Related papers: Bidirectional Trained Tree-Structured Decoder for …

Abstract Meaning Representation (AMR) is a rooted, labeled, acyclic graph representing the semantics of natural language. As previous works show, although AMR is designed for English at first, it can also represent semantics in other…

Large language models (LLMs) have shown remarkable performance in various natural language processing tasks. However, a primary constraint they face is the context limit, i.e., the maximum number of tokens they can process. Previous works…

Models based on large-pretrained language models, such as S(entence)BERT, provide effective and efficient sentence embeddings that show high correlation to human similarity ratings, but lack interpretability. On the other hand, graph…

While originally designed for unidirectional generative modeling, decoder-only large language models (LLMs) are increasingly being adapted for bidirectional modeling. However, unidirectional and bidirectional models are typically trained…

Pretraining on large-scale datasets can boost the performance of object detectors while the annotated datasets for object detection are hard to scale up due to the high labor cost. What we possess are numerous isolated filed-specific…

Over the past few decades, Artificial Intelligence(AI) has progressed from the initial machine learning stage to the deep learning stage, and now to the stage of foundational models. Foundational models have the characteristics of…

Protein representation learning is critical for numerous biological tasks. Recently, large transformer-based protein language models (pLMs) pretrained on large scale protein sequences have demonstrated significant success in sequence-based…

(Renyi Qu's Master's Thesis) Recent advancements in interpretable models for vision-language tasks have achieved competitive performance; however, their interpretability often suffers due to the reliance on unstructured text outputs from…

Latent tree learning(LTL) methods learn to parse sentences using only indirect supervision from a downstream task. Recent advances in latent tree learning have made it possible to recover moderately high quality tree structures by training…

Handwritten text recognition is an open problem of great interest in the area of automatic document image analysis. The transcription of handwritten content present in digitized documents is significant in analyzing historical archives or…

Handwritten mathematical expression recognition is a challenging problem due to the complicated two-dimensional structures, ambiguous handwriting input and variant scales of handwritten math symbols. To settle this problem, we utilize the…

Handwritten Mathematical Expression Recognition (HMER) methods have made remarkable progress, with most existing HMER approaches based on either a hybrid CNN/RNN-based with GRU architecture or Transformer architectures. Each of these has…

Arabic handwritten text recognition (HTR) is challenging, especially for historical texts, due to diverse writing styles and the intrinsic features of Arabic script. Additionally, Arabic handwriting datasets are smaller compared to English…

Large language models (LLMs) have shown remarkable ability to generate code, yet their outputs often violate syntactic or semantic constraints when guided only through natural language prompts. We introduce TreeCoder, the most general and…

The majority of existing human parsing methods formulate the task as semantic segmentation, which regard each semantic category equally and fail to exploit the intrinsic physiological structure of human body, resulting in inaccurate…

Vision-and-language reasoning requires an understanding of visual concepts, language semantics, and, most importantly, the alignment and relationships between these two modalities. We thus propose the LXMERT (Learning Cross-Modality Encoder…

In hybrid HMM based speech recognition, LSTM language models have been widely applied and achieved large improvements. The theoretical capability of modeling any unlimited context suggests that no recombination should be applied in…

The significant advancements in visual understanding and instruction following from Multimodal Large Language Models (MLLMs) have opened up more possibilities for broader applications in diverse and universal human-centric scenarios.…

The dominant object detection approaches treat the recognition of each region separately and overlook crucial semantic correlations between objects in one scene. This paradigm leads to substantial performance drop when facing heavy…

This paper presents our segmentation system developed for the MLP 2017 shared tasks on cross-lingual word segmentation and morpheme segmentation. We model both word and morpheme segmentation as character-level sequence labelling tasks. The…