Related papers: On Explaining Your Explanations of BERT: An Empiri…
Given a sequence of tokens generated by a language model, we may want to identify the preceding tokens that influence the model to generate this sequence. Performing such token attribution is expensive; a common approach is to ablate…
Attribution methods shed light on the explainability of data-driven approaches such as deep learning models by uncovering the most influential features in a to-be-explained decision. While determining feature attributions via gradients…
With the explosive growth of biomedical literature, designing automatic tools to extract information from the literature has great significance in biomedical research. Recently, transformer-based BERT models adapted to the biomedical domain…
Artificial intelligence and machine learning have significantly bolstered the technological world. This paper explores the potential of transfer learning in natural language processing focusing mainly on sentiment analysis. The models…
The pre-trained BERT model achieves a remarkable state of the art across a wide range of tasks in natural language processing. For solving the gender bias in gendered pronoun resolution task, I propose a novel neural network model based on…
How can we effectively regularize BERT? Although BERT proves its effectiveness in various downstream natural language processing tasks, it often overfits when there are only a small number of training instances. A promising direction to…
Attribution scores indicate the importance of different input parts and can, thus, explain model behaviour. Currently, prompt-based models are gaining popularity, i.a., due to their easier adaptability in low-resource settings. However, the…
Unlike classical lexical overlap metrics such as BLEU, most current evaluation metrics for machine translation (for example, COMET or BERTScore) are based on black-box large language models. They often achieve strong correlations with human…
With the growth of social medias, such as Twitter, plenty of user-generated data emerge daily. The short texts published on Twitter -- the tweets -- have earned significant attention as a rich source of information to guide many…
While large language models like BERT demonstrate strong empirical performance on semantic tasks, whether this reflects true conceptual competence or surface-level statistical association remains unclear. I investigate whether BERT encodes…
Deep Learning and Machine Learning based models have become extremely popular in text processing and information retrieval. However, the non-linear structures present inside the networks make these models largely inscrutable. A significant…
This paper proposes a medical literature summary generation method based on the BERT model to address the challenges brought by the current explosion of medical information. By fine-tuning and optimizing the BERT model, we develop an…
The successful application of large pre-trained models such as BERT in natural language processing has attracted more attention from researchers. Since the BERT typically acts as an end-to-end black box, classification systems based on it…
The role of social media in opinion formation has far-reaching implications in all spheres of society. Though social media provide platforms for expressing news and views, it is hard to control the quality of posts due to the sheer volumes…
Several tasks in argumentation mining and debating, question-answering, and natural language inference involve classifying a sequence in the context of another sequence (referred as bi-sequence classification). For several single sequence…
Pre-trained transformer models shine in many natural language processing tasks and therefore are expected to bear the representation of the input sentence or text meaning. These sentence-level embeddings are also important in…
A typical architecture for end-to-end entity linking systems consists of three steps: mention detection, candidate generation and entity disambiguation. In this study we investigate the following questions: (a) Can all those steps be…
By introducing a small set of additional parameters, a probe learns to solve specific linguistic tasks (e.g., dependency parsing) in a supervised manner using feature representations (e.g., contextualized embeddings). The effectiveness of…
Building systems with capability of natural language understanding (NLU) has been one of the oldest areas of AI. An essential component of NLU is to detect logical succession of events contained in a text. The task of sentence ordering is…
This paper explores the application of deep learning techniques, particularly focusing on BERT models, in sentiment analysis. It begins by introducing the fundamental concept of sentiment analysis and how deep learning methods are utilized…