Related papers: Porous Lattice-based Transformer Encoder for Chine…

Data-driven artificial intelligence (AI) techniques are becoming prominent for learning in support of data compression, but are focused on standard problems such as text compression. To instead address the emerging problem of semantic…

Deep convolutional neural networks (CNNs) have shown outstanding performance in the task of semantically segmenting images. Applying the same methods on 3D data still poses challenges due to the heavy memory requirements and the lack of…

Ever-larger language models with ever-increasing capabilities are by now well-established text processing tools. Alas, information extraction tasks such as named entity recognition are still largely unaffected by this progress as they are…

Recent studies have shown effectiveness in using neural networks for Chinese word segmentation. However, these models rely on large-scale data and are less effective for low-resource datasets because of insufficient training data. We…

In this paper, we explore a new approach to named entity recognition (NER) with the goal of learning from context and fragment features more effectively, contributing to the improvement of overall recognition performance. We use the recent…

Recent advances in deep neural models allow us to build reliable named entity recognition (NER) systems without handcrafting features. However, such methods require large amounts of manually-labeled training data. There have been efforts on…

Recent works have revealed that Transformers are implicitly learning the syntactic information in its lower layers from data, albeit is highly dependent on the quality and scale of the training data. However, learning syntactic information…

Bidirectional Encoder Representations from Transformers (BERT) has shown marvelous improvements across various NLP tasks, and consecutive variants have been proposed to further improve the performance of the pre-trained language models. In…

Lattice codes with optimal decoding coefficient are capacity-achieving when dimension $N \rightarrow \infty$. In communications systems, finite dimensional lattice codes are considered, where the optimal decoding coefficients may still fail…

Distantly supervised relation extraction intrinsically suffers from noisy labels due to the strong assumption of distant supervision. Most prior works adopt a selective attention mechanism over sentences in a bag to denoise from wrongly…

Named entity recognition (NER) is an important research problem in natural language processing. There are three types of NER tasks, including flat, nested and discontinuous entity recognition. Most previous sequential labeling models are…

In this paper, we propose a new strategy for the task of named entity recognition (NER). We cast the task as a query-based machine reading comprehension task: e.g., the task of extracting entities with PER is formalized as answering the…

The Bidirectional long short-term memory networks (BiLSTM) have been widely used as an encoder in models solving the named entity recognition (NER) task. Recently, the Transformer is broadly adopted in various Natural Language Processing…

Previous work has predominantly focused on monolingual English semantic parsing. We, instead, explore the feasibility of Chinese semantic parsing in the absence of labeled data for Chinese meaning representations. We describe the pipeline…

Graph auto-encoders have proved to be useful in network embedding task. However, current models only consider explicit structures and fail to explore the informative latent structures cohered in networks. To address this issue, we propose a…

Although Transformers-based architectures excel at processing textual information, their naive adaptation for tabular data often involves flattening the table structure. This simplification can lead to the loss of essential…

Pre-trained Transformer language models (LM) have become go-to text representation encoders. Prior research fine-tunes deep LMs to encode text sequences such as sentences and passages into single dense vector representations for efficient…

Token representation strategies within large-scale neural architectures often rely on contextually refined embeddings, yet conventional approaches seldom encode structured relationships explicitly within token interactions. Self-attention…

Chain-of-thought (CoT) reasoning improves large language models (LLMs) on difficult tasks, but it also makes inference expensive because every intermediate step must be generated as a discrete token. Latent reasoning reduces visible token…

Transformer-based models have recently shown success in representation learning on graph-structured data beyond natural language processing and computer vision. However, the success is limited to small-scale graphs due to the drawbacks of…