相关论文: SentBS: Sentence-level Beam Search for Controllabl…

One of the most important challenges in text generation systems is to produce outputs that are not only correct but also diverse. Recently, Minimum Bayes-Risk (MBR) decoding has gained prominence for generating sentences of the highest…

In this paper, we use large language models to generate personalized stories for language learners, using only the vocabulary they know. The generated texts are specifically written to teach the user new vocabulary by simply reading stories…

Producing a reduced version of a source text, as in generic or focused summarization, inherently involves two distinct subtasks: deciding on targeted content and generating a coherent text conveying it. While some popular approaches address…

Despite the fact that image captioning models have been able to generate impressive descriptions for a given image, challenges remain: (1) the controllability and diversity of existing models are still far from satisfactory; (2) models…

Text summarization condenses a text to a shorter version while retaining the important informations. Abstractive summarization is a recent development that generates new phrases, rather than simply copying or rephrasing sentences within the…

Semantic control entails steering LM generations towards satisfying subtle non-lexical constraints, e.g., toxicity, sentiment, or politeness, attributes that can be captured by a sequence-level verifier. It can thus be viewed as sampling…

Large language models (LM) based on Transformers allow to generate plausible long texts. In this paper, we explore how this generation can be further controlled at decoding time to satisfy certain constraints (e.g. being non-toxic,…

Sentence extraction based summarization methods has some limitations as it doesn't go into the semantics of the document. Also, it lacks the capability of sentence generation which is intuitive to humans. Here we present a novel method to…

This study addresses the challenge that generative models struggle to balance flexibility, stability, and controllability in complex interactive scenarios. It proposes a controllable generation framework for dynamic interactive content…

Traditional Retrieval-Augmented Generation (RAG) effectively supports single-hop question answering with large language models but faces significant limitations in multi-hop question answering tasks, which require combining evidence from…

Sentence simplification reduces semantic complexity to benefit people with language impairments. Previous simplification studies on the sentence level and word level have achieved promising results but also meet great challenges. For…

In this paper, we focus on the problem of unsupervised image-sentence matching. Existing research explores to utilize document-level structural information to sample positive and negative instances for model training. Although the approach…

We propose an approach for the structure controllable summarization of long legal opinions that considers the argument structure of the document. Our approach involves using predicted argument role information to guide the model in…

Recall the classical text generation works, the generation framework can be briefly divided into two phases: \textbf{idea reasoning} and \textbf{surface realization}. The target of idea reasoning is to figure out the main idea which will be…

Recent advancements in song generation have shown promising results in generating songs from lyrics and/or global text prompts. However, most existing systems lack the ability to model the temporally varying attributes of songs, limiting…

With the advances of deep learning techniques, text generation is attracting increasing interest in the artificial intelligence (AI) community, because of its wide applications and because it is an essential component of AI. Traditional…

The principle of the Information Bottleneck (Tishby et al. 1999) is to produce a summary of information X optimized to predict some other relevant information Y. In this paper, we propose a novel approach to unsupervised sentence…

Automatically generating human-readable text describing the functionality of a program is the intent of source code summarization. Although neural language models achieve significant performance in this field, they are limited by their…

Beam search optimization resolves many issues in neural machine translation. However, this method lacks principled stopping criteria and does not learn how to stop during training, and the model naturally prefers the longer hypotheses…

This paper focuses on enhancing the captions generated by image-caption generation systems. We propose an approach for improving caption generation systems by choosing the most closely related output to the image rather than the most likely…