Search Results for author:
Found 27 papers, 16 papers with code
UniHD@CL-SciSumm 2020: Citation Extraction as Search
This work presents the entry by the team from Heidelberg University in the CL-SciSumm 2020 shared task at the Scholarly Document Processing workshop at EMNLP 2020.
ClusterTalk: Corpus Exploration Framework using Multi-Dimensional Exploratory Search
Exploratory search of large text corpora is essential in domains like biomedical research, where large amounts of research literature are continuously generated.
Numbers Matter! Bringing Quantity-awareness to Retrieval Systems
Quantitative information plays a crucial role in understanding and interpreting the content of documents.
A first passage model of intravitreal drug delivery and residence time, in relation to ocular geometry, individual variability, and injection location
In human eyes, we investigated the impact of variability in vitreous cavity size and eccentricity, and in injection location, on drug elimination.
LexDrafter: Terminology Drafting for Legislative Documents using Retrieval Augmented Generation
With the increase in legislative documents at the EU, the number of new terms and their definitions is increasing as well.
Evaluating Factual Consistency of Texts with Semantic Role Labeling
We introduce SRLScore, a reference-free evaluation metric designed with text summarization in mind.
CQE: A Comprehensive Quantity Extractor
Compared to other information extraction approaches, interestingly only a few works exist that describe methods for a proper extraction and representation of quantities in text.
On the State of German (Abstractive) Text Summarization
We attribute poor evaluation quality to a variety of different factors, which are investigated in more detail in this work: A lack of qualitative (and diverse) gold data considered for training, understudied (and untreated) positional biases in some of the existing datasets, and the lack of easily accessible and streamlined pre-processing strategies or analysis tools.
UniHD at TSAR-2022 Shared Task: Is Compute All We Need for Lexical Simplification?
Previous state-of-the-art models for lexical simplification consist of complex pipelines with several components, each of which requires deep technical knowledge and fine-tuned interaction to achieve its full potential.
EUR-Lex-Sum: A Multi- and Cross-lingual Dataset for Long-form Summarization in the Legal Domain
Existing summarization datasets come with two main drawbacks: (1) They tend to focus on overly exposed domains, such as news articles or wiki-like texts, and (2) are primarily monolingual, with few multilingual datasets.
Klexikon: A German Dataset for Joint Summarization and Simplification
Traditionally, Text Simplification is treated as a monolingual translation task where sentences between source texts and their simplified counterparts are aligned for training.
Ranked #1 on
Text Summarization
on Klexikon
BERT got a Date: Introducing Transformers to Temporal Tagging
By supplementing training resources with weakly labeled data from rule-based systems, our model surpasses previous works in temporal tagging and type classification, especially on rare classes.
Ranked #1 on
Temporal Tagging
on TempEval-3
Structural Text Segmentation of Legal Documents
The growing complexity of legal cases has lead to an increasing interest in legal information retrieval systems that can effectively satisfy user-specific information needs.
DeepNC: Deep Generative Network Completion
In this paper, we present DeepNC, a novel method for inferring the missing parts of a network based on a deep generative model of graphs.
TopExNet: Entity-Centric Network Topic Exploration in News Streams
The recent introduction of entity-centric implicit network representations of unstructured text offers novel ways for exploring entity relations in document collections and streams efficiently and interactively.
Retrieving Multi-Entity Associations: An Evaluation of Combination Modes for Word Embeddings
Word embeddings have gained significant attention as learnable representations of semantic relations between words, and have been shown to improve upon the results of traditional word representations.
Word Embeddings for Entity-annotated Texts
We discuss two distinct approaches to the generation of such embeddings, namely the training of state-of-the-art embeddings on raw-text and annotated versions of the corpus, as well as node embeddings of a co-occurrence graph representation of the annotated corpus.
Improving the Cluster Structure Extracted from OPTICS Plots
Density-based clustering is closely associated with the two algorithms DBSCAN and OPTICS.
HeidelPlace: An Extensible Framework for Geoparsing
Geographic information extraction from textual data sources, called geoparsing, is a key task in text processing and central to subsequent spatial analysis approaches.
Semantic Word Clouds with Background Corpus Normalization and t-distributed Stochastic Neighbor Embedding
We then select keywords based on their significance and construct the word cloud based on the derived affinity.
Extending HeidelTime for Temporal Expressions Referring to Historic Dates
Thus, references to historic dates are often not well handled by temporal taggers although they frequently occur in narrative-style documents about history, e. g., in many Wikipedia articles.
Computational Narratology: Extracting Tense Clusters from Narrative Texts
Computational Narratology is an emerging field within the Digital Humanities.
Temporal Tagging on Different Domains: Challenges, Strategies, and Gold Standards
Only recently, two temporal annotated corpora of narrative-style documents were developed, and it was shown that a domain shift results in significant challenges for temporal tagging.
