Related papers: Keyword Extraction from Short Texts with a Text-To…

Pretrained language models (PLMs) have made remarkable progress in text generation tasks via fine-tuning. While, it is challenging to fine-tune PLMs in a data-scarce situation. Therefore, it is non-trivial to develop a general and…

Although speech recognition algorithms have developed quickly in recent years, achieving high transcription accuracy across diverse audio formats and acoustic environments remains a major challenge. This work explores how incorporating…

Automated terminology extraction refers to the task of extracting meaningful terms from domain-specific texts. This paper proposes a novel machine learning approach to terminology extraction, which combines features from traditional term…

One of the challenges in developing a high quality custom keyword spotting (KWS) model is the lengthy and expensive process of collecting training data covering a wide range of languages, phrases and speaking styles. We introduce Synth4Kws…

Extracting dense representations for terms and phrases is a task of great importance for knowledge discovery platforms targeting highly-technical fields. Dense representations are used as features for downstream components and have multiple…

Suicidal ideation is a serious health problem affecting millions of people worldwide. Social networks provide information about these mental health problems through users' emotional expressions. We propose a multilingual model leveraging…

Prompt tuning has recently emerged as an effective method for adapting pre-trained language models to a number of language understanding and generation tasks. In this paper, we investigate prompt tuning for semantic parsing -- the task of…

Neural Machine Translation (NMT) has improved translation by using Transformer-based models, but it still struggles with word ambiguity and context. This problem is especially important in domain-specific applications, which often have…

In recent years, there has been increased interest in building predictive models that harness natural language processing and machine learning techniques to detect emotions from various text sources, including social media posts,…

In recent years, the fields of natural language processing (NLP) and information retrieval (IR) have made tremendous progress thanksto deep learning models like Recurrent Neural Networks (RNNs), Gated Recurrent Units (GRUs) and Long…

Large language models (LLMs) exhibit remarkable multilingual capabilities despite English-dominated pre-training, attributed to cross-lingual mechanisms during pre-training. Existing methods for enhancing cross-lingual transfer remain…

In this paper, the problem of recovery of morphological information lost in abbreviated forms is addressed with a focus on highly inflected languages. Evidence is presented that the correct inflected form of an expanded abbreviation can in…

Label scarcity is a bottleneck for improving task performance in specialised domains. We propose a novel compositional transfer learning framework (DoT5 - domain compositional zero-shot T5) for zero-shot domain transfer. Without access to…

This study explores the use of large language models (LLMs) to predict emotion intensity in Polish political texts, a resource-poor language context. The research compares the performance of several LLMs against a supervised model trained…

Continuous prompts, or "soft prompts", are a widely-adopted parameter-efficient tuning strategy for large language models, but are often less favorable due to their opaque nature. Prior attempts to interpret continuous prompts relied on…

Enhancing small language models for real-life application deployment is a significant challenge facing the research community. Due to the difficulties and costs of using large language models, researchers are seeking ways to effectively…

Transformer-based language models have achieved remarkable success in few-shot in-context learning and drawn a lot of research interest. However, these models' performance greatly depends on the choice of the example prompts and also has…

Unlike English, morphologically rich languages can reveal characteristics of speakers or their conversational partners, such as gender and number, via pronouns, morphological endings of words and syntax. When translating from English to…

In this paper, we compare Czech-specific and multilingual sentence embedding models through intrinsic and extrinsic evaluation paradigms. For intrinsic evaluation, we employ Costra, a complex sentence transformation dataset, and several…

Extracting MITRE ATT\&CK Tactics, Techniques, and Procedures (TTPs) from natural language threat reports is crucial yet challenging. Existing methods primarily focus on performance metrics using data-driven approaches, often neglecting…