arXiv subjects

Domenic Rosati

Publications and source records attributed to Domenic Rosati.

27 records · Page 2Linked to original sources

arXiv2023

Background Knowledge Grounding for Readable, Relevant, and Factual Biomedical Lay Summaries

Communication of scientific findings to the public is important for keeping non-experts informed of developments such as life-saving medical treatments. However, generating readable lay summaries from scientific documents is challenging, and currently, these summaries suffer from critical factual errors. One popular intervention for improving factuality is using additional external knowledge to provide factual grounding. However, it is unclear how these grounding sources should be retrieved, selected, or integrated, and how supplementary grounding documents might affect the readability or relevance of the generated summaries. We develop a simple method for selecting grounding sources and integrating them with source documents. We then use the BioLaySum summarization dataset to evaluate the effects of different grounding sources on summary quality. We found that grounding source documents improves the relevance and readability of lay summaries but does not improve factuality of lay summaries. This continues to be true in zero-shot summarization settings where we hypothesized that grounding might be even more important for factual lay summaries.

cs.CL↗

arXiv2023

Measuring Reliability of Large Language Models through Semantic Consistency

While large pretrained language models (PLMs) demonstrate incredible fluency and performance on many natural language tasks, recent work has shown that well-performing PLMs are very sensitive to what prompts are feed into them. Even when prompts are semantically identical, language models may give very different answers. When considering safe and trustworthy deployments of PLMs we would like their outputs to be consistent under prompts that mean the same thing or convey the same intent. While some work has looked into how state-of-the-art PLMs address this need, they have been limited to only evaluating lexical equality of single- or multi-word answers and do not address consistency of generative text sequences. In order to understand consistency of PLMs under text generation settings, we develop a measure of semantic consistency that allows the comparison of open-ended text outputs. We implement several versions of this consistency metric to evaluate the performance of a number of PLMs on paraphrased versions of questions in the TruthfulQA dataset, we find that our proposed metrics are considerably more consistent than traditional metrics embodying lexical consistency, and also correlate with human evaluation of output consistency to a higher degree.

cs.CL↗

arXiv2023

Discovering substantive disagreement with review articles?

Disagreements help drive science. How does one identify and track them in scholarly literature? We ask the research question will searching review articles (RA) will be more time efficient for this purpose than searching non-review ones (NRA). This is especially so to the extent NRAs exceed RAs in a given field. We also discuss a metric for whether RAs report more substantive disagreements than NRAs.

cs.DL↗

arXiv2022

Moving beyond word lists: towards abstractive topic labels for human-like topics of scientific documents

Topic models represent groups of documents as a list of words (the topic labels). This work asks whether an alternative approach to topic labeling can be developed that is closer to a natural language description of a topic than a word list. To this end, we present an approach to generating human-like topic labels using abstractive multi-document summarization (MDS). We investigate our approach with an exploratory case study. We model topics in citation sentences in order to understand what further research needs to be done to fully operationalize MDS for topic labeling. Our case study shows that in addition to more human-like topics there are additional advantages to evaluation by using clustering and summarization measures instead of topic model measures. However, we find that there are several developments needed before we can design a well-powered study to evaluate MDS for topic modeling fully. Namely, improving cluster cohesion, improving the factuality and faithfulness of MDS, and increasing the number of documents that might be supported by MDS. We present a number of ideas on how these can be tackled and conclude with some thoughts on how topic modeling can also be used to improve MDS in general.

cs.CL↗

arXiv2022

Title detection: a novel approach to automatically finding retractions and other editorial notices in the scholarly literature

Despite being a key element in the process of disseminating scientific knowledge, editorial notices are often obscured and not clearly linked to the papers to which they refer. In the present paper, we describe established methods of aggregating notice data, and introduce a novel method of finding editorial notices in the scientific literature. Specifically, we describe how article titles denote notices to existing publications, and how this information can be used to tie notices to papers in an automated fashion. Finally, as part of a broader movement to make science more transparent, we make notices detected through this and other methods publicly available and describe this dataset and how it can be accessed.

cs.DL↗

arXiv2022

SynSciPass: detecting appropriate uses of scientific text generation

Approaches to machine generated text detection tend to focus on binary classification of human versus machine written text. In the scientific domain where publishers might use these models to examine manuscripts under submission, misclassification has the potential to cause harm to authors. Additionally, authors may appropriately use text generation models such as with the use of assistive technologies like translation tools. In this setting, a binary classification scheme might be used to flag appropriate uses of assistive text generation technology as simply machine generated which is a cause of concern. In our work, we simulate this scenario by presenting a state-of-the-art detector trained on the DAGPap22 with machine translated passages from Scielo and find that the model performs at random. Given this finding, we develop a framework for dataset development that provides a nuanced approach to detecting machine generated text by having labels for the type of technology used such as for translation or paraphrase resulting in the construction of SynSciPass. By training the same model that performed well on DAGPap22 on SynSciPass, we show that not only is the model more robust to domain shifts but also is able to uncover the type of technology used for machine generated text. Despite this, we conclude that current datasets are neither comprehensive nor realistic enough to understand how these models would perform in the wild where manuscript submissions can come from many unknown or novel distributions, how they would perform on scientific full-texts rather than small passages, and what might happen when there is a mix of appropriate and inappropriate uses of natural language generation.

cs.CL↗

arXiv2022

Learning to pronounce as measuring cross-lingual joint orthography-phonology complexity

Machine learning models allow us to compare languages by showing how hard a task in each language might be to learn and perform well on. Following this line of investigation, we explore what makes a language "hard to pronounce" by modelling the task of grapheme-to-phoneme (g2p) transliteration. By training a character-level transformer model on this task across 22 languages and measuring the model's proficiency against its grapheme and phoneme inventories, we show that certain characteristics emerge that separate easier and harder languages with respect to learning to pronounce. Namely the complexity of a language's pronunciation from its orthography is due to the expressive or simplicity of its grapheme-to-phoneme mapping. Further discussion illustrates how future studies should consider relative data sparsity per language to design fairer cross-lingual comparison tasks.

cs.CL↗

arXiv2021

Citations are not opinions: a corpus linguistics approach to understanding how citations are made

Citation content analysis seeks to understand citations based on the language used during the making of a citation. A key issue in citation content analysis is looking for linguistic structures that characterize distinct classes of citations for the purposes of understanding the intent and function of a citation. Previous works have focused on modeling linguistic features first and drawn conclusions on the language structures unique to each class of citation function based on the performance of a classification task or inter-annotator agreement. In this study, we start with a large sample of a pre-classified citation corpus, 2 million citations from each class of the scite Smart Citation dataset (supporting, disputing, and mentioning citations), and analyze its corpus linguistics in order to reveal the unique and statistically significant language structures belonging to each type of citation. By generating comparison tables for each citation type we present a number of interesting linguistic features that uniquely characterize citation type. What we find is that within citation collocates, there is very low correlation between citation type and sentiment. Additionally, we find that the subjectivity of citation collocates across classes is very low. These findings suggest that the sentiment of collocates is not a predictor of citation function and that due to their low subjectivity, an opinion-expressing mode of understanding citations, implicit in previous citation sentiment analysis literature, is inappropriate. Instead, we suggest that citations can be better understood as claims-making devices where the citation type can be explained by understanding how two claims are being compared. By presenting this approach, we hope to inspire similar corpus linguistic studies on citations that derive a more robust theory of citation from an empirical basis using citation corpora

cs.DL↗

arXiv2021

How are journals cited? characterizing journal citations by type of citation

Evaluation of journals for quality is one of the dominant themes of bibliometrics since journals are the primary venue of vetting and distribution of scholarship. There are many criticisms of quantifying journal impact with bibliometrics including disciplinary differences among journals, what source materials are used, time windows for the inclusion of works to measure, and skewness of citation distributions (Lariviere & Sugimoto, 2019). However, despite various attempts to remediate these in newly proposed indicators such as SJR, SNIP, and Eigenfactor (Walters, 2017) indicators still remain based on citation counts and fail to acknowledge the critical differences that the type of citation made, whether it's supporting or disputing a work when quantifying journal impact. While various programs have been suggested to apply and encompass citation content analysis within bibliometrics projects, citation content analysis has not been done at the scale needed in order to supplement quantitate journal citation analysis until the scite citation index was produced. Using this citation index containing citation types based on citation function (supporting, disputing, or mentioning) we present initial results on the statistical characterization of citations to journals based on citation function. We also present initial results of characterizing the ratio of supports and disputes received by a journal as a potential indicator of quality and show two interesting results: the ratio of supports and disputes do not correlate with total citations and that the distribution of this ratio is not skewed showing a normal distribution. We conclude with a proposal for future research using citation analysis qualified by citation function as well as the implications of performing bibliometrics tasks such as research evaluation and information retrieval using citation function.

cs.DL↗