Search Results for author: Sebastian Padó

Found 30 papers, 9 papers with code

New Domain, Major Effort? How Much Data is Necessary to Adapt a Temporal Tagger to the Voice Assistant Domain

1 code implementation IWCS (ACL) 2021 Touhidul Alam, Alessandra Zarcone, Sebastian Padó

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).

Transfer Learning

Using Hierarchical Class Structure to Improve Fine-Grained Claim Classification

no code implementations ACL (spnlp) 2021 Erenay Dayanik, Andre Blessing, Nico Blokker, Sebastian Haunss, Jonas Kuhn, Gabriella Lapesa, Sebastian Padó

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

no code implementations EMNLP (NLP+CSS) 2020 Nico Blokker, Erenay Dayanik, Gabriella Lapesa, Sebastian Padó

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

1 code implementation19 Mar 2024 Dojun Park, Sebastian Padó

Almost all frameworks for the manual or automatic evaluation of machine translation characterize the quality of an MT output with a single number.

Machine Translation Sentence +1

Beyond prompt brittleness: Evaluating the reliability and consistency of political worldviews in LLMs

no code implementations27 Feb 2024 Tanise Ceron, Neele Falk, Ana Barić, Dmitry Nikolaev, Sebastian Padó

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

1 code implementation5 Feb 2024 Lucas Möller, Dmitry Nikolaev, Sebastian Padó

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.

Negation Sentence

Actor Identification in Discourse: A Challenge for LLMs?

no code implementations1 Feb 2024 Ana Barić, Sean Papay, Sebastian Padó

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

1 code implementation19 Oct 2023 Dmitry Nikolaev, Tanise Ceron, Sebastian Padó

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

1 code implementation18 Oct 2023 Dmitry Nikolaev, Sebastian Padó

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.

Decoder Natural Language Inference +3

Political claim identification and categorization in a multilingual setting: First experiments

no code implementations13 Oct 2023 Urs Zaberer, Sebastian Padó, Gabriella Lapesa

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.

Machine Translation Translation

An Attribution Method for Siamese Encoders

1 code implementation9 Oct 2023 Lucas Möller, Dmitry Nikolaev, Sebastian Padó

Despite the success of Siamese encoder models such as sentence transformers (ST), little is known about the aspects of inputs they pay attention to.

Sentence STS

Adverbs, Surprisingly

no code implementations31 May 2023 Dmitry Nikolaev, Collin F. Baker, Miriam R. L. Petruck, Sebastian Padó

This paper begins with the premise that adverbs are neglected in computational linguistics.

Language Modelling

Additive manifesto decomposition: A policy domain aware method for understanding party positioning

1 code implementation17 May 2023 Tanise Ceron, Dmitry Nikolaev, Sebastian Padó

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

no code implementations30 Jan 2023 Dmitry Nikolaev, Sebastian Padó

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.

Sentence Sentence Embeddings

Optimizing text representations to capture (dis)similarity between political parties

1 code implementation21 Oct 2022 Tanise Ceron, Nico Blokker, Sebastian Padó

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.

Word-order typology in Multilingual BERT: A case study in subordinate-clause detection

no code implementations NAACL (SIGTYP) 2022 Dmitry Nikolaev, Sebastian Padó

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

no code implementations20 Jan 2022 Moiz Rauf, Sebastian Padó, Michael Pradel

Source code summarization is the task of generating a high-level natural language description for a segment of programming language code.

Code Summarization Meta-Learning +1

Between welcome culture and border fence. A dataset on the European refugee crisis in German newspaper reports

no code implementations19 Nov 2021 Nico Blokker, André Blessing, Erenay Dayanik, Jonas Kuhn, Sebastian Padó, Gabriella Lapesa

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).

Cultural Vocal Bursts Intensity Prediction

Constraining Linear-chain CRFs to Regular Languages

1 code implementation ICLR 2022 Sean Papay, Roman Klinger, Sebastian Padó

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).

Semantic Role Labeling Structured Prediction

Emotion Ratings: How Intensity, Annotation Confidence and Agreements are Entangled

no code implementations EACL (WASSA) 2021 Enrica Troiano, Sebastian Padó, Roman Klinger

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

no code implementations EMNLP 2020 Sean Papay, Roman Klinger, Sebastian Padó

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.

Chunking NER

Living a discrete life in a continuous world: Reference with distributed representations

no code implementations6 Feb 2017 Gemma Boleda, Sebastian Padó, Nghia The Pham, Marco Baroni

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

no code implementations28 Jun 2016 Gemma Boleda, Sebastian Padó, Marco Baroni

One of the most basic functions of language is to refer to objects in a shared scene.

Cannot find the paper you are looking for? You can Submit a new open access paper.