Related papers: Contextual Gating within the Transformer Stack: Sy…
Encoder transformer models compress information from all tokens in a sequence into a single [CLS] token to represent global context. This approach risks diluting fine-grained or hierarchical features, leading to information loss in…
Over the past few years, deep convolutional neural network-based methods have made great progress in semantic segmentation of street scenes. Some recent methods align feature maps to alleviate the semantic gap between them and achieve high…
The transformer is a state-of-the-art neural translation model that uses attention to iteratively refine lexical representations with information drawn from the surrounding context. Lexical features are fed into the first layer and…
Pretraining deep language models has led to large performance gains in NLP. Despite this success, Schick and Sch\"utze (2020) recently showed that these models struggle to understand rare words. For static word embeddings, this problem has…
Code-mixed languages, characterized by frequent within-sentence language transitions, present structural challenges that standard language models fail to address. In this work, we propose CMLFormer, an enhanced multi-layer dual-decoder…
Incorporating lexical knowledge into deep learning models has been proved to be very effective for sequence labeling tasks. However, previous works commonly have difficulty dealing with large-scale dynamic lexicons which often cause…
Scene graph generation (SGG) is a sophisticated task that suffers from both complex visual features and dataset long-tail problem. Recently, various unbiased strategies have been proposed by designing novel loss functions and data balancing…
Semantic sentence embedding models encode natural language sentences into vectors, such that closeness in embedding space indicates closeness in the semantics between the sentences. Bilingual data offers a useful signal for learning such…
We introduce semantic form mid-tuning, an approach for transferring semantic knowledge from semantic meaning representations into transformer-based language encoders. In mid-tuning, we learn to align the text of general sentences -- not…
We study the settings for which deep contextual embeddings (e.g., BERT) give large improvements in performance relative to classic pretrained embeddings (e.g., GloVe), and an even simpler baseline---random word embeddings---focusing on the…
Multimodal sentiment analysis has become an increasingly popular research area as the demand for multimodal online content is growing. For multimodal sentiment analysis, words can have different meanings depending on the linguistic context…
Embedding acoustic information into fixed length representations is of interest for a whole range of applications in speech and audio technology. Two novel unsupervised approaches to generate acoustic embeddings by modelling of acoustic…
Compositional generalization, the ability of intelligent models to extrapolate understanding of components to novel compositions, is a fundamental yet challenging facet in AI research, especially within multimodal environments. In this…
Sound event localization and detection (SELD) is a task for the classification of sound events and the localization of direction of arrival (DoA) utilizing multichannel acoustic signals. Prior studies employ spectral and channel information…
To accomplish the punctuation restoration task, most existing approaches focused on leveraging extra information (e.g., part-of-speech tags) or addressing the class imbalance problem. Recent works have widely applied the transformer-based…
Sentence embedding is an important research topic in natural language processing (NLP) since it can transfer knowledge to downstream tasks. Meanwhile, a contextualized word representation, called BERT, achieves the state-of-the-art…
Continuous representations of logic formulae allow us to integrate symbolic knowledge into data-driven learning algorithms. If such embeddings are semantically consistent, i.e. if similar specifications are mapped into nearby vectors, they…
Today, the acquisition of various behavioral log data has enabled deeper understanding of customer preferences and future behaviors in the marketing field. In particular, multimodal deep learning has achieved highly accurate predictions by…
We propose SentiBERT, a variant of BERT that effectively captures compositional sentiment semantics. The model incorporates contextualized representation with binary constituency parse tree to capture semantic composition. Comprehensive…
The pre-dominant approach to language modeling to date is based on recurrent neural networks. Their success on this task is often linked to their ability to capture unbounded context. In this paper we develop a finite context approach…