Papers by Alexandros Potamianos
Aggregation Artifacts in Subjective Tasks Collapse Large Language Models’ Posteriors (2025.naacl-long)
Copied to clipboard
| Challenge: | In-context Learning (ICL) is the primary method for performing natural language tasks with Large Language Models. |
| Approach: | They examine whether aggregation is a confounding factor in the modeling of subjective tasks . they find it is possible for minority annotators to better align with LLMs . |
| Outcome: | The proposed method is based on aggregation of annotations in a dataset with appropriate priors. |
An Embarrassingly Simple Approach for Transfer Learning from Pretrained Language Models (N19-1)
Copied to clipboard
| Challenge: | Existing transfer learning methods employ language models pretrained on large generic corpora, but results come at a high computational cost and require task-specific architectures. |
| Approach: | They propose a transfer learning approach that combine a task-specific optimization function with an auxiliary language model objective, which is adjusted during the training process. |
| Outcome: | The proposed method surpasses well established transfer learning methods with greater level of complexity on a variety of affective and text classification tasks surpassing well established methods with higher level of difficulty. |
Attention-based Conditioning Methods for External Knowledge Integration (P19-1)
Copied to clipboard
| Challenge: | Existing approaches for incorporating external knowledge into deep neural networks (RNNs) lexicon features are used to concatenate external information into the input or hidden network layers. |
| Approach: | They propose a method for conditioning external knowledge into RNNs by concatenating a representation of the external information to the input or hidden network layers. |
| Outcome: | The proposed approach improves performance on six benchmark datasets. |
Neural Activation Semantic Models: Computational lexical semantic models of localized neural activations (C18-1)
Copied to clipboard
| Challenge: | Neural activation models have been proposed to map word semantics to localized neural activations. |
| Approach: | They propose a computational model that estimates semantic similarity in the neural activation space and investigate its performance for various natural language processing tasks. |
| Outcome: | The proposed model performs better than state-of-the-art word embeddings for the task of semantic similarity estimation between very similar or very dissimilar words while performing well on other tasks such as entailment and word categorization. |
Multi-User MultiWOZ: Task-Oriented Dialogues among Multiple Users (2023.findings-emnlp)
Copied to clipboard
Yohan Jo, Xinyan Zhao, Arijit Biswas, Nikoletta Basiou, Vincent Auvray, Nikolaos Malandrakis, Angeliki Metallinou, Alexandros Potamianos
| Challenge: | a dataset of task-oriented dialogues assume conversations between the agent and one user at a time . but multi-user task-orientated dialogues are richer, containing deliberation and deliberations . a novel task is proposed to rewrite a task-focused query that retains only task-relevant information . |
| Approach: | They propose to rewrite a task-oriented chat between two users as a concise task-orientated query that retains only task-relevant information and is directly consumable by the dialogue system. |
| Outcome: | The proposed method surpasses existing models on multi-user dialogues and generalizes to unseen domains. |
SEQˆ3: Differentiable Sequence-to-Sequence-to-Sequence Autoencoder for Unsupervised Abstractive Sentence Compression (N19-1)
Copied to clipboard
| Challenge: | Neural sequence-to-sequence models are currently the dominant approach in natural language processing tasks, but require massive parallel corpora. |
| Approach: | They propose a sequence-to-sequence-tosequnce autoencoder with words as latent variables . they apply the model to unsupervised abstractive sentence compression . |
| Outcome: | The proposed model achieves promising results in unsupervised sentence compression on benchmark datasets. |
Cross-Topic Distributional Semantic Representations Via Unsupervised Mappings (N19-1)
Copied to clipboard
| Challenge: | Existing distributional semantic models cannot capture the distinct meanings of polysemous words, resulting in conflated word representations of diverse contextual semantics. |
| Approach: | They propose a distributional semantic model that learns multiple representations of a word based on different topics. |
| Outcome: | The proposed model outperforms single-prototype models on NLP downstream tasks. |
UDALM: Unsupervised Domain Adaptation through Language Modeling (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing techniques for unsupervised domain adaptation (UDA) are limited by domain shift, which leads to performance degradation. |
| Approach: | They propose a fine-tuning procedure that uses a mixed classification and Masked Language Model loss to adapt to the target domain distribution in a robust and sample efficient manner. |
| Outcome: | The proposed procedure can adapt to the target domain distribution in a robust and sample efficient manner. |