Access to higher education is critical for minority populations and emergent bilingual students. However, the language used by higher education institutions to communicate with prospective students is often too complex; concretely, many institutions in the US publish admissions application instructions far above the average reading level of a typical high school graduate, often near the 13th or 14th grade level. This leads to an unnecessary barrier between students and access to higher education. This work aims to tackle this challenge via text simplification. We present PSAT (Professionally Simplified Admissions Texts), a dataset with 112 admissions instructions randomly selected from higher education institutions across the US. These texts are then professionally simplified, and verified and accepted by subject-matter experts who are full-time employees in admissions offices at various institutions. Additionally, PSAT comes with manual alignments of 1,883 original-simplified sentence pairs. The result is a first-of-its-kind corpus for the evaluation and fine-tuning of text simplification systems in a high-stakes genre distinct from existing simplification resources.
more »
« less
Elaborative Simplification: Content Addition and Explanation Generation in Text Simplification
Much of modern-day text simplification research focuses on sentence-level simplification, transforming original, more complex sentences into simplified versions. However, adding content can often be useful when difficult concepts and reasoning need to be explained. In this work, we present the first data-driven study of content addition in text simplification, which we call elaborative simplification. We introduce a new annotated dataset of 1.3K instances of elaborative simplification in the Newsela corpus, and analyze how entities, ideas, and concepts are elaborated through the lens of contextual specificity. We establish baselines for elaboration generation using large-scale pre-trained language models, and demonstrate that considering contextual specificity during generation can improve performance. Our results illustrate the complexities of elaborative simplification, suggesting many interesting directions for future work.
more »
« less
- Award ID(s):
- 1850153
- NSF-PAR ID:
- 10350193
- Date Published:
- Journal Name:
- Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021
- Page Range / eLocation ID:
- 5123 to 5137
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Automatic Text Simplification (ATS), which replaces text with simpler equivalents, is rapidly improving. While some research has examined ATS reading-assistance tools, little has examined preferences of adults who are deaf or hard-of-hearing (DHH), and none empirically evaluated lexical simplification technology (replacement of individual words) with these users. Prior research has revealed that U.S. DHH adults have lower reading literacy on average than their hearing peers, with unique characteristics to their literacy profile. We investigate whether DHH adults perceive a benefit from lexical simplification applied automatically or when users are provided with greater autonomy, with on-demand control and visibility as to which words are replaced. Formative interviews guided the design of an experimental study, in which DHH participants read English texts in their original form and with lexical simplification applied automatically or on-demand. Participants indicated that they perceived a benefit form lexical simplification, and they preferred a system with on-demand simplification.more » « less
-
A Dataset of Word-Complexity Judgements from Deaf and Hard-of-Hearing Adults for Text SimplificationResearch has explored the use of automatic text simplification (ATS), which consists of techniques to make text simpler to read, to provide reading assistance to Deaf and Hard-of-hearing (DHH) adults with various literacy levels. Prior work in this area has identified interest in and benefits from ATS-based reading assistance tools. However, no prior work on ATS has gathered judgements from DHH adults as to what constitutes complex text. Thus, following approaches in prior NLP work, this paper contributes new word-complexity judgements from 11 DHH adults on a dataset of 15,000 English words that had been previously annotated by L2 speakers, which we also augmented to include automatic annotations of linguistic characteristics of the words. Additionally, we conduct a supplementary analysis of the interaction effect between the linguistic characteristics of the words and the groups of annotators. This analysis highlights the importance of collecting judgements from DHH adults for training ATS systems, as it revealed statistically significant interaction effects for nearly all of the linguistic characteristics of the words.more » « less
-
Automatic Text Simplification (ATS) aims to rewrite text in a way that reduces its linguistic complexity while preserving its original meaning. While some prior research has explored using ATS to provide reading assistance to different user groups, relatively little work has investigated its use for Deaf and Hard-of-hearing (DHH) adults or readers in a particular domain. In this project, we investigate the use of ATS-based reading assistance tools for DHH individuals in the computing and information technology (IT) fields, motivated by prior work suggesting that computing professions often require reading about new technologies in order to stay current in the profession. Employing a variety of research methods, we investigate questions including the needs and interests of DHH individuals in the computing and IT fields for ATS-based reading assistance tools and their preferences for different interface parameters of these tools. We also investigate how to evaluate these technologies with this particular user group and how they may benefit from using these tools. This summary presents the motivation for this work, positions it in the context of the related literature, and outlines the proposed solution, our current progress and the project's contributions.more » « less
-
null (Ed.)In this work, we study the question of what set of simple-to-state assumptions suffice for constructing functional encryption and indistinguishability obfuscation (IO), supporting all functions describable by polynomial-size circuits. Our work improves over the state-of-the-art work of Jain, Lin, Matt, and Sahai (Eurocrypt 2019) in multiple dimensions. New Assumption: Previous to our work, all constructions of IO from simple assumptions required novel pseudorandomness generators involving LWE samples and constant-degree polynomials over the integers, evaluated on the error of the LWE samples. In contrast, Boolean pseudorandom generators (PRGs) computable by constant-degree polynomials have been extensively studied since the work of Goldreich (2000). (Goldreich and follow-up works study Boolean pseudorandom generators with constant-locality, which can be computed by constant-degree polynomials.) We show how to replace the novel pseudorandom objects over the integers used in previous works, with appropriate Boolean pseudorandom generators with sufficient stretch, when combined with LWE with binary error over suitable parameters. Both binary error LWE and constant degree Goldreich PRGs have been a subject of extensive cryptanalysis since much before our work and thus we back the plausibility of our assumption with security against algorithms studied in context of cryptanalysis of these objects. New Techniques: we introduce a number of new techniques: – We show how to build partially-hiding public-key functional encryption, supporting degree-2 functions in the secret part of the message, and arithmetic NC1 functions over the public part of the message, assuming only standard assumptions over asymmetric pairing groups. – We construct single-ciphertext secret-key functional encryption for all circuits with linear key generation, assuming only the LWE assumption. Simplification: Unlike prior works, our new techniques furthermore let us construct public-key functional encryption for polynomial-sized circuits directly (without invoking any bootstrapping theorem, nor transformation from secret-key to public key FE), and based only on the polynomial hardness of underlying assumptions. The functional encryption scheme satisfies a strong notion of efficiency where the size of the ciphertext grows only sublinearly in the output size of the circuit and not its size. Finally, assuming that the underlying assumptions are subexponentially hard, we can bootstrap this construction to achieve iO.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.18653/v1/2021.findings-acl.455
