Related papers: Combining pattern-based CRFs and weighted context-…

Conditional Random Field (CRF) based neural models are among the most performant methods for solving sequence labeling problems. Despite its great success, CRF has the shortcoming of occasionally generating illegal sequences of tags, e.g.…

We describe a Context Free Grammar (CFG) for Bangla language and hence we propose a Bangla parser based on the grammar. Our approach is very much general to apply in Bangla Sentences and the method is well accepted for parsing a language of…

We approach the problem of generalizing pre-trained word embeddings beyond fixed-size vocabularies without using additional contextual information. We propose a subword-level word vector generation model that views words as bags of…

Recently researchers working in the LFG framework have proposed algorithms for taking advantage of the implicit context-free components of a unification grammar [Maxwell 96]. This paper clarifies the mathematical foundations of these…

We introduce a probabilistic formalism subsuming Markov random fields of bounded tree width and probabilistic context free grammars. Our models are based on a representation of Boolean formulas that we call case-factor diagrams (CFDs). CFDs…

Integrating Pre-trained Language Models (PLMs) with Graph Neural Networks (GNNs) remains a central challenge in text-rich heterophilic graph learning. We propose a novel integration framework that enables effective fusion between powerful…

Parikh's Theorem states that every context-free grammar (CFG) is equivalent to some regular CFG when the ordering of symbols in the words is ignored. The same is not true for the so-called weighted CFGs, which additionally assign a weight…

Recurrent neural networks have been very successful at predicting sequences of words in tasks such as language modeling. However, all such models are based on the conventional classification framework, where the model is trained against…

Many tasks in natural language processing involve predicting structured outputs, e.g., sequence labeling, semantic role labeling, parsing, and machine translation. Researchers are increasingly applying deep representation learning to these…

Majority of state-of-the-art deep learning methods are discriminative approaches, which model the conditional distribution of labels given inputs features. The success of such approaches heavily depends on high-quality labeled instances,…

Most existing word embedding methods can be categorized into Neural Embedding Models and Matrix Factorization (MF)-based methods. However some models are opaque to probabilistic interpretation, and MF-based methods, typically solved using…

Graph data model and graph databases are very popular in various areas such as bioinformatics, semantic web, and social networks. One specific problem in the area is a path querying with constraints formulated in terms of formal grammars.…

Plug-and-play functionality allows deep learning models to adapt well to different tasks without requiring any parameters modified. Recently, prefix-tuning was shown to be a plug-and-play method on various text generation tasks by simply…

Character-based sequence labeling framework is flexible and efficient for Chinese word segmentation (CWS). Recently, many character-based neural models have been applied to CWS. While they obtain good performance, they have two obvious…

A critical bottleneck in supervised machine learning is the need for large amounts of labeled data which is expensive and time consuming to obtain. However, it has been shown that a small amount of labeled data, while insufficient to…

The applications of LLM Agents are becoming increasingly complex and diverse, leading to a high demand for structured outputs that can be parsed into code, structured function calls, and embodied agent commands. These developments bring…

This paper addresses the problem of approximate MAP-MRF inference in general graphical models. Following [36], we consider a family of linear programming relaxations of the problem where each relaxation is specified by a set of nested pairs…

We investigate models for learning the class of context-free and context-sensitive languages (CFLs and CSLs). We begin with a brief discussion of some early hardness results which show that unrestricted language learning is impossible, and…

Recent years have witnessed increasing interests in prompt-based learning in which models can be trained on only a few annotated instances, making them suitable in low-resource settings. When using prompt-based learning for text…

Classifier-Free Guidance (CFG) is a widely used inference-time technique to boost the image quality of diffusion models. Yet, its reliance on text conditions prevents its use in unconditional generation. We propose a simple method to enable…