Search Results for author: Nikolaos Aletras

Found 73 papers, 31 papers with code

Quality In, Quality Out: Learning from Actual Mistakes

no code implementations EAMT 2020 Frederic Blain, Nikolaos Aletras, Lucia Specia

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.

Machine Translation Transfer Learning +1

How Does Calibration Data Affect the Post-training Pruning and Quantization of Large Language Models?

no code implementations16 Nov 2023 Miles Williams, Nikolaos Aletras

Pruning and quantization form the foundation of model compression for neural networks, enabling efficient inference for large language models (LLMs).

Model Compression Quantization

Understanding the Role of Input Token Characters in Language Models: How Does Information Loss Affect Performance?

no code implementations26 Oct 2023 Ahmed Alajrami, Katerina Margatina, Nikolaos Aletras

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

no code implementations11 Oct 2023 Huiyin Xue, Nikolaos Aletras

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

no code implementations9 Oct 2023 Catalina Goanta, Nikolaos Aletras, Ilias Chalkidis, Sofia Ranchordas, Gerasimos Spanakis

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

no code implementations20 Sep 2023 Yida Mu, Xingyi Song, Kalina Bontcheva, Nikolaos Aletras

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

1 code implementation15 Sep 2023 Miles Williams, Nikolaos Aletras

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

no code implementations14 Sep 2023 Danae Sánchez Villegas, Daniel Preoţiuc-Pietro, Nikolaos Aletras

Effectively leveraging multimodal information from social media posts is essential to various downstream tasks such as sentiment analysis, sarcasm detection and hate speech classification.

Image-text matching Sarcasm Detection +3

A Multimodal Analysis of Influencer Content on Twitter

1 code implementation6 Sep 2023 Danae Sánchez Villegas, Catalina Goanta, Nikolaos Aletras

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

1 code implementation26 May 2023 Yue Feng, Yunlong Jiao, Animesh Prasad, Nikolaos Aletras, Emine Yilmaz, Gabriella Kazai

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.

Language Modelling Task-Oriented Dialogue Systems

Active Learning Principles for In-Context Learning with Large Language Models

no code implementations23 May 2023 Katerina Margatina, Timo Schick, Nikolaos Aletras, Jane Dwivedi-Yu

The remarkable advancements in large language models (LLMs) have significantly enhanced the performance in few-shot learning settings.

Active Learning Few-Shot Learning

Navigating Prompt Complexity for Zero-Shot Classification: A Study of Large Language Models in Computational Social Science

no code implementations23 May 2023 Yida Mu, Ben P. Wu, William Thorne, Ambrose Robinson, Nikolaos Aletras, Carolina Scarton, Kalina Bontcheva, Xingyi Song

Instruction-tuned Large Language Models (LLMs) have exhibited impressive language understanding and the capacity to generate responses that follow specific prompts.

Zero-Shot Learning

Rethinking Semi-supervised Learning with Language Models

2 code implementations22 May 2023 Zhengxiang Shi, Francesco Tonolini, Nikolaos Aletras, Emine Yilmaz, Gabriella Kazai, Yunlong Jiao

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.

Pseudo Label Semi-Supervised Text Classification +1

On the Limitations of Simulating Active Learning

no code implementations21 May 2023 Katerina Margatina, Nikolaos Aletras

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.

Active Learning Fairness

Trading Syntax Trees for Wordpieces: Target-oriented Opinion Words Extraction with Wordpieces and Aspect Enhancement

no code implementations18 May 2023 Samuel Mensah, Kai Sun, Nikolaos Aletras

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.

target-oriented opinion words extraction

Incorporating Attribution Importance for Improving Faithfulness Metrics

1 code implementation17 May 2023 Zhixue Zhao, Nikolaos Aletras

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

no code implementations28 Feb 2023 Kai Sun, Richong Zhang, Samuel Mensah, Nikolaos Aletras, Yongyi Mao, Xudong Liu

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.

Aspect Extraction Domain Adaptation +1

On the Impact of Temporal Concept Drift on Model Explanations

1 code implementation17 Oct 2022 Zhixue Zhao, George Chrysostomou, Kalina Bontcheva, Nikolaos Aletras

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).

Text Classification

Improving Graph-Based Text Representations with Character and Word Level N-grams

no code implementations12 Oct 2022 Wenzhe Li, Nikolaos Aletras

Graph-based text representation focuses on how text documents are represented as graphs for exploiting dependency information between tokens and documents within a corpus.

Graph Representation Learning text-classification +2

Identifying and Characterizing Active Citizens who Refute Misinformation in Social Media

1 code implementation21 Apr 2022 Yida Mu, Pu Niu, Nikolaos Aletras

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

1 code implementation16 Apr 2022 Mingchen Li, Junfan Chen, Samuel Mensah, Nikolaos Aletras, Xiulong Yang, Yang Ye

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.

Knowledge Graphs Link Prediction

Dynamically Refined Regularization for Improving Cross-corpora Hate Speech Detection

1 code implementation Findings (ACL) 2022 Tulika Bose, Nikolaos Aletras, Irina Illina, Dominique Fohr

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.

Hate Speech Detection

How does the pre-training objective affect what large language models learn about linguistic properties?

1 code implementation ACL 2022 Ahmed Alajrami, Nikolaos Aletras

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.

Language Modelling Masked Language Modeling

An Empirical Study on Explanations in Out-of-Domain Settings

1 code implementation ACL 2022 George Chrysostomou, Nikolaos Aletras

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).

Active Learning by Acquiring Contrastive Examples

1 code implementation EMNLP 2021 Katerina Margatina, Giorgos Vernikos, Loïc Barrault, Nikolaos Aletras

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.

Active Learning Natural Language Understanding

Frustratingly Simple Pretraining Alternatives to Masked Language Modeling

1 code implementation EMNLP 2021 Atsuki Yamaguchi, George Chrysostomou, Katerina Margatina, Nikolaos Aletras

Masked language modeling (MLM), a self-supervised pretraining objective, is widely used in natural language processing for learning text representations.

Language Modelling Masked Language Modeling

An Empirical Study on Leveraging Position Embeddings for Target-oriented Opinion Words Extraction

1 code implementation EMNLP 2021 Samuel Mensah, Kai Sun, Nikolaos Aletras

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.

target-oriented opinion words extraction Word Embeddings

Point-of-Interest Type Prediction using Text and Images

1 code implementation EMNLP 2021 Danae Sánchez Villegas, Nikolaos Aletras

Point-of-interest (POI) type prediction is the task of inferring the type of a place from where a social media post was shared.

Type prediction Vocal Bursts Type Prediction

Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience

1 code implementation EMNLP 2021 George Chrysostomou, Nikolaos Aletras

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

no code implementations Findings (ACL) 2022 Marina Fomicheva, Lucia Specia, Nikolaos Aletras

Recent Quality Estimation (QE) models based on multilingual pre-trained representations have achieved very competitive results when predicting the overall quality of translated sentences.


Knowledge Distillation for Quality Estimation

1 code implementation Findings (ACL) 2021 Amit Gajbhiye, Marina Fomicheva, Fernando Alva-Manchego, Frédéric Blain, Abiola Obamuyide, Nikolaos Aletras, Lucia Specia

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.

Data Augmentation Knowledge Distillation +2

Analyzing Online Political Advertisements

no code implementations Findings (ACL) 2021 Danae Sánchez Villegas, Saeid Mokaram, Nikolaos Aletras

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

no code implementations Findings (ACL) 2021 Dimitrios Tsarapatsanis, Nikolaos Aletras

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.

Flexible Instance-Specific Rationalization of NLP Models

1 code implementation16 Apr 2021 George Chrysostomou, Nikolaos Aletras

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).

General Classification text-classification +1

Modeling the Severity of Complaints in Social Media

1 code implementation NAACL 2021 Mali Jin, Nikolaos Aletras

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

no code implementations COLING 2020 Mali Jin, Nikolaos Aletras

Complaining is a speech act extensively used by humans to communicate a negative inconsistency between reality and expectations.

Automatic Generation of Topic Labels

1 code implementation29 May 2020 Areej Alokaili, Nikolaos Aletras, Mark Stevenson

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.

Descriptive Information Retrieval +3

Unsupervised Quality Estimation for Neural Machine Translation

3 code implementations21 May 2020 Marina Fomicheva, Shuo Sun, Lisa Yankovskaya, Frédéric Blain, Francisco Guzmán, Mark Fishel, Nikolaos Aletras, Vishrav Chaudhary, Lucia Specia

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.

Machine Translation Translation

Analyzing Political Parody in Social Media

no code implementations ACL 2020 Antonis Maronikolakis, Danae Sanchez Villegas, Daniel Preotiuc-Pietro, Nikolaos Aletras

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.

Fact Checking Sentiment Analysis

Journalist-in-the-Loop: Continuous Learning as a Service for Rumour Analysis

no code implementations IJCNLP 2019 Twin Karmakharm, Nikolaos Aletras, Kalina Bontcheva

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.

Rumour Detection

Automatically Identifying Complaints in Social Media

1 code implementation ACL 2019 Daniel Preotiuc-Pietro, Mihaela Gaman, Nikolaos Aletras

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.

Re-Ranking Words to Improve Interpretability of Automatically Generated Topics

1 code implementation WS 2019 Areej Alokaili, Nikolaos Aletras, Mark Stevenson

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.

Interpretable Machine Learning Re-Ranking +1

Nowcasting the Stance of Social Media Users in a Sudden Vote: The Case of the Greek Referendum

no code implementations26 Aug 2018 Adam Tsakalidis, Nikolaos Aletras, Alexandra I. Cristea, Maria Liakata

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

1 code implementation11 Apr 2018 Nikolaos Aletras, Benjamin Paul Chamberlain

Inferring socioeconomic attributes of social media users such as occupation and income is an important problem in computational social science.

Recommendation Systems

Multimodal Topic Labelling

no code implementations EACL 2017 Ionut Sorodoc, Jey Han Lau, Nikolaos Aletras, Timothy Baldwin

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.

Topic Models

Labeling Topics with Images using Neural Networks

no code implementations1 Aug 2016 Nikolaos Aletras, Arpit Mittal

Topics generated by topic models are usually represented by lists of $t$ terms or alternatively using short phrases and images.

Re-Ranking Topic Models

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