Search Results for author:
Found 77 papers, 35 papers with code
Quality In, Quality Out: Learning from Actual Mistakes
However, QE models are often trained on noisy approximations of quality annotations derived from the proportion of post-edited words in translated sentences instead of direct human annotations of translation errors.
Who is bragging more online? A large scale analysis of bragging in social media
Bragging is the act of uttering statements that are likely to be positively viewed by others and it is extensively employed in human communication with the aim to build a positive self-image of oneself.
Comparing Explanation Faithfulness between Multilingual and Monolingual Fine-tuned Language Models
Previous studies have explored how different factors affect faithfulness, mainly in the context of monolingual English models.
An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Generative LLM Inference
We also show that adapting LLMs that have been pre-trained on more balanced multilingual data results in downstream performance comparable to the original models.
We Need to Talk About Classification Evaluation Metrics in NLP
In Natural Language Processing (NLP) classification tasks such as topic categorisation and sentiment analysis, model generalizability is generally measured with standard metrics such as Accuracy, F-Measure, or AUC-ROC.
How Does Calibration Data Affect the Post-training Pruning and Quantization of Large Language Models?
Pruning and quantization form the foundation of model compression for neural networks, enabling efficient inference for large language models (LLMs).
Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization
Despite the remarkable performance of generative large language models (LLMs) on abstractive summarization, they face two significant challenges: their considerable size and tendency to hallucinate.
Understanding the Role of Input Token Characters in Language Models: How Does Information Loss Affect Performance?
Understanding how and what pre-trained language models (PLMs) learn about language is an open challenge in natural language processing.
Pit One Against Many: Leveraging Attention-head Embeddings for Parameter-efficient Multi-head Attention
Scaling pre-trained language models has resulted in large performance gains in various natural language processing tasks but comes with a large cost in memory requirements.
Regulation and NLP (RegNLP): Taming Large Language Models
Regulation studies are a rich source of knowledge on how to systematically deal with risk and uncertainty, as well as with scientific evidence, to evaluate and compare regulatory options.
Examining the Limitations of Computational Rumor Detection Models Trained on Static Datasets
A crucial aspect of a rumor detection model is its ability to generalize, particularly its ability to detect emerging, previously unknown rumors.
Frustratingly Simple Memory Efficiency for Pre-trained Language Models via Dynamic Embedding Pruning
The extensive memory footprint of pre-trained language models (PLMs) can hinder deployment in memory-constrained settings, such as cloud environments or on-device.
Improving Multimodal Classification of Social Media Posts by Leveraging Image-Text Auxiliary Tasks
However, prior work on multimodal classification of social media posts has not yet addressed these challenges.
A Multimodal Analysis of Influencer Content on Twitter
Influencer marketing involves a wide range of strategies in which brands collaborate with popular content creators (i. e., influencers) to leverage their reach, trust, and impact on their audience to promote and endorse products or services.
Schema-Guided User Satisfaction Modeling for Task-Oriented Dialogues
Further, it employs a fulfillment representation layer for learning how many task attributes have been fulfilled in the dialogue, an importance predictor component for calculating the importance of task attributes.
Navigating Prompt Complexity for Zero-Shot Classification: A Study of Large Language Models in Computational Social Science
Instruction-tuned Large Language Models (LLMs) have exhibited impressive language understanding and the capacity to generate responses that follow specific prompts.
Active Learning Principles for In-Context Learning with Large Language Models
The remarkable advancements in large language models (LLMs) have significantly enhanced the performance in few-shot learning settings.
Rethinking Semi-supervised Learning with Language Models
Semi-supervised learning (SSL) is a popular setting aiming to effectively utilize unlabelled data to improve model performance in downstream natural language processing (NLP) tasks.
On the Limitations of Simulating Active Learning
Active learning (AL) is a human-and-model-in-the-loop paradigm that iteratively selects informative unlabeled data for human annotation, aiming to improve over random sampling.
Trading Syntax Trees for Wordpieces: Target-oriented Opinion Words Extraction with Wordpieces and Aspect Enhancement
State-of-the-art target-oriented opinion word extraction (TOWE) models typically use BERT-based text encoders that operate on the word level, along with graph convolutional networks (GCNs) that incorporate syntactic information extracted from syntax trees.
Incorporating Attribution Importance for Improving Faithfulness Metrics
Widely used faithfulness metrics, such as sufficiency and comprehensiveness use a hard erasure criterion, i. e. entirely removing or retaining the top most important tokens ranked by a given FA and observing the changes in predictive likelihood.
Self-training through Classifier Disagreement for Cross-Domain Opinion Target Extraction
Inspired by the theoretical foundations in domain adaptation [2], we propose a new SSL approach that opts for selecting target samples whose model output from a domain-specific teacher and student network disagree on the unlabelled target data, in an effort to boost the target domain performance.
It's about Time: Rethinking Evaluation on Rumor Detection Benchmarks using Chronological Splits
New events emerge over time influencing the topics of rumors in social media.
On the Impact of Temporal Concept Drift on Model Explanations
Explanation faithfulness of model predictions in natural language processing is typically evaluated on held-out data from the same temporal distribution as the training data (i. e. synchronous settings).
HashFormers: Towards Vocabulary-independent Pre-trained Transformers
These embeddings are subsequently fed into transformer layers for text classification.
Improving Graph-Based Text Representations with Character and Word Level N-grams
Graph-based text representation focuses on how text documents are represented as graphs for exploiting dependency information between tokens and documents within a corpus.
Domain Classification-based Source-specific Term Penalization for Domain Adaptation in Hate-speech Detection
State-of-the-art approaches for hate-speech detection usually exhibit poor performance in out-of-domain settings.
Combining Humor and Sarcasm for Improving Political Parody Detection
Parody is a figurative device used for mimicking entities for comedic or critical purposes.
Identifying and Characterizing Active Citizens who Refute Misinformation in Social Media
The phenomenon of misinformation spreading in social media has developed a new form of active citizens who focus on tackling the problem by refuting posts that might contain misinformation.
A Hierarchical N-Gram Framework for Zero-Shot Link Prediction
Thus, in this paper, we propose a Hierarchical N-Gram framework for Zero-Shot Link Prediction (HNZSLP), which considers the dependencies among character n-grams of the relation surface name for ZSLP.
Dynamically Refined Regularization for Improving Cross-corpora Hate Speech Detection
In this paper, we propose to automatically identify and reduce spurious correlations using attribution methods with dynamic refinement of the list of terms that need to be regularized during training.
How does the pre-training objective affect what large language models learn about linguistic properties?
Several pre-training objectives, such as masked language modeling (MLM), have been proposed to pre-train language models (e. g. BERT) with the aim of learning better language representations.
Automatic Identification and Classification of Bragging in Social Media
Bragging is a speech act employed with the goal of constructing a favorable self-image through positive statements about oneself.
An Empirical Study on Explanations in Out-of-Domain Settings
Recent work in Natural Language Processing has focused on developing approaches that extract faithful explanations, either via identifying the most important tokens in the input (i. e. post-hoc explanations) or by designing inherently faithful models that first select the most important tokens and then use them to predict the correct label (i. e. select-then-predict models).
LexGLUE: A Benchmark Dataset for Legal Language Understanding in English
Laws and their interpretations, legal arguments and agreements\ are typically expressed in writing, leading to the production of vast corpora of legal text.
Ranked #1 on
Natural Language Understanding
on LexGLUE
Active Learning by Acquiring Contrastive Examples
Common acquisition functions for active learning use either uncertainty or diversity sampling, aiming to select difficult and diverse data points from the pool of unlabeled data, respectively.
Frustratingly Simple Pretraining Alternatives to Masked Language Modeling
Masked language modeling (MLM), a self-supervised pretraining objective, is widely used in natural language processing for learning text representations.
An Empirical Study on Leveraging Position Embeddings for Target-oriented Opinion Words Extraction
Target-oriented opinion words extraction (TOWE) (Fan et al., 2019b) is a new subtask of target-oriented sentiment analysis that aims to extract opinion words for a given aspect in text.
Point-of-Interest Type Prediction using Text and Images
Point-of-interest (POI) type prediction is the task of inferring the type of a place from where a social media post was shared.
Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience
In this paper, we hypothesize that salient information extracted a priori from the training data can complement the task-specific information learned by the model during fine-tuning on a downstream task.
Translation Error Detection as Rationale Extraction
Recent Quality Estimation (QE) models based on multilingual pre-trained representations have achieved very competitive results when predicting the overall quality of translated sentences.
In Factuality: Efficient Integration of Relevant Facts for Visual Question Answering
Visual Question Answering (VQA) methods aim at leveraging visual input to answer questions that may require complex reasoning over entities.
Knowledge Distillation for Quality Estimation
Quality Estimation (QE) is the task of automatically predicting Machine Translation quality in the absence of reference translations, making it applicable in real-time settings, such as translating online social media conversations.
Analyzing Online Political Advertisements
Finally, we provide an in-depth analysis of the limitations of our best-performing models and linguistic analysis to study the characteristics of political ads discourse.
On the Ethical Limits of Natural Language Processing on Legal Text
Natural language processing (NLP) methods for analyzing legal text offer legal scholars and practitioners a range of tools allowing to empirically analyze law on a large scale.
Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification
In this paper, we seek to improve the faithfulness of attention-based explanations for text classification.
On the Importance of Effectively Adapting Pretrained Language Models for Active Learning
Recent Active Learning (AL) approaches in Natural Language Processing (NLP) proposed using off-the-shelf pretrained language models (LMs).
Flexible Instance-Specific Rationalization of NLP Models
Recent research on model interpretability in natural language processing extensively uses feature scoring methods for identifying which parts of the input are the most important for a model to make a prediction (i. e. explanation or rationale).
Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Cases
We also release a new dataset comprising European Court of Human Rights cases, including annotations for paragraph-level rationales.
Modeling the Severity of Complaints in Social Media
The speech act of complaining is used by humans to communicate a negative mismatch between reality and expectations as a reaction to an unfavorable situation.
Complaint Identification in Social Media with Transformer Networks
Complaining is a speech act extensively used by humans to communicate a negative inconsistency between reality and expectations.
LEGAL-BERT: The Muppets straight out of Law School
Thus we propose a systematic investigation of the available strategies when applying BERT in specialised domains.
An Empirical Study on Large-Scale Multi-Label Text Classification Including Few and Zero-Shot Labels
Furthermore, we show that Transformer-based approaches outperform the state-of-the-art in two of the datasets, and we propose a new state-of-the-art method which combines BERT with LWANs.
Multi-Label Classification
Multi Label Text Classification
+5
Point-of-Interest Type Inference from Social Media Text
Physical places help shape how we perceive the experiences we have there.
Automatic Generation of Topic Labels
A topic is usually represented by a list of terms ranked by their probability but, since these can be difficult to interpret, various approaches have been developed to assign descriptive labels to topics.
Unsupervised Quality Estimation for Neural Machine Translation
Quality Estimation (QE) is an important component in making Machine Translation (MT) useful in real-world applications, as it is aimed to inform the user on the quality of the MT output at test time.
Analyzing Political Parody in Social Media
Parody is a figurative device used to imitate an entity for comedic or critical purposes and represents a widespread phenomenon in social media through many popular parody accounts.
Journalist-in-the-Loop: Continuous Learning as a Service for Rumour Analysis
The system features a rumour annotation service that allows journalists to easily provide feedback for a given social media post through a web-based interface.
Automatically Identifying Complaints in Social Media
Complaining is a basic speech act regularly used in human and computer mediated communication to express a negative mismatch between reality and expectations in a particular situation.
Neural Legal Judgment Prediction in English
Legal judgment prediction is the task of automatically predicting the outcome of a court case, given a text describing the case's facts.
Ranked #1 on
Binary text classification
on ECHR Non-Anonymized
Extreme Multi-Label Legal Text Classification: A case study in EU Legislation
We consider the task of Extreme Multi-Label Text Classification (XMTC) in the legal domain.
Re-Ranking Words to Improve Interpretability of Automatically Generated Topics
Making their output interpretable is an important area of research with applications to areas such as the enhancement of exploratory search interfaces and the development of interpretable machine learning models.
Graph Node-Feature Convolution for Representation Learning
Graph convolutional network (GCN) is an emerging neural network approach.
Nowcasting the Stance of Social Media Users in a Sudden Vote: The Case of the Greek Referendum
Modelling user voting intention in social media is an important research area, with applications in analysing electorate behaviour, online political campaigning and advertising.
Predicting Twitter User Socioeconomic Attributes with Network and Language Information
Inferring socioeconomic attributes of social media users such as occupation and income is an important problem in computational social science.
Multimodal Topic Labelling
Automatic topic labelling is the task of generating a succinct label that summarises the theme or subject of a topic, with the intention of reducing the cognitive load of end-users when interpreting these topics.
Labeling Topics with Images using Neural Networks
Topics generated by topic models are usually represented by lists of $t$ terms or alternatively using short phrases and images.
