Papers by Michael Gertz
CQE: A Comprehensive Quantity Extractor (2023.emnlp-main)
Copied to clipboard
| Challenge: | Quantities are essential in documents to describe factual information. |
| Approach: | They propose a comprehensive quantity extraction framework that detects combinations of values and units, the behavior of a quantity and the concept a quantity is associated with. |
| Outcome: | The proposed framework outperforms existing methods and is the first to detect concepts associated with identified quantities. |
Numbers Matter! Bringing Quantity-awareness to Retrieval Systems (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Quantitative information is important for understanding documents and interpreting them. |
| Approach: | They propose two quantity-aware ranking techniques that rank both quantity and textual content . they use available retrieval systems to incorporate quantity information into queries . |
| Outcome: | The proposed methods can rank both quantity and textual content, either jointly or independently. |
EUR-Lex-Sum: A Multi- and Cross-lingual Dataset for Long-form Summarization in the Legal Domain (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing summarization datasets focus on overly exposed domains and are primarily monolingual with few multilingual datasets. |
| Approach: | They propose a new summarization dataset based on manually curated document summaries from the European Union law platform EUR-Lex. |
| Outcome: | The proposed dataset is based on document summaries of legal acts from the European Union law platform (EUR-Lex). |
LexDrafter: Terminology Drafting for Legislative Documents Using Retrieval Augmented Generation (2024.lrec-main)
Copied to clipboard
| Challenge: | With the increase in legislative documents, the number of new terms and their definitions is increasing as well. |
| Approach: | They propose a framework that helps in drafting Definitions articles for legislative documents using retrieval augmented generation and existing term definitions present in different legislative documents. |
| Outcome: | The proposed framework can be used to draft Definitions articles for legislative documents using retrieval augmented generation and existing term definitions present in different legislative documents. |
Klexikon: A German Dataset for Joint Summarization and Simplification (2022.lrec-1)
Copied to clipboard
| Challenge: | Traditionally, Text Simplification is a monolingual translation task where individual sentences are "translated" into a simplified version. |
| Approach: | They propose to use a dataset to jointly simplify long source documents by combining sentences from a source and their simplified counterparts. |
| Outcome: | The proposed system can summarize and simplify long source documents using almost 2,900 documents. |
Evaluating Factual Consistency of Texts with Semantic Role Labeling (2023.starsem-1)
Copied to clipboard
| Challenge: | Existing evaluation methods rely on task-specific language models, which in turn hampers interpretation of generated scores. |
| Approach: | They propose a reference-free evaluation metric for text summarization that measures factuality . their method generates fact tuples from Semantic Role Labels, applied to both input and summary texts. |
| Outcome: | The proposed evaluation metric is comparable with state-of-the-art methods and has a stable generalization across datasets. |
Three Real-World Datasets and Neural Computational Models for Classification Tasks in Patent Landscaping (2022.emnlp-main)
Copied to clipboard
| Challenge: | Patent Landscaping is one of the central tasks of intellectual property management and involves selecting and grouping patents according to user-defined technical or application-oriented criteria. |
| Approach: | They propose to use a novel model that takes into account textual information from the patents’ full texts as well as embeddings created based on the patent’s CPC labels. |
| Outcome: | The proposed model takes into account textual information from the patents’ full texts as well as embeddings created based on the patent’s CPC labels. |