Papers by Shomir Wilson
STAPI: An Automatic Scraper for Extracting Iterative Title-Text Structure from Web Documents (2022.lrec-1)
Copied to clipboard
| Challenge: | Formal documents are organized into sections of text, each with a title . but there is no corpus of web documents annotated with titles and prose texts . cnn.com's john mccarthy and daniel mclears are working on a new title-text dataset . |
| Approach: | They propose a first title-text dataset on web documents that incorporates a wide variety of domains to facilitate downstream training. |
| Outcome: | The proposed system outperforms baseline models in terms of title-text identification. |
An Audit on the Perspectives and Challenges of Hallucinations in NLP (2024.emnlp-main)
Copied to clipboard
Pranav Narayanan Venkit, Tatiana Chakravorti, Vipul Gupta, Heidi Biggs, Mukund Srinath, Koustava Goswami, Sarah Rajtmajer, Shomir Wilson
| Challenge: | 103 peer-reviewed publications on hallucination in large language models (LLMs) are characterized by a lack of agreement with the term ‘hallucination’ in the field of NLP. |
| Approach: | They examine 103 peer-reviewed publications on hallucination in large language models (LLMs) and conduct a survey with 171 practitioners from the field of NLP and AI to capture varying perspectives on halllucination. |
| Outcome: | The findings highlight the need for explicit definitions and frameworks outlining hallucination within NLP and highlight potential challenges. |
Creation and Analysis of an International Corpus of Privacy Laws (2024.lrec-main)
Copied to clipboard
Sonu Gupta, Geetika Gopi, Harish Balaji, Ellen Poplavska, Nora O’Toole, Siddhant Arora, Thomas Norton, Norman Sadeh, Shomir Wilson
| Challenge: | a corpus of 1,043 privacy laws, regulations, and guidelines covers 183 jurisdictions . prior efforts to study privacy law in the form of privacy policies have lacked a large-scale collection . |
| Approach: | They propose a corpus of 1,043 privacy laws, regulations, and guidelines covering 183 jurisdictions. |
| Outcome: | The Privacy Law Corpus covers 1,043 privacy laws, regulations, and guidelines covering 183 jurisdictions. |
A Study of Implicit Bias in Pretrained Language Models against People with Disabilities (2022.coling-1)
Copied to clipboard
| Challenge: | Pretrained language models exhibit sociodemographic biases, such as against gender and race, raising concerns of downstream biase in language technologies. |
| Approach: | They propose to use word embedding-based and transformer-based PLMs to test for the presence of biases against people with disabilities (PWDs) |
| Outcome: | The proposed models favor ableist language, despite their sociodemographic biases against race and gender. |
Question Answering for Privacy Policies: Combining Computational and Legal Perspectives (D19-1)
Copied to clipboard
| Challenge: | Privacy policies are long and complex documents that are difficult for users to read and understand. |
| Approach: | They present a corpus of 1750 questions about privacy policies of mobile applications and over 3500 expert annotations of relevant answers. |
| Outcome: | The proposed corpus of 1750 questions on privacy policies shows that a strong neural baseline underperforms human performance by almost 0.3 F1 on PrivacyQA. |
Can Third Parties Read Our Emotions? (2025.acl-long)
Copied to clipboard
Jiayi Li, Yingfan Zhou, Pranav Narayanan Venkit, Halima Binte Islam, Sneha Arya, Shomir Wilson, Sarah Rajtmajer
| Challenge: | Existing approaches to infer author’s private states from written text have relied heavily on datasets annotated by third-party annotators. |
| Approach: | They propose a framework for evaluating the limitations of third-party annotations and call for refined annotation practices to accurately represent and model authors’ private states. |
| Outcome: | The proposed methods outperform human annotators on emotion recognition tasks. |
A Tale of Two Regulatory Regimes: Creation and Analysis of a Bilingual Privacy Policy Corpus (2022.lrec-1)
Copied to clipboard
Siddhant Arora, Henry Hosseini, Christine Utz, Vinayshekhar Bannihatti Kumar, Tristan Dhellemmes, Abhilasha Ravichander, Peter Story, Jasmine Mangat, Rex Chen, Martin Degeling, Thomas Norton, Thomas Hupperich, Shomir Wilson, Norman Sadeh
| Challenge: | With the introduction of new privacy regulations, disclosures made by the same organization are not always the same in different languages. |
| Approach: | They propose a language annotation scheme to capture nuances of two new privacy regulations, namely the EU’s GDPR and California’s CCPA/CPRA. |
| Outcome: | The proposed method captures the nuances of two new privacy regulations and compares them to a corpus of 64 privacy policies in English and 91 in German with manual annotations for 8K and 19K fine-grained data practices. |
Privacy at Scale: Introducing the PrivaSeer Corpus of Web Privacy Policies (2021.acl-long)
Copied to clipboard
| Challenge: | Existing tools to interpret privacy policies have been used to understand them but there is a lack of large privacy policy corpora to simplify the process. |
| Approach: | They propose to use a corpus of 1,005,380 English language privacy policies collected from the web to create semi-supervised and unsupervised models to interpret and simplify privacy policies. |
| Outcome: | The proposed model outperforms all other publicly available privacy policy corpora and is ten times larger than the next largest public collection of privacy policies combined. |
Breaking Down Walls of Text: How Can NLP Benefit Consumer Privacy? (2021.acl-long)
Copied to clipboard
| Challenge: | Privacy policies are long and complex documents that are difficult for users to read and comprehend. |
| Approach: | They propose language technologies to help users reclaim control over their privacy . they highlight many remaining opportunities to develop more precise or nuanced language technologies . |
| Outcome: | The proposed language technologies can address the privacy information gap . they can be more precise or nuanced in the way they use the text of privacy policies. |
Automated Detection and Analysis of Data Practices Using A Real-World Corpus (2024.findings-acl)
Copied to clipboard
| Challenge: | a crowd-sourced annotation tool matches data practices with policy excerpts . the complexity of privacy policies often deter users from reading them . |
| Approach: | They propose an automated approach to identify and visualize data practices within privacy policies at different levels of detail. |
| Outcome: | The proposed approach matches data practices with policy excerpts at different levels of detail. |
Nationality Bias in Text Generation (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing studies have shown that nationality biases in language models can be a factor in improving the performance of social NLP models. |
| Approach: | They propose to use a text generation model, GPT-2, to analyze how the number of internet users and the country’s economic status affects the sentiment of stories. |
| Outcome: | The proposed model accentuates biases about country-based demonyms and reduces them with the use of adversarial triggering. |
The Sentiment Problem: A Critical Survey towards Deconstructing Sentiment Analysis (2023.emnlp-main)
Copied to clipboard
Pranav Venkit, Mukund Srinath, Sanjana Gautam, Saranya Venkatraman, Vipul Gupta, Rebecca Passonneau, Shomir Wilson
| Challenge: | Existing research reveals a notable absence of interdisciplinary endeavors to comprehend the social dimensions of sentiment analysis, encompassing aspects like emotion and fairness. |
| Approach: | They propose an ethics sheet encompassing critical inquiries to guide practitioners in ensuring equitable utilization of SA. |
| Outcome: | The proposed ethics sheet outlines the importance of adopting an interdisciplinary approach to defining sentiment in SA and offers a pragmatic solution for its implementation. |
Supervised and Unsupervised Methods for Robust Separation of Section Titles and Prose Text in Web Documents (D18-1)
Copied to clipboard
| Challenge: | a web text structure is underutilized, but its visual organization is useful for NLP tasks . a flexible system for extracting hierarchical section titles and prose organization is developed . |
| Approach: | a new system extracts hierarchical section titles and prose organization from web documents . the system uses features from syntax, semantics, discourse and markup to build two models . |
| Outcome: | a new system extracts the hierarchical section titles and prose organization of web documents . the system achieves an overall precision of 0.82 and a recall of 0.98 on three domains of web text . |