相关论文: InvBERT: Reconstructing Text from Contextualized W…

Detecting keywords in texts is important for many text mining applications. Graph-based methods have been commonly used to automatically find the key concepts in texts, however, relevant information provided by embeddings has not been…

In this paper, we propose a novel approach for generating document embeddings using a combination of Sentence-BERT (SBERT) and RoBERTa, two state-of-the-art natural language processing models. Our approach treats sentences as tokens and…

Text embedding inversion attacks reconstruct original sentences from latent representations, posing severe privacy threats in collaborative inference and edge computing. We propose TextCrafter, an optimization-based adversarial perturbation…

This study evaluates the performance of TF-IDF weighting, averaged Word2Vec embeddings, and BERT embeddings for document similarity scoring across two contrasting textual domains. By analysing cosine similarity scores, the methods'…

Text classification is a fundamental Natural Language Processing task that has a wide variety of applications, where deep learning approaches have produced state-of-the-art results. While these models have been heavily criticized for their…

Contextual embeddings generated by LLMs exhibit strong positional inductive biases, which can limit their ability to fully capture long-range, order-sensitive dependencies in highly structured source code. Consequently, how to further…

The integrity and reliability of scientific literature is facing a serious threat by adversarial text generation techniques, specifically from the use of automated paraphrasing tools to mask plagiarism. These tools generate "tortured…

This study investigates the internal mechanisms of BERT, a transformer-based large language model, with a focus on its ability to cluster narrative content and authorial style across its layers. Using a dataset of narratives developed via…

We explore to what extent knowledge about the pre-trained language model that is used is beneficial for the task of abstractive summarization. To this end, we experiment with conditioning the encoder and decoder of a Transformer-based…

Text classification has become widely used in various natural language processing applications like sentiment analysis. Current applications often use large transformer-based language models to classify input texts. However, there is a lack…

Self-attentive neural syntactic parsers using contextualized word embeddings (e.g. ELMo or BERT) currently produce state-of-the-art results in joint parsing and disfluency detection in speech transcripts. Since the contextualized word…

Reverse dictionary is the task to find the proper target word given the word description. In this paper, we tried to incorporate BERT into this task. However, since BERT is based on the byte-pair-encoding (BPE) subword encoding, it is…

Following procedural texts written in natural languages is challenging. We must read the whole text to identify the relevant information or identify the instruction flows to complete a task, which is prone to failures. If such texts are…

Document screening is a central task within Evidenced Based Medicine, which is a clinical discipline that supplements scientific proof to back medical decisions. Given the recent advances in DL (Deep Learning) methods applied to Information…

The way the words are used evolves through time, mirroring cultural or technological evolution of society. Semantic change detection is the task of detecting and analysing word evolution in textual data, even in short periods of time. In…

Transformer-based language models have taken many fields in NLP by storm. BERT and its derivatives dominate most of the existing evaluation benchmarks, including those for Word Sense Disambiguation (WSD), thanks to their ability in…

Several NLP tasks need the effective representation of text documents. Arora et. al., 2017 demonstrate that simple weighted averaging of word vectors frequently outperforms neural models. SCDV (Mekala et. al., 2017) further extends this…

Newly-introduced deep learning architectures, namely BERT, XLNet, RoBERTa and ALBERT, have been proved to be robust on several NLP tasks. However, the datasets trained on these architectures are fixed in terms of size and generalizability.…

Summarizing long, domain-specific documents with large language models (LLMs) remains challenging due to context limitations, information loss, and hallucinations, particularly in clinical and legal settings. We propose a Discrete Wavelet…

Improving our understanding of how information is encoded in vector space can yield valuable interpretability insights. Alongside vector dimensions, we argue that it is possible for the vector norm to also carry linguistic information. We…