Search Results for author:
Found 152 papers, 39 papers with code
Social Media Unrest Prediction during the COVID-19 Pandemic: Neural Implicit Motive Pattern Recognition as Psychometric Signs of Severe Crises
We employ this model to investigate a change of language towards social unrest during the COVID-19 pandemic by comparing established psychological predictors on samples of tweets from spring 2019 with spring 2020.
Classification of German Jungian Extraversion and Introversion Texts with Assessment of Changes During the COVID-19 Pandemic
It can be assumed that the Jungian psychology types of extraverts and introverts react differently to these challenges.
Question Answering Classification for Amharic Social Media Community Based Questions
Questions are posted in Amharic, English, or Amharic but in a Latin script.
Error Analysis of using BART for Multi-Document Summarization: A Study for English and German Language
Recent research using pre-trained language models for multi-document summarization task lacks deep investigation of potential erroneous cases and their possible application on other languages.
Elvis vs. M. Jackson: Who has More Albums? Classification and Identification of Elements in Comparative Questions
Comparative Question Answering (cQA) is the task of providing concrete and accurate responses to queries such as: “Is Lyft cheaper than a regular taxi?” or “What makes a mortgage different from a regular loan?”.
MOTIF: Contextualized Images for Complex Words to Improve Human Reading
In this respect, several traditional NLP approaches can assist L2 readers in text comprehension processes, such as simplifying text or giving dictionary descriptions for complex words.
Dataset of Student Solutions to Algorithm and Data Structure Programming Assignments
We present a dataset containing source code solutions to algorithmic programming exercises solved by hundreds of Bachelor-level students at the University of Hamburg.
Improved Open Source Automatic Subtitling for Lecture Videos
Ranked #2 on
Speech Recognition
on TUDA
(using extra training data)
An Investigation towards Differentially Private Sequence Tagging in a Federated Framework
In this paper, we investigate the applicability of a privacy-preserving framework for sequence tagging tasks, specifically NER.
Generating Lexical Representations of Frames using Lexical Substitution
We investigate a simple yet effective method, lexical substitution with word representation models, to automatically expand a small set of frame-annotated sentences with new words for their respective roles and LUs.
Probing Pre-trained Language Models for Semantic Attributes and their Values
Pretrained language models (PTLMs) yield state-of-the-art performance on many natural language processing tasks, including syntax, semantics and commonsense.
Centurio: On Drivers of Multilingual Ability of Large Vision-Language Model
Most Large Vision-Language Models (LVLMs) to date are trained predominantly on English data, which makes them struggle to understand non-English input and fail to generate output in the desired target language.
CogSteer: Cognition-Inspired Selective Layer Intervention for Efficient Semantic Steering in Large Language Models
Despite their impressive capabilities, large language models (LLMs) often lack interpretability and can generate toxic content.
Large Language Models Are Overparameterized Text Encoders
We evaluate four different state-of-the-art LLMs on text embedding tasks and find that our method can prune up to 30\% of layers with negligible impact on performance and up to 80\% with only a modest drop.
Demarked: A Strategy for Enhanced Abusive Speech Moderation through Counterspeech, Detoxification, and Message Management
Despite regulations imposed by nations and social media platforms, such as recent EU regulations targeting digital violence, abusive content persists as a significant challenge.
Low-Resource Machine Translation through the Lens of Personalized Federated Learning
We present a new approach called MeritOpt based on the Personalized Federated Learning algorithm MeritFed that can be applied to Natural Language Tasks with heterogeneous data.
Dataset of Quotation Attribution in German News Articles
We specify our annotation schema, describe the creation of the dataset and provide a quantitative analysis.
Exploring Boundaries and Intensities in Offensive and Hate Speech: Unveiling the Complex Spectrum of Social Media Discourse
The prevalence of digital media and evolving sociopolitical dynamics have significantly amplified the dissemination of hateful content.
Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding
Our method is inspired by our observation that what we call disturbance instructions significantly exacerbate hallucinations in multimodal fusion modules.
On Zero-Shot Counterspeech Generation by LLMs
In terms of prompting, we find that our proposed strategies help in improving counter speech generation across all the models.
SemRel2024: A Collection of Semantic Textual Relatedness Datasets for 13 Languages
Exploring and quantifying semantic relatedness is central to representing language and holds significant implications across various NLP tasks.
Probing Large Language Models from A Human Behavioral Perspective
Large Language Models (LLMs) have emerged as dominant foundational models in modern NLP.
DBLPLink: An Entity Linker for the DBLP Scholarly Knowledge Graph
In this work, we present a web application named DBLPLink, which performs entity linking over the DBLP scholarly knowledge graph.
The Role of Output Vocabulary in T2T LMs for SPARQL Semantic Parsing
In this work, we analyse the role of output vocabulary for text-to-text (T2T) models on the task of SPARQL semantic parsing.
GETT-QA: Graph Embedding based T2T Transformer for Knowledge Graph Question Answering
To further improve the results, we instruct the model to produce a truncated version of the KG embedding for each entity.
DBLP-QuAD: A Question Answering Dataset over the DBLP Scholarly Knowledge Graph
In this work we create a question answering dataset over the DBLP scholarly knowledge graph (KG).
A System for Human-AI collaboration for Online Customer Support
AI enabled chat bots have recently been put to use to answer customer service queries, however it is a common feedback of users that bots lack a personal touch and are often unable to understand the real intent of the user's question.
ARDIAS: AI-Enhanced Research Management, Discovery, and Advisory System
In this work, we present ARDIAS, a web-based application that aims to provide researchers with a full suite of discovery and collaboration tools.
Modern Baselines for SPARQL Semantic Parsing
In this work, we focus on the task of generating SPARQL queries from natural language questions, which can then be executed on Knowledge Graphs (KGs).
SCoT: Sense Clustering over Time: a tool for the analysis of lexical change
There are two main approaches to the exploration of dynamic networks: the discrete one compares a series of clustered graphs from separate points in time.
Language Models Explain Word Reading Times Better Than Empirical Predictability
(3) In recurrent neural networks (RNNs), the subsymbolic units are trained to predict the next word, given all preceding words in the sentences.
How Hateful are Movies? A Study and Prediction on Movie Subtitles
Hence, we show that transfer learning from the social media domain is efficacious in classifying hate and offensive speech in movies through subtitles.
ActiveAnno: General-Purpose Document-Level Annotation Tool with Active Learning Integration
ActiveAnno is built with extensible design and easy deployment in mind, all to enable users to perform annotation tasks with high efficiency and high-quality annotation results.
Towards Multi-Modal Text-Image Retrieval to improve Human Reading
In primary school, children{'}s books, as well as in modern language learning apps, multi-modal learning strategies like illustrations of terms and phrases are used to support reading comprehension.
Towards Layered Events and Schema Representations in Long Documents
In this thesis proposal, we explore the application of event extraction to literary texts.
Word Complexity is in the Eye of the Beholder
Lexical complexity is a highly subjective notion, yet this factor is often neglected in lexical simplification and readability systems which use a {''}one-size-fits-all{''} approach.
Forum 4.0: An Open-Source User Comment Analysis Framework
With the increasing number of user comments in diverse domains, including comments on online journalism and e-commerce websites, the manual content analysis of these comments becomes time-consuming and challenging.
HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection
We also observe that models, which utilize the human rationales for training, perform better in reducing unintended bias towards target communities.
Ranked #3 on
Hate Speech Detection
on HateXplain
Social Media Unrest Prediction during the {COVID}-19 Pandemic: Neural Implicit Motive Pattern Recognition as Psychometric Signs of Severe Crises
We employ this model to investigate a change of language towards social unrest during the COVID-19 pandemic by comparing established psychological predictors on samples of tweets from spring 2019 with spring 2020.
Exploring Amharic Sentiment Analysis from Social Media Texts: Building Annotation Tools and Classification Models
To advance the sentiment analysis research in Amharic and other related low-resource languages, we release the dataset, the annotation tool, source code, and models publicly under a permissive.
Introducing various Semantic Models for Amharic: Experimentation and Evaluation with multiple Tasks and Datasets
We find that newly trained models perform better than pre-trained multilingual models.
Individual corpora predict fast memory retrieval during reading
Then we trained word2vec models from individual corpora and a 70 million-sentence newspaper corpus to obtain individual and norm-based long-term memory structure.
Estimating the influence of auxiliary tasks for multi-task learning of sequence tagging tasks
We propose new methods to automatically assess the similarity of sequence tagging datasets to identify beneficial auxiliary data for MTL or TL setups.
Neural Entity Linking: A Survey of Models Based on Deep Learning
This survey presents a comprehensive description of recent neural entity linking (EL) systems developed since 2015 as a result of the "deep learning revolution" in natural language processing.
Improving Unsupervised Sparsespeech Acoustic Models with Categorical Reparameterization
The model is trained on 600h and 6000h of English read speech.
Ranked #2 on
Speech Recognition
on Libri-Light test-other
(ABX-within metric)
UHH-LT at SemEval-2020 Task 12: Fine-Tuning of Pre-Trained Transformer Networks for Offensive Language Detection
Fine-tuning of pre-trained transformer networks such as BERT yield state-of-the-art results for text classification tasks.
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.
Automatic Compilation of Resources for Academic Writing and Evaluating with Informal Word Identification and Paraphrasing System
The aim is to build a writing aid system that automatically edits a text so that it better adheres to the academic style of writing.
Analysis of the Ethiopic Twitter Dataset for Abusive Speech in Amharic
Since several languages can be written using the Fidel script, we have used the existing Amharic, Tigrinya and Ge'ez corpora to retain only the Amharic tweets.
Does BERT Make Any Sense? Interpretable Word Sense Disambiguation with Contextualized Embeddings
Since vectors of the same word type can vary depending on the respective context, they implicitly provide a model for word sense disambiguation (WSD).
TARGER: Neural Argument Mining at Your Fingertips
We present TARGER, an open source neural argument mining framework for tagging arguments in free input texts and for keyword-based retrieval of arguments from an argument-tagged web-scale corpus.
Improving Neural Entity Disambiguation with Graph Embeddings
Entity Disambiguation (ED) is the task of linking an ambiguous entity mention to a corresponding entry in a knowledge base.
Hierarchical Multi-label Classification of Text with Capsule Networks
Capsule networks have been shown to demonstrate good performance on structured data in the area of visual inference.
On the Compositionality Prediction of Noun Phrases using Poincar\'e Embeddings
In particular, we use hypernymy information of the multiword and its constituents encoded in the form of the recently introduced Poincar{\'e} embeddings in addition to the distributional information to detect compositionality for noun phrases.
Making Fast Graph-based Algorithms with Graph Metric Embeddings
The computation of distance measures between nodes in graphs is inefficient and does not scale to large graphs.
Adversarial Learning of Privacy-Preserving Text Representations for De-Identification of Medical Records
De-identification is the task of detecting protected health information (PHI) in medical text.
On the Compositionality Prediction of Noun Phrases using Poincaré Embeddings
In particular, we use hypernymy information of the multiword and its constituents encoded in the form of the recently introduced Poincar\'e embeddings in addition to the distributional information to detect compositionality for noun phrases.
Every child should have parents: a taxonomy refinement algorithm based on hyperbolic term embeddings
We introduce the use of Poincar\'e embeddings to improve existing state-of-the-art approaches to domain-specific taxonomy induction from text as a signal for both relocating wrong hyponym terms within a (pre-induced) taxonomy as well as for attaching disconnected terms in a taxonomy.
Reviving a psychometric measure: Classification and prediction of the Operant Motive Test
In addition, we found a significant correlation of r = . 2 between subsequent academic success and data automatically labeled with our model in an extrinsic evaluation.
LT Expertfinder: An Evaluation Framework for Expert Finding Methods
Particularly for dynamic systems, where topics are not predefined but formulated as a search query, we believe a more informative approach is to perform user studies for directly comparing different methods in the same view.
UHH-LT at SemEval-2019 Task 6: Supervised vs. Unsupervised Transfer Learning for Offensive Language Detection
We present a neural network based approach of transfer learning for offensive language detection.
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).
Language-Agnostic Model for Aspect-Based Sentiment Analysis
In this paper, we propose a language-agnostic deep neural network architecture for aspect-based sentiment analysis.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+3
Answering Comparative Questions: Better than Ten-Blue-Links?
We present CAM (comparative argumentative machine), a novel open-domain IR system to argumentatively compare objects with respect to information extracted from the Common Crawl.
Transfer Learning from LDA to BiLSTM-CNN for Offensive Language Detection in Twitter
Best results are achieved from pre-training our model on the unsupervised topic clustering of tweets in combination with thematic user cluster information.
microNER: A Micro-Service for German Named Entity Recognition based on BiLSTM-CRF
We evaluate the performance of different word and character embeddings on two standard German datasets and with a special focus on out-of-vocabulary words.
Categorizing Comparative Sentences
We tackle the tasks of automatically identifying comparative sentences and categorizing the intended preference (e. g., "Python has better NLP libraries than MATLAB" => (Python, better, MATLAB).
Unsupervised Sense-Aware Hypernymy Extraction
In this paper, we show how unsupervised sense representations can be used to improve hypernymy extraction.
A Multilingual Information Extraction Pipeline for Investigative Journalism
We introduce an advanced information extraction pipeline to automatically process very large collections of unstructured textual data for the purpose of investigative journalism.
Using Semantics for Granularities of Tokenization
First, we introduce DRUID, which is a method for detecting MWEs.
Demonstrating PAR4SEM - A Semantic Writing Aid with Adaptive Paraphrasing
In this paper, we present Par4Sem, a semantic writing aid tool based on adaptive paraphrasing.
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.
Learning Graph Embeddings from WordNet-based Similarity Measures
We present path2vec, a new approach for learning graph embeddings that relies on structural measures of pairwise node similarities.
New/s/leak 2.0 - Multilingual Information Extraction and Visualization for Investigative Journalism
Investigative journalism in recent years is confronted with two major challenges: 1) vast amounts of unstructured data originating from large text collections such as leaks or answers to Freedom of Information requests, and 2) multi-lingual data due to intensified global cooperation and communication in politics, business and civil society.
Par4Sim -- Adaptive Paraphrasing for Text Simplification
Learning from a real-world data stream and continuously updating the model without explicit supervision is a new challenge for NLP applications with machine learning components.
Document-based Recommender System for Job Postings using Dense Representations
Detecting the similarity between job advertisements is important for job recommendation systems as it allows, for example, the application of item-to-item based recommendations.
Unsupervised Semantic Frame Induction using Triclustering
We use dependency triples automatically extracted from a Web-scale corpus to perform unsupervised semantic frame induction.
BomJi at SemEval-2018 Task 10: Combining Vector-, Pattern- and Graph-based Information to Identify Discriminative Attributes
This paper describes BomJi, a supervised system for capturing discriminative attributes in word pairs (e. g. yellow as discriminative for banana over watermelon).
Ranked #3 on
Relation Extraction
on SemEval 2018 Task 10
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.
A Report on the Complex Word Identification Shared Task 2018
We report the findings of the second Complex Word Identification (CWI) shared task organized as part of the BEA workshop co-located with NAACL-HLT'2018.
Unspeech: Unsupervised Speech Context Embeddings
We introduce "Unspeech" embeddings, which are based on unsupervised learning of context feature representations for spoken language.
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.
What do we need to build explainable AI systems for the medical domain?
In this paper we outline some of our research topics in the context of the relatively new area of explainable-AI with a focus on the application in medicine, which is a very special domain.
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.
Improving Hypernymy Extraction with Distributional Semantic Classes
In this paper, we show how distributionally-induced semantic classes can be helpful for extracting hypernyms.
CWIG3G2 - Complex Word Identification Task across Three Text Genres and Two User Groups
Complex word identification (CWI) is an important task in text accessibility.
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.
Entity-Centric Information Access with Human in the Loop for the Biomedical Domain
In this paper, we describe the concept of entity-centric information access for the biomedical domain.
Multilingual and Cross-Lingual Complex Word Identification
Complex Word Identification (CWI) is an important task in lexical simplification and text accessibility.
Human and Machine Judgements for Russian Semantic Relatedness
On the one hand, humans easily make judgments about semantic relatedness.
Fighting with the Sparsity of Synonymy Dictionaries
Graph-based synset induction methods, such as MaxMax and Watset, induce synsets by performing a global clustering of a synonymy graph.
Making Sense of Word Embeddings
We present a simple yet effective approach for learning word sense embeddings.
IIT-UHH at SemEval-2017 Task 3: Exploring Multiple Features for Community Question Answering and Implicit Dialogue Identification
In this paper we present the system for Answer Selection and Ranking in Community Question Answering, which we build as part of our participation in SemEval-2017 Task 3.
IITPB at SemEval-2017 Task 5: Sentiment Prediction in Financial Text
The other system was based on Support Vector Regression using word embeddings, lexicon features, and PMI scores as features.
STS-UHH at SemEval-2017 Task 1: Scoring Semantic Textual Similarity Using Supervised and Unsupervised Ensemble
This paper reports the STS-UHH participation in the SemEval 2017 shared Task 1 of Semantic Textual Similarity (STS).
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.
Negative Sampling Improves Hypernymy Extraction Based on Projection Learning
We present a new approach to extraction of hypernyms based on projection learning and word embeddings.
Watset: Automatic Induction of Synsets from a Graph of Synonyms
This paper presents a new graph-based approach that induces synsets using synonymy dictionaries and word embeddings.
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.
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.
Towards a resource based on users' knowledge to overcome the Tip of the Tongue problem.
To this end, we asked crowdworkers to provide some cues to describe a given target and to specify then how each one of them relates to the target, in the hope that this could help others to find the elusive word.
Demonstrating Ambient Search: Implicit Document Retrieval for Speech Streams
In this demonstration paper we describe Ambient Search, a system that displays and retrieves documents in real time based on speech input.
Ambient Search: A Document Retrieval System for Speech Streams
We present Ambient Search, an open source system for displaying and retrieving relevant documents in real time for speech input.
Vectors or Graphs? On Differences of Representations for Distributional Semantic Models
Distributional Semantic Models (DSMs) have recently received increased attention, together with the rise of neural architectures for scalable training of dense vector embeddings.
A Web-based Tool for the Integrated Annotation of Semantic and Syntactic Structures
We introduce the third major release of WebAnno, a generic web-based annotation tool for distributed teams.
Domain-Specific Corpus Expansion with Focused Webcrawling
This work presents a straightforward method for extending or creating in-domain web corpora by focused webcrawling.
SemRelData ― Multilingual Contextual Annotation of Semantic Relations between Nominals: Dataset and Guidelines
Semantic relations play an important role in linguistic knowledge representation.
That's sick dude!: Automatic identification of word sense change across different timescales
In this paper, we propose an unsupervised method to identify noun sense changes based on rigorous analysis of time-varying text data available in the form of millions of digitized books.
Lexical Substitution Dataset for German
This article describes a lexical substitution dataset for German.
NoSta-D Named Entity Annotation for German: Guidelines and Dataset
We describe our approach to creating annotation guidelines based on linguistic and semantic considerations, and how we iteratively refined and tested them in the early stages of annotation in order to arrive at the largest publicly available dataset for German NER, consisting of over 31, 000 manually annotated sentences (over 591, 000 tokens) from German Wikipedia and German online news.
Distributed Distributional Similarities of Google Books Over the Centuries
This paper introduces a distributional thesaurus and sense clusters computed on the complete Google Syntactic N-grams, which is extracted from Google Books, a very large corpus of digitized books published between 1520 and 2008.
Turk Bootstrap Word Sense Inventory 2.0: A Large-Scale Resource for Lexical Substitution
This lexical resource, created by a crowdsourcing process using Amazon Mechanical Turk (http://www. mturk. com), encompasses a sense inventory for lexical substitution for 1, 012 highly frequent English common nouns.
