = {Discovering classes of attitude verbs using subcategorization frame distributions},
	volume = {2},
	booktitle = {Proceedings of the 43rd {Annual} {Meeting} of the {North} {East} {Linguistic} {Society}},
	publisher = {GLSA Publications},
	author = {White, Aaron Steven and Dudley, Rachel and Hacquard, Valentine and Lidz, Jeffrey},
	editor = {Hsin-Lun Huang and Ethan Poole and Amanda Rysling},
	year = {2014},
	pages = {249--260}
}

Copied!