Search Results for author:
Found 30 papers, 7 papers with code
New Domain, Major Effort? How Much Data is Necessary to Adapt a Temporal Tagger to the Voice Assistant Domain
Reliable tagging of Temporal Expressions (TEs, e. g., Book a table at L’Osteria for Sunday evening) is a central requirement for Voice Assistants (VAs).
Disentangling Document Topic and Author Gender in Multiple Languages: Lessons for Adversarial Debiasing
Text classification is a central tool in NLP.
Using Hierarchical Class Structure to Improve Fine-Grained Claim Classification
The analysis of public debates crucially requires the classification of political demands according to hierarchical claim ontologies (e. g. for immigration, a supercategory “Controlling Migration” might have subcategories “Asylum limit” or “Border installations”).
Swimming with the Tide? Positional Claim Detection across Political Text Types
Manifestos are official documents of political parties, providing a comprehensive topical overview of the electoral programs.
Multi-Dimensional Machine Translation Evaluation: Model Evaluation and Resource for Korean
Almost all frameworks for the manual or automatic evaluation of machine translation characterize the quality of an MT output with a single number.
Towards Understanding the Relationship between In-context Learning and Compositional Generalization
This indicates the usefulness of in-context learning problems as an inductive bias for generalization.
Beyond prompt brittleness: Evaluating the reliability and consistency of political worldviews in LLMs
Due to the widespread use of large language models (LLMs) in ubiquitous systems, we need to understand whether they embed a specific worldview and what these views reflect.
Approximate Attributions for Off-the-Shelf Siamese Transformers
In this work, we reassess these restrictions and propose (i) a model with exact attribution ability that retains the original model's predictive performance and (ii) a way to compute approximate attributions for off-the-shelf models.
Actor Identification in Discourse: A Challenge for LLMs?
The identification of political actors who put forward claims in public debate is a crucial step in the construction of discourse networks, which are helpful to analyze societal debates.
Multilingual estimation of political-party positioning: From label aggregation to long-input Transformers
We carry out the analysis of the Comparative Manifestos Project dataset across 41 countries and 27 languages and find that the task can be efficiently solved by state-of-the-art models, with label aggregation producing the best results.
Investigating semantic subspaces of Transformer sentence embeddings through linear structural probing
The question of what kinds of linguistic information are encoded in different layers of Transformer-based language models is of considerable interest for the NLP community.
Political claim identification and categorization in a multilingual setting: First experiments
The identification and classification of political claims is an important step in the analysis of political newspaper reports; however, resources for this task are few and far between.
An Attribution Method for Siamese Encoders
Despite the success of Siamese encoder models such as sentence transformers (ST), little is known about the aspects of inputs they pay attention to.
Adverbs, Surprisingly
This paper begins with the premise that adverbs are neglected in computational linguistics.
Additive manifesto decomposition: A policy domain aware method for understanding party positioning
The workflow covers (a) definition of suitable policy domains; (b) automatic labeling of domains, if no manual labels are available; (c) computation of domain-level similarities and aggregation at a global level; (d) extraction of interpretable party positions on major policy axes via multidimensional scaling.
Representation biases in sentence transformers
Variants of the BERT architecture specialised for producing full-sentence representations often achieve better performance on downstream tasks than sentence embeddings extracted from vanilla BERT.
Optimizing text representations to capture (dis)similarity between political parties
Even though fine-tuned neural language models have been pivotal in enabling "deep" automatic text analysis, optimizing text representations for specific applications remains a crucial bottleneck.
Understanding the Relation of User and News Representations in Content-Based Neural News Recommendation
A number of models for neural content-based news recommendation have been proposed.
Word-order typology in Multilingual BERT: A case study in subordinate-clause detection
The capabilities and limitations of BERT and similar models are still unclear when it comes to learning syntactic abstractions, in particular across languages.
Meta Learning for Code Summarization
Source code summarization is the task of generating a high-level natural language description for a segment of programming language code.
Between welcome culture and border fence. A dataset on the European refugee crisis in German newspaper reports
Besides the released resources and the case-study, our contribution is also methodological: we talk the reader through the steps from a newspaper article to a discourse network, demonstrating that there is not just one discourse network for the German migration debate, but multiple ones, depending on the topic of interest (political actors, policy fields, time spans).
Multi-Task Learning with Sentiment, Emotion, and Target Detection to Recognize Hate Speech and Offensive Language
The recognition of hate speech and offensive language (HOF) is commonly formulated as a classification task to decide if a text contains HOF.
Constraining Linear-chain CRFs to Regular Languages
However, the CRF's Markov assumption makes it impossible for CRFs to represent distributions with \textit{nonlocal} dependencies, and standard CRFs are unable to respect nonlocal constraints of the data (such as global arity constraints on output labels).
Ranked #6 on
Semantic Role Labeling
on OntoNotes
Emotion Ratings: How Intensity, Annotation Confidence and Agreements are Entangled
When humans judge the affective content of texts, they also implicitly assess the correctness of such judgment, that is, their confidence.
Dissecting Span Identification Tasks with Performance Prediction
Span identification (in short, span ID) tasks such as chunking, NER, or code-switching detection, ask models to identify and classify relevant spans in a text.
SemEval-2010 Task 8: Multi-Way Classification of Semantic Relations Between Pairs of Nominals
In this paper, we define the task, describe the creation of the datasets, and discuss the results of the participating 28 systems submitted by 10 teams.
Crowdsourcing and Validating Event-focused Emotion Corpora for German and English
Sentiment analysis has a range of corpora available across multiple languages.
Leveraging Lexical Substitutes for Unsupervised Word Sense Induction
Word sense induction is the most prominent unsupervised approach to lexical disambiguation.
Living a discrete life in a continuous world: Reference with distributed representations
Reference is a crucial property of language that allows us to connect linguistic expressions to the world.
"Show me the cup": Reference with Continuous Representations
One of the most basic functions of language is to refer to objects in a shared scene.
