Kyle Rawlins
YOU?
Author Swipe
View article: Analyzing naturally-sourced Questions Under Discussion
Analyzing naturally-sourced Questions Under Discussion Open
The Question Under Discussion (QUD) framework of discourse has been a highly influential theoretical device in many accounts of various pragmatic phenomena, yet there has been comparatively little work assessing the extent to which the QUD…
View article: Perspectival biscuits
Perspectival biscuits Open
This paper describes a novel class of biscuit conditional, the 'perspectival biscuit', which arises when an if-clause containing a generic pronoun (e.g., generic you) is used to shift perspective for the interpretation of a perspective-sen…
View article: Deriving the evidence asymmetry in positive polar questions
Deriving the evidence asymmetry in positive polar questions Open
This paper explores a famous puzzle about English positive polar questions introduced by Buring and Gunlogson 2000: while in many contexts they seem to indicate nothing whatsoever about what the speaker takes for granted or thinks likely, …
View article: Zero and Few-shot Semantic Parsing with Ambiguous Inputs
Zero and Few-shot Semantic Parsing with Ambiguous Inputs Open
Despite the frequent challenges posed by ambiguity when representing meaning via natural language, it is often ignored or deliberately removed in tasks mapping language to formally-designed representations, which generally assume a one-to-…
View article: Asymmetries between uniqueness and familiarity in the semantics of definite descriptions
Asymmetries between uniqueness and familiarity in the semantics of definite descriptions Open
In over a century of research into the English definite article "the", two main theoretical factors have been identified as relevant to its meaning: namely, (i) uniqueness and (ii) familiarity. The identification of these factors has led t…
View article: LOME: Large Ontology Multilingual Extraction
LOME: Large Ontology Multilingual Extraction Open
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 subsequentl…
View article: LOME: Large Ontology Multilingual Extraction
LOME: Large Ontology Multilingual Extraction Open
Patrick Xia, Guanghui Qin, Siddharth Vashishtha, Yunmo Chen, Tongfei Chen, Chandler May, Craig Harman, Kyle Rawlins, Aaron Steven White, Benjamin Van Durme. Proceedings of the 16th Conference of the European Chapter of the Association for …
View article: Evidential meaning of English clause-embedding verbs
Evidential meaning of English clause-embedding verbs Open
English clause-embedding verbs can be used in the evidential meaning (Simons, 2007; Murray, 2017), modulating the degree to which the speaker is committed to the truth of the\nproposition in the embedded clause. For example, an utterance l…
View article: Frequency, acceptability, and selection: A case study of clause-embedding
Frequency, acceptability, and selection: A case study of clause-embedding Open
We investigate the relationship between the frequency with which verbs are found in particular subcategorization frames and the acceptability of those verbs in those frames, focusing in particular on subordinate clause-taking verbs, such a…
View article: Frequency, Acceptability, and Selection: A case study of\n clause-embedding
Frequency, Acceptability, and Selection: A case study of\n clause-embedding Open
We investigate the relationship between the frequency with which verbs are\nfound in particular subcategorization frames and the acceptability of those\nverbs in those frames, focusing in particular on subordinate clause-taking\nverbs, suc…
View article: An Experimental Investigation of the Role of Uniqueness and Familiarity in Interpreting Definite Descriptions
An Experimental Investigation of the Role of Uniqueness and Familiarity in Interpreting Definite Descriptions Open
In this study, we follow a long line of researchers in asking about the precise role of uniqueness and familiarity in the semantics of the English definite article the. We attempt to answer this question experimentally, by observing how de…
View article: Multi-Sentence Argument Linking
Multi-Sentence Argument Linking Open
We present a novel document-level model for finding argument spans that fill an event's roles, connecting related ideas in sentence-level semantic role labeling and coreference resolution. Because existing datasets for cross-sentence linki…
View article: Attitudes in discourse: Italian polar questions and the particle mica
Attitudes in discourse: Italian polar questions and the particle mica Open
This paper explores ways in which discourse participants convey an attitude about another discourse participant's conversational move. We examine the semantics/pragmatics of Italian positive and negative polar questions (building on the li…
View article: What ifs
What ifs Open
We develop a dynamic account of what if questions on which they re-pose questions inside local contexts introduced by their if-clauses subject to the felicity constraint that the resulting context is inquisitive. While this analysis is dir…
View article: The Universal Decompositional Semantics Dataset and Decomp Toolkit
The Universal Decompositional Semantics Dataset and Decomp Toolkit Open
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 sp…
View article: Predicting the Argumenthood of English Prepositional Phrases
Predicting the Argumenthood of English Prepositional Phrases Open
Distinguishing between arguments and adjuncts of a verb is a longstanding, nontrivial problem. In natural language processing, argumenthood information is important in tasks such as semantic role labeling (SRL) and prepositional phrase (PP…
View article: Predicting the Argumenthood of English Prepositional Phrases
Predicting the Argumenthood of English Prepositional Phrases Open
Distinguishing between arguments and adjuncts of a verb is a longstanding, nontrivial problem. In natural language processing, argumenthood information is important in tasks such as semantic role labeling (SRL) and prepositional phrase (PP…
View article: Lexicosyntactic Inference in Neural Models
Lexicosyntactic Inference in Neural Models Open
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 factuali…
View article: Lexicosyntactic Inference in Neural Models
Lexicosyntactic Inference in Neural Models Open
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 factuali…
View article: Or what?
Or what? Open
This paper develops an argument that discourse considerations are crucial in the semantics of questions by looking at the case of English “or what” questions. We argue that “what” in these questions is a discourse pronoun anaphoric with th…
View article: Rhetorical questions: Severing asking from questioning
Rhetorical questions: Severing asking from questioning Open
Rhetorical questions (RhQs) are puzzling for theoretical accounts of questions: while they have an interrogative form, they seem to provide the same information as a parallel assertion. We propose that solving this puzzle requires a deeper…
View article: The Semantic Proto-Role Linking Model
The Semantic Proto-Role Linking Model Open
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 empi…
View article: A computational model of S-selection
A computational model of S-selection Open
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)…
View article: Epistemic Resistance Moves
Epistemic Resistance Moves Open
This paper introduces and analyzes a new kind of non-acceptance, non-disagreeing move: resistance. We focus in particular on attention-targeted resistance facilitated by epistemic possibility claims. In this response type, we suggest, an a…
View article: Computational linking theory
Computational linking theory Open
A linking theory explains how verbs' semantic arguments are mapped to their syntactic arguments---the inverse of the Semantic Role Labeling task from the shallow semantic parsing literature. In this paper, we develop the Computational Link…
View article: Similarity of wh-Phrases and Acceptability Variation in wh-Islands
Similarity of wh-Phrases and Acceptability Variation in wh-Islands Open
In wh-questions that form a syntactic dependency between the fronted wh-phrase and its thematic position, acceptability is severely degraded when the dependency crosses another wh-phrase. It is well known that the acceptability degradation…
View article: Universal Decompositional Semantics on Universal Dependencies
Universal Decompositional Semantics on Universal Dependencies Open
Aaron Steven White, Drew Reisinger, Keisuke Sakaguchi, Tim Vieira, Sheng Zhang, Rachel Rudinger, Kyle Rawlins, Benjamin Van Durme. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. 2016.