- PAR ID:
- 10432260
- Date Published:
- Journal Name:
- Proceedings of the 29th International Conference on Computational Linguistics
- Page Range / eLocation ID:
- 6505–6515
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
Automated text simplification aims to produce simple versions of complex texts. This task is especially useful in the medical domain, where the latest medical findings are typically communicated via complex and technical articles. This creates barriers for laypeople seeking access to up-to-date medical findings, consequently impeding progress on health literacy. Most existing work on medical text simplification has focused on monolingual settings, with the result that such evidence would be available only in just one language (most often, English). This work addresses this limitation via multilingual simplification, i.e., directly simplifying complex texts into simplified texts in multiple languages. We introduce MultiCochrane, the first sentence-aligned multilingual text simplification dataset for the medical domain in four languages: English, Spanish, French, and Farsi. We evaluate fine-tuned and zero-shot models across these languages with extensive human assessments and analyses. Although models can generate viable simplified texts, we identify several outstanding challenges that this dataset might be used to address.more » « less
-
Automated simplification models aim to make input texts more readable. Such methods have the potential to make complex information accessible to a wider audience, e.g., providing access to recent medical literature which might otherwise be impenetrable for a lay reader. However, such models risk introducing errors into automatically simplified texts, for instance by inserting statements unsupported by the corresponding original text, or by omitting key information. Providing more readable but inaccurate versions of texts may in many cases be worse than providing no such access at all. The problem of factual accuracy (and the lack thereof) has received heightened attention in the context of summarization models, but the factuality of automatically simplified texts has not been investigated. We introduce a taxonomy of errors that we use to analyze both references drawn from standard simplification datasets and state-of-the-art model outputs. We find that errors often appear in both that are not captured by existing evaluation metrics, motivating a need for research into ensuring the factual accuracy of automated simplification models.more » « less
-
Research has revealed benefits and interest among Deaf and Hard-of-Hearing (DHH) adults in reading-assistance tools powered by Automatic Text Simplification (ATS), a technology whose development benefits from evaluations by specific user groups. While prior work has provided guidance for evaluating text complexity among DHH adults, researchers lack guidance for evaluating the fluency of automatically simplified texts, which may contain errors from the simplification process. Thus, we conduct methodological research on the effectiveness of metrics (including reading speed; comprehension questions; and subjective judgements of understandability, readability, grammaticality, and system performance) for evaluating texts controlled to be at different levels of fluency, when measured among DHH participants at different literacy levels. Reading speed and grammaticality judgements effectively distinguished fluency levels among participants across literacy levels. Readability and understandability judgements, however, only worked among participants with higher literacy. Our findings provide methodological guidance for designing ATS evaluations with DHH participants.more » « less
-
Many undergraduate neuroscience trainees aspire to earn a PhD. In recent years the number, demographics, and previous experiences of PhD applicants in neuroscience has changed. This has necessitated both a reconsideration of admissions processes to ensure equity for an increasingly diverse applicant pool as well as renewed efforts to expand access to the training and research experiences required for admission to graduate programs. Here, we describe both facets of graduate school admissions by demystifying the process and providing faculty with tools and resources to help undergraduate students successfully navigate it. We discuss admissions requirements and processes at two graduate institutions, highlighting holistic approaches to evaluating students, the ever-increasing research experience expectations, and the decreasing reliance on the GRE. With a particular focus on improving equity, diversity, inclusion and belonging, we discuss resources for applying to graduate school that are available for students from underrepresented populations, including summer institutes and fellowship programs and intentional relationships with minority serving institutions (MSIs) to foster bi-directional engagement between undergraduate programs at MSIs and graduate institutions. With diverse perspectives as faculty involved in undergraduate education, graduate programs, and post-baccalaureate training programs, we provide recommendations and resources for how to help all trainees — especially those from populations underrepresented in the STEM workforce — succeed in the current graduate education admissions landscape.
-
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