Related papers: Constraints First: A New MDD-based Model to Genera…
A wide range of control perspectives have been explored in controllable text generation. Structure-controlled summarization is recently proposed as a useful and interesting research direction. However, current structure-controlling methods…
Assessing the quality of LLM-generated text remains a fundamental challenge in natural language processing. Current evaluation approaches often rely on isolated metrics or simplistic aggregations that fail to capture the nuanced trade-offs…
Despite the remarkable generative capabilities of language models in producing naturalistic language, their effectiveness on explicit manipulation and generation of linguistic structures remain understudied. In this paper, we investigate…
Discrete diffusion models are a class of generative models that construct sequences by progressively denoising samples from a categorical noise distribution. Beyond their rapidly growing ability to generate coherent natural language, these…
In this paper, we study automatic keyphrase generation. Although conventional approaches to this task show promising results, they neglect correlation among keyphrases, resulting in duplication and coverage issues. To solve these problems,…
The standard recurrent neural network language model (RNNLM) generates sentences one word at a time and does not work from an explicit global sentence representation. In this work, we introduce and study an RNN-based variational autoencoder…
We study the problem of generating arithmetic math word problems (MWPs) given a math equation that specifies the mathematical computation and a context that specifies the problem scenario. Existing approaches are prone to generating MWPs…
Providing pretrained language models with simple task descriptions in natural language enables them to solve some tasks in a fully unsupervised fashion. Moreover, when combined with regular learning from examples, this idea yields…
Recent advances in neural network-based generative modeling have reignited the hopes in having computer systems capable of seamlessly conversing with humans and able to understand natural language. Neural architectures have been employed to…
Sentence ordering aims at arranging a list of sentences in the correct order. Based on the observation that sentence order at different distances may rely on different types of information, we devise a new approach based on multi-granular…
Unsupervised constrained text generation aims to generate text under a given set of constraints without any supervised data. Current state-of-the-art methods stochastically sample edit positions and actions, which may cause unnecessary…
Short-text classification, like all data science, struggles to achieve high performance using limited data. As a solution, a short sentence may be expanded with new and relevant feature words to form an artificially enlarged dataset, and…
Beyond generating long and topic-coherent paragraphs in traditional captioning tasks, the medical image report composition task poses more task-oriented challenges by requiring both the highly-accurate medical term diagnosis and multiple…
Large language models generate fluent texts and can follow natural language instructions to solve a wide range of tasks without task-specific training. Nevertheless, it is notoriously difficult to control their generation to satisfy the…
Conditional text generation has been a challenging task that is yet to see human-level performance from state-of-the-art models. In this work, we specifically focus on the Commongen benchmark, wherein the aim is to generate a plausible…
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…
Large Language Models (LLMs) have demonstrated a powerful ability for text generation. However, achieving optimal results with a given prompt or instruction can be challenging, especially for billion-sized models. Additionally, undesired…
Streamlining constraints (or streamliners, for short) narrow the search space, enhancing the speed and feasibility of solving complex constraint satisfaction problems. Traditionally, streamliners were crafted manually or generated through…
Structured texts refer to texts containing structured elements beyond plain texts, such as code snippets and placeholders. Such structured texts increasingly require segmentation into semantically meaningful components, which cannot be…
We propose a neural multi-document summarization (MDS) system that incorporates sentence relation graphs. We employ a Graph Convolutional Network (GCN) on the relation graphs, with sentence embeddings obtained from Recurrent Neural Networks…