相关论文: WEKA-Based: Key Features and Classifier for French…

In-context learning is a popular inference strategy where large language models solve a task using only a few labeled demonstrations without needing any parameter updates. Although there have been extensive studies on English in-context…

In the evolving landscape of deep learning, there is a pressing need for more comprehensive datasets capable of training models across multiple modalities. Concurrently, in digital humanities, there is a growing demand to leverage…

Word embeddings are representations of individual words of a text document in a vector space and they are often use- ful for performing natural language pro- cessing tasks. Current state of the art al- gorithms for learning word embeddings…

Several recent studies on dyadic human-human interactions have been done on conversations without specific business objectives. However, many companies might benefit from studies dedicated to more precise environments such as after sales…

In this paper, we introduce a contrastive learning framework for keypoint detection (CoKe). Keypoint detection differs from other visual tasks where contrastive learning has been applied because the input is a set of images in which…

The world of language models is going through turbulent times, better and ever larger models are coming out at an unprecedented speed. However, we argue that, especially for the scientific community, encoder models of up to 1 billion…

Named Entity Recognition (NER) involves the identification and classification of named entities in unstructured text into predefined classes. NER in languages with limited resources, like French, is still an open problem due to the lack of…

This paper introduces a context-aware model for robust counterspeech generation, which achieved significant success in the MCG-COLING-2025 shared task. Our approach particularly excelled in low-resource language settings. By leveraging a…

This work presents a speech-to-text system "Pisets" for scientists and journalists which is based on a three-component architecture aimed at improving speech recognition accuracy while minimizing errors and hallucinations associated with…

One of the main computational and scientific challenges in the modern age is to extract useful information from unstructured texts. Topic models are one popular machine-learning approach which infers the latent topical structure of a…

Tokenization is a crucial step in information retrieval, especially for lexical matching algorithms, where the quality of indexable tokens directly impacts the effectiveness of a retrieval system. Since different languages have unique…

Data mining (also known as knowledge discovery from databases) is the process of extraction of hidden, previously unknown and potentially useful information from databases. The outcome of the extracted data can be analyzed for the future…

Language models have outpaced our ability to evaluate them effectively, but for their future development it is essential to study the frontier of their capabilities. We find real-world software engineering to be a rich, sustainable, and…

We present BenCzechMark (BCM), the first comprehensive Czech language benchmark designed for large language models, offering diverse tasks, multiple task formats, and multiple evaluation metrics. Its duel scoring system is grounded in…

We introduce Latxa, a family of large language models for Basque ranging from 7 to 70 billion parameters. Latxa is based on Llama 2, which we continue pretraining on a new Basque corpus comprising 4.3M documents and 4.2B tokens. Addressing…

While the use of cluster features became ubiquitous in core NLP tasks, most cluster features in NLP are based on distributional similarity. We propose a new type of clustering criteria, specific to the task of part-of-speech tagging.…

Recent work in automated sarcasm detection has placed a heavy focus on context and meta-data. Whilst certain utterances indeed require background knowledge and commonsense reasoning, previous works have only explored shallow models for…

Owing to the lack of corpora for low-resource languages, current works on dialogue generation have mainly focused on English. In this paper, we present mDIA, the first large-scale multilingual benchmark for dialogue generation across low-…

To facilitate future research in unsupervised induction of syntactic structure and to standardize best-practices, we propose a tagset that consists of twelve universal part-of-speech categories. In addition to the tagset, we develop a…

Unlike major Western languages, most African languages are very low-resourced. Furthermore, the resources that do exist are often scattered and difficult to obtain and discover. As a result, the data and code for existing research has…