Articles

AbstractDespite rapid developments in the field of Natural Language Processing (NLP) in the past few years, the task of Multilingual Entity Linking (MEL) and especially its end-to-end formulation remains challenging. In this paper we aim to evaluate solutions for general end-to-end multilingual entity linking by conducting experiments using both existing …...

AbstractTransformer-based language models such as Bidirectional Encoder Representations from Transformers (BERT) are now mainstream in the NLP field, but extensions to languages other than English, to new domains and/or to more specific text genres are still in demand. In this paper we introduced BERTabaporu, a BERT language model that has …...

AbstractRecent work has shown evidence of “Clever Hans” behavior in high-performance neural translationese classifiers, where BERT-based classifiers capitalize on spurious correlations, in particular topic information, between data and target classification labels, rather than genuine translationese signals. Translationese signals are subtle (especially for professional translation) and compete with many other signals …...

AbstractStance prediction - the computational task of inferring attitudes towards a given target topic of interest - relies heavily on text data provided by social media or similar sources, but it may also benefit from non-text information such as demographics (e.g., users’ gender, age, etc.), network structure (e.g., friends, followers, …...

AbstractLarge language models (LLMs) and generative AI have emerged as the most important areas in the field of natural language processing (NLP). LLMs are considered to be a key component in several NLP tasks, such as summarization, question-answering, sentiment classification, and translation. Newer LLMs, such as ChatGPT, BLOOMZ, and several …...

AbstractA fundamental challenge in the current NLP context, dominated by language models, comes from the inflexibility of current architectures to “learn” new information. While model-centric solutions like continual learning or parameter-efficient fine-tuning are available, the question still remains of how to reliably identify changes in language or in the world. …...

AbstractOne of the many advantages of pre-trained language models (PLMs) such as BERT and RoBERTa is their flexibility and contextual nature. These features give PLMs strong capabilities for representing lexical semantics. However, PLMs seem incapable of capturing high-level semantics in terms of compositionally. We show that when augmented with the …...

AbstractThis paper proposes an open-ended task for Visual Question Answering (VQA) that leverages the InceptionV3 Object Detection model and an attention-based Long Short-Term Memory (LSTM) network for question answering. Our proposed model provides accurate natural language answers to questions about an image, including those that require understanding contextual information and …...

AbstractThis paper aims to explore and enhance ChatGPT’s abilities to generate more human-like conversations by taking into account the emotional state of the user. To achieve this goal, a prompt-driven Emotional Intelligence is used through the empathetic dialogue dataset in order to propose a more empathetic conversational language model. We …...

AbstractMulti-document summarization (MDS) is a difficult task in Natural Language Processing, aiming to summarize information from several documents. However, the source documents are often insufficient to obtain a qualitative summary. We propose a retriever-guided model combined with non-parametric memory for summary generation. This model retrieves relevant candidates from a database …...

AbstractThis article presents a work-in-progress project, which aims to build and utilize a corpus of Romanian texts written or spoken by non-native students of different nationalities, who learn Romanian as a foreign language in the one-year, intensive academic program organized by the University of Bucharest. This corpus, called LECOR – …...

AbstractThis paper examines the effectiveness of different feature representations of audio data in accurately classifying discourse meaning in Spanish. The task involves determining whether an utterance is a declarative sentence, an interrogative, an imperative, etc. We explore how pitch contour can be represented for a discourse-meaning classification task, employing three …...

AbstractAutomatic emotion analysis is a highly challenging task for Natural Language Processing, which has so far mainly relied on textual contents to determine the emotion of text. However, words are not the only media that carry emotional information. In social media, people also use emojis to convey their feelings. Recently, …...

AbstractGenerative language models achieve the state of the art in many tasks within natural language processing (NLP). Although these models correctly capture syntactic information, they fail to interpret knowledge (semantics). Moreover, the lack of interpretability of these models promotes the use of other technologies as a replacement or complement to …...

AbstractRelationship extraction from unstructured data remains one of the most challenging tasks in the field of Natural Language Processing (NLP). The complexity of relationship extraction arises from the need to comprehend the underlying semantics, syntactic structures, and contextual dependencies within the text. Unstructured data poses challenges with diverse linguistic patterns, …...

AbstractThis study investigates the use of Natural Language Processing (NLP) methods to analyze politics, conflicts and violence in the Middle East using domain-specific pre-trained language models. We introduce Arabic text and present ConfliBERT-Arabic, a pre-trained language models that can efficiently analyze political, conflict and violence-related texts. Our technique hones a …...

AbstractIt is neither possible nor fair to compare the performance of question-answering systems for the Holy Quran and Hadith Sharif in Arabic due to both the absence of a golden test dataset on the Hadith Sharif and the small size and easy questions of the newly created golden test dataset …...

AbstractMetaphors use words from one domain of knowledge to describe another, which can make the meaning less clear and require human interpretation to understand. This makes it difficult for automated models to detect metaphorical usage. The objective of the experiments in the paper is to enhance the ability of deep …...

AbstractToday, artificial intelligence systems are incredibly intelligent, however they lack the human like capacity for understanding. In this context, sense-based lexical resources become a requirement for artificially intelligent machines. Lexical resources like Wordnets have received scholarly attention because they are considered as the crucial sense-based resources in the field of …...

AbstractThe rise of social media eases the spread of hateful content, especially racist content with severe consequences. In this paper, we analyze the tweets targeting the death of George Floyd in May 2020 as the event accelerated debates on racism globally. We focus on the tweets published in French for …...