Search Results for author:
Found 79 papers, 35 papers with code
The Robotic Surgery Procedural Framebank
Robot-Assisted minimally invasive robotic surgery is the gold standard for the surgical treatment of many pathological conditions, and several manuals and academic papers describe how to perform these interventions.
Masking and Transformer-based Models for Hyperpartisanship Detection in News
Hyperpartisan news show an extreme manipulation of reality based on an underlying and extreme ideological orientation.
FrameASt: A Framework for Second-level Agenda Setting in Parliamentary Debates through the Lense of Comparative Agenda Topics
In addition, we present a new annotated data set of parliamentary debates, following the coding schema of policy topics developed in the Comparative Agendas Project (CAP), and release models for topic classification in parliamentary debates.
Come hither or go away? Recognising pre-electoral coalition signals in the news
In this paper, we introduce the task of political coalition signal prediction from text, that is, the task of recognizing from the news coverage leading up to an election the (un)willingness of political parties to form a government coalition.
DeTikZify: Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ
Creating high-quality scientific figures can be time-consuming and challenging, even though sketching ideas on paper is relatively easy.
ROUGE-K: Do Your Summaries Have Keywords?
Keywords, that is, content-relevant words in summaries play an important role in efficient information conveyance, making it critical to assess if system-generated summaries contain such informative words during evaluation.
ACLSum: A New Dataset for Aspect-based Summarization of Scientific Publications
Extensive efforts in the past have been directed toward the development of summarization datasets.
Do LLMs Dream of Ontologies?
Large language models (LLMs) have recently revolutionized automated text understanding and generation.
Vicinal Risk Minimization for Few-Shot Cross-lingual Transfer in Abusive Language Detection
In this work, we resort to data augmentation and continual pre-training for domain adaptation to improve cross-lingual abusive language detection.
Multi-Source (Pre-)Training for Cross-Domain Measurement, Unit and Context Extraction
We present a cross-domain approach for automated measurement and context extraction based on pre-trained language models.
Can Demographic Factors Improve Text Classification? Revisiting Demographic Adaptation in the Age of Transformers
Previous work showed that incorporating demographic factors can consistently improve performance for various NLP tasks with traditional NLP models.
Overview of the SV-Ident 2022 Shared Task on Survey Variable Identification in Social Science Publications
In this paper, we provide an overview of the SV-Ident shared task as part of the 3rd Workshop on Scholarly Document Processing (SDP) at COLING 2022.
Ranked #1 on
Variable Disambiguation
on SV-Ident
Towards Automated Survey Variable Search and Summarization in Social Science Publications
Nowadays there is a growing trend in many scientific disciplines to support researchers by providing enhanced information access through linking of publications and underlying datasets, so as to support research with infrastructure to enhance reproducibility and reusability of research results.
Massively Multilingual Lexical Specialization of Multilingual Transformers
While pretrained language models (PLMs) primarily serve as general-purpose text encoders that can be fine-tuned for a wide variety of downstream tasks, recent work has shown that they can also be rewired to produce high-quality word representations (i. e., static word embeddings) and yield good performance in type-level lexical tasks.
On the Limitations of Sociodemographic Adaptation with Transformers
We adapt the language representations for the sociodemographic dimensions of gender and age, using continuous language modeling and dynamic multi-task learning for adaptation, where we couple language modeling with the prediction of a sociodemographic class.
X-SCITLDR: Cross-Lingual Extreme Summarization of Scholarly Documents
The number of scientific publications nowadays is rapidly increasing, causing information overload for researchers and making it hard for scholars to keep up to date with current trends and lines of work.
ZusammenQA: Data Augmentation with Specialized Models for Cross-lingual Open-retrieval Question Answering System
This paper introduces our proposed system for the MIA Shared Task on Cross-lingual Open-retrieval Question Answering (COQA).
Multi2WOZ: A Robust Multilingual Dataset and Conversational Pretraining for Task-Oriented Dialog
We then introduce a new framework for multilingual conversational specialization of pretrained language models (PrLMs) that aims to facilitate cross-lingual transfer for arbitrary downstream TOD tasks.
Fair and Argumentative Language Modeling for Computational Argumentation
We employ our resource to assess the effect of argumentative fine-tuning and debiasing on the intrinsic bias found in transformer-based language models using a lightweight adapter-based approach that is more sustainable and parameter-efficient than full fine-tuning.
PET: An Annotated Dataset for Process Extraction from Natural Language Text
Therefore, to bridge this gap, we present the PET dataset, a first corpus of business process descriptions annotated with activities, gateways, actors, and flow information.
On Cross-Lingual Retrieval with Multilingual Text Encoders
In this work we present a systematic empirical study focused on the suitability of the state-of-the-art multilingual encoders for cross-lingual document and sentence retrieval tasks across a number of diverse language pairs.
DS-TOD: Efficient Domain Specialization for Task Oriented Dialog
Recent work has shown that self-supervised dialog-specific pretraining on large conversational datasets yields substantial gains over traditional language modeling (LM) pretraining in downstream task-oriented dialog (TOD).
Process Extraction from Text: Benchmarking the State of the Art and Paving the Way for Future Challenges
The extraction of process models from text refers to the problem of turning the information contained in an unstructured textual process descriptions into a formal representation, i. e., a process model.
Diachronic Analysis of German Parliamentary Proceedings: Ideological Shifts through the Lens of Political Biases
We analyze bias in historical corpora as encoded in diachronic distributional semantic models by focusing on two specific forms of bias, namely a political (i. e., anti-communism) and racist (i. e., antisemitism) one.
Large-scale Taxonomy Induction Using Entity and Word Embeddings
Taxonomies are an important ingredient of knowledge organization, and serve as a backbone for more sophisticated knowledge representations in intelligent systems, such as formal ontologies.
DebIE: A Platform for Implicit and Explicit Debiasing of Word Embedding Spaces
In this work, we present DebIE, the first integrated platform for (1) measuring and (2) mitigating bias in word embeddings.
FakeFlow: Fake News Detection by Modeling the Flow of Affective Information
To capture this, we propose in this paper to model the flow of affective information in fake news articles using a neural architecture.
Evaluating Multilingual Text Encoders for Unsupervised Cross-Lingual Retrieval
Therefore, in this work we present a systematic empirical study focused on the suitability of the state-of-the-art multilingual encoders for cross-lingual document and sentence retrieval tasks across a large number of language pairs.
Self-Supervised Learning for Visual Summary Identification in Scientific Publications
Providing visual summaries of scientific publications can increase information access for readers and thereby help deal with the exponential growth in the number of scientific publications.
SemEval-2020 Task 2: Predicting Multilingual and Cross-Lingual (Graded) Lexical Entailment
The shared task spans three dimensions: (1) monolingual vs. cross-lingual LE, (2) binary vs. graded LE, and (3) a set of 6 diverse languages (and 15 corresponding language pairs).
AraWEAT: Multidimensional Analysis of Biases in Arabic Word Embeddings
Our analysis yields several interesting findings, e. g., that implicit gender bias in embeddings trained on Arabic news corpora steadily increases over time (between 2007 and 2017).
Word Sense Disambiguation for 158 Languages using Word Embeddings Only
We use this method to induce a collection of sense inventories for 158 languages on the basis of the original pre-trained fastText word embeddings by Grave et al. (2018), enabling WSD in these languages.
Policy Preference Detection in Parliamentary Debate Motions
Debate motions (proposals) tabled in the UK Parliament contain information about the stated policy preferences of the Members of Parliament who propose them, and are key to the analysis of all subsequent speeches given in response to them.
SEAGLE: A Platform for Comparative Evaluation of Semantic Encoders for Information Retrieval
We introduce Seagle, a platform for comparative evaluation of semantic text encoding models on information retrieval (IR) tasks.
FacTweet: Profiling Fake News Twitter Accounts
We present an approach to detect fake news in Twitter at the account level using a neural recurrent model and a variety of different semantic and stylistic features.
A General Framework for Implicit and Explicit Debiasing of Distributional Word Vector Spaces
Moreover, we successfully transfer debiasing models, by means of cross-lingual embedding spaces, and remove or attenuate biases in distributional word vector spaces of languages that lack readily available bias specifications.
Multilingual and Cross-Lingual Graded Lexical Entailment
Starting from HyperLex, the only available GR-LE dataset in English, we construct new monolingual GR-LE datasets for three other languages, and combine those to create a set of six cross-lingual GR-LE datasets termed CL-HYPERLEX.
Computational Analysis of Political Texts: Bridging Research Efforts Across Communities
Political scientists created resources and used available NLP methods to process textual data largely in isolation from the NLP community.
Unmasking Bias in News
We present experiments on detecting hyperpartisanship in news using a 'masking' method that allows us to assess the role of style vs. content for the task at hand.
HHMM at SemEval-2019 Task 2: Unsupervised Frame Induction using Contextualized Word Embeddings
We present our system for semantic frame induction that showed the best performance in Subtask B. 1 and finished as the runner-up in Subtask A of the SemEval 2019 Task 2 on unsupervised semantic frame induction (QasemiZadeh et al., 2019).
Knowledge-rich Image Gist Understanding Beyond Literal Meaning
We investigate the problem of understanding the message (gist) conveyed by images and their captions as found, for instance, on websites or news articles.
Political Text Scaling Meets Computational Semantics
During the last fifteen years, automatic text scaling has become one of the key tools of the Text as Data community in political science.
Event-based Access to Historical Italian War Memoirs
The progressive digitization of historical archives provides new, often domain specific, textual resources that report on facts and events which have happened in the past; among these, memoirs are a very common type of primary source.
An Argument-Annotated Corpus of Scientific Publications
We analyze the annotated argumentative structures and investigate the relations between argumentation and other rhetorical aspects of scientific writing, such as discourse roles and citation contexts.
Investigating the Role of Argumentation in the Rhetorical Analysis of Scientific Publications with Neural Multi-Task Learning Models
Exponential growth in the number of scientific publications yields the need for effective automatic analysis of rhetorical aspects of scientific writing.
Unsupervised Sense-Aware Hypernymy Extraction
In this paper, we show how unsupervised sense representations can be used to improve hypernymy extraction.
Watset: Local-Global Graph Clustering with Applications in Sense and Frame Induction
We present a detailed theoretical and computational analysis of the Watset meta-algorithm for fuzzy graph clustering, which has been found to be widely applicable in a variety of domains.
UniMa at SemEval-2018 Task 7: Semantic Relation Extraction and Classification from Scientific Publications
Large repositories of scientific literature call for the development of robust methods to extract information from scholarly papers.
Unsupervised Semantic Frame Induction using Triclustering
We use dependency triples automatically extracted from a Web-scale corpus to perform unsupervised semantic frame induction.
Unsupervised Cross-Lingual Information Retrieval using Monolingual Data Only
We propose a fully unsupervised framework for ad-hoc cross-lingual information retrieval (CLIR) which requires no bilingual data at all.
An Unsupervised Word Sense Disambiguation System for Under-Resourced Languages
The sparse mode uses the traditional vector space model to estimate the most similar word sense corresponding to its context.
Enriching Frame Representations with Distributionally Induced Senses
We introduce a new lexical resource that enriches the Framester knowledge graph, which links Framnet, WordNet, VerbNet and other resources, with semantic features from text corpora.
A Resource-Light Method for Cross-Lingual Semantic Textual Similarity
In contrast, we propose an unsupervised and a very resource-light approach for measuring semantic similarity between texts in different languages.
Cross-Lingual Information Retrieval
Cross-Lingual Semantic Textual Similarity
+9
A Framework for Enriching Lexical Semantic Resources with Distributional Semantics
While both kinds of semantic resources are available with high lexical coverage, our aligned resource combines the domain specificity and availability of contextual information from distributional models with the conciseness and high quality of manually crafted lexical networks.
Building a Web-Scale Dependency-Parsed Corpus from CommonCrawl
We present DepCC, the largest-to-date linguistically analyzed corpus in English including 365 million documents, composed of 252 billion tokens and 7. 5 billion of named entity occurrences in 14. 3 billion sentences from a web-scale crawl of the \textsc{Common Crawl} project.
Effects of Lexical Properties on Viewing Time per Word in Autistic and Neurotypical Readers
Eye tracking studies from the past few decades have shaped the way we think of word complexity and cognitive load: words that are long, rare and ambiguous are more difficult to read.
Topic-Based Agreement and Disagreement in US Electoral Manifestos
We present a topic-based analysis of agreement and disagreement in political manifestos, which relies on a new method for topic detection based on key concept clustering.
Dual Tensor Model for Detecting Asymmetric Lexico-Semantic Relations
Detection of lexico-semantic relations is one of the central tasks of computational semantics.
Cross-Lingual Classification of Topics in Political Texts
In this paper, we propose an approach for cross-lingual topical coding of sentences from electoral manifestos of political parties in different languages.
Unsupervised, Knowledge-Free, and Interpretable Word Sense Disambiguation
In word sense disambiguation (WSD), knowledge-based systems tend to be much more interpretable than knowledge-free counterparts as they rely on the wealth of manually-encoded elements representing word senses, such as hypernyms, usage examples, and images.
Exploring Neural Text Simplification Models
Unlike the previously proposed automated TS systems, our neural text simplification (NTS) systems are able to simultaneously perform lexical simplification and content reduction.
Ranked #14 on
Text Simplification
on TurkCorpus
Sentence Alignment Methods for Improving Text Simplification Systems
We provide several methods for sentence-alignment of texts with different complexity levels.
Using Linked Disambiguated Distributional Networks for Word Sense Disambiguation
We introduce a new method for unsupervised knowledge-based word sense disambiguation (WSD) based on a resource that links two types of sense-aware lexical networks: one is induced from a corpus using distributional semantics, the other is manually constructed.
Improving Neural Knowledge Base Completion with Cross-Lingual Projections
We exploit multilingual synsets from BabelNet to translate English triples to other languages and then augment the reference knowledge base with cross-lingual triples.
Unsupervised Cross-Lingual Scaling of Political Texts
Political text scaling aims to linearly order parties and politicians across political dimensions (e. g., left-to-right ideology) based on textual content (e. g., politician speeches or party manifestos).
The ContrastMedium Algorithm: Taxonomy Induction From Noisy Knowledge Graphs With Just A Few Links
In this paper, we present ContrastMedium, an algorithm that transforms noisy semantic networks into full-fledged, clean taxonomies.
Unsupervised Does Not Mean Uninterpretable: The Case for Word Sense Induction and Disambiguation
On the example of word sense induction and disambiguation (WSID), we show that it is possible to develop an interpretable model that matches the state-of-the-art models in accuracy.
A Large DataBase of Hypernymy Relations Extracted from the Web.
Hypernymy relations (those where an hyponym term shares a {``}isa{''} relationship with his hypernym) play a key role for many Natural Language Processing (NLP) tasks, e. g. ontology learning, automatically building or extending knowledge bases, or word sense disambiguation and induction.
DBpedia Domains: augmenting DBpedia with domain information
We present an approach for augmenting DBpedia, a very large ontology lying at the heart of the Linked Open Data (LOD) cloud, with domain information.
