Related papers: Syntax-Aware Network for Handwritten Mathematical …

Encoding facts as representations of entities and binary relationships between them, as learned by knowledge graph representation models, is useful for various tasks, including predicting new facts, question answering, fact checking and…

Multimodal Named Entity Recognition (MNER) is a crucial task for information extraction from social media platforms such as Twitter. Most current methods rely on attention weights to extract information from both text and images but are…

In recent years, brain-computer interfaces have made advances in decoding various motor-related tasks, including gesture recognition and movement classification, utilizing electroencephalogram (EEG) data. These developments are fundamental…

Predicting linearized Abstract Meaning Representation (AMR) graphs using pre-trained sequence-to-sequence Transformer models has recently led to large improvements on AMR parsing benchmarks. These parsers are simple and avoid explicit…

Speech is the most natural way of expressing ourselves as humans. Identifying emotion from speech is a nontrivial task due to the ambiguous definition of emotion itself. Speaker Emotion Recognition (SER) is essential for understanding human…

Automated content analysis increasingly supports communication research, yet scaling manual coding into computational pipelines raises concerns about measurement reliability and validity. We introduce a Hierarchical Error Correction (HEC)…

Text generation from AMR involves emitting sentences that reflect the meaning of their AMR annotations. Neural sequence-to-sequence models have successfully been used to decode strings from flattened graphs (e.g., using depth-first or…

Multimodal intent recognition aims to infer human intents by jointly modeling various modalities, playing a pivotal role in real-world dialogue systems. However, current methods struggle to model hierarchical semantics underlying complex…

DNA sequences encode critical genetic information, yet their variable length and discrete nature impede direct utilization in deep learning models. Existing DNA representation schemes convert sequences into numerical vectors but fail to…

Open-text (or open-domain) semantic parsers are designed to interpret any statement in natural language by inferring a corresponding meaning representation (MR). Unfortunately, large scale systems cannot be easily machine-learned due to…

Multimodal Emotion Recognition (MER) is a critical research area that seeks to decode human emotions from diverse data modalities. However, existing machine learning methods predominantly rely on predefined emotion taxonomies, which fail to…

Cross-database micro-expression recognition (CDMER) is one of recently emerging and interesting problem in micro-expression analysis. CDMER is more challenging than the conventional micro-expression recognition (MER), because the training…

We replace the Hidden Markov Model (HMM) which is traditionally used in in continuous speech recognition with a bi-directional recurrent neural network encoder coupled to a recurrent neural network decoder that directly emits a stream of…

Speech emotion recognition (SER) systems aim to recognize human emotional state during human-computer interaction. Most existing SER systems are trained based on utterance-level labels. However, not all frames in an audio have affective…

We propose a method to create document representations that reflect their internal structure. We modify Tree-LSTMs to hierarchically merge basic elements such as words and sentences into blocks of increasing complexity. Our Structure…

Representation learning is a critical ingredient for natural language processing systems. Recent Transformer language models like BERT learn powerful textual representations, but these models are targeted towards token- and sentence-level…

We successfully combine Expectation-Maximization algorithm and variational approaches for parameter learning and computing inference on Markov random felds. This is a general method that can be applied to many computer vision tasks. In this…

Handwritten Text Line Segmentation (HTLS) is a low-level but important task for many higher-level document processing tasks like handwritten text recognition. It is often formulated in terms of semantic segmentation or object detection in…

Hierarchical text classification (HTC) is a challenging subtask of multi-label classification as the labels form a complex hierarchical structure. Existing dual-encoder methods in HTC achieve weak performance gains with huge memory…

Semantic relationships, such as hyponym-hypernym, cause-effect, meronym-holonym etc. between a pair of entities in a sentence are usually reflected through syntactic patterns. Automatic extraction of such patterns benefits several…