Related papers: Parallel Refinements for Lexically Constrained Tex…
We propose Composition Sampling, a simple but effective method to generate diverse outputs for conditional generation of higher quality compared to previous stochastic decoding strategies. It builds on recently proposed plan-based neural…
Paraphrase generation strives to generate high-quality and diverse expressions of a given text, a domain where diffusion models excel. Though SOTA diffusion generation reconciles generation quality and diversity, textual diffusion suffers…
Learning distributed sentence representations remains an interesting problem in the field of Natural Language Processing (NLP). We want to learn a model that approximates the conditional latent space over the representations of a logical…
Generative models for Information Retrieval, where ranking of documents is viewed as the task of generating a query from a document's language model, were very successful in various IR tasks in the past. However, with the advent of modern…
For a computer to naturally interact with a human, it needs to be human-like. In this paper, we propose a neural response generation model with multi-task learning of generation and classification, focusing on emotion. Our model based on…
Multi-hop question generation (MQG) aims to generate complex questions which require reasoning over multiple pieces of information of the input passage. Most existing work on MQG has focused on exploring graph-based networks to equip the…
Large-scale language models (LMs) pretrained on massive corpora of text, such as GPT-2, are powerful open-domain text generators. However, as our systematic examination reveals, it is still challenging for such models to generate coherent…
The wave of pre-training language models has been continuously improving the quality of the machine-generated conversations, however, some of the generated responses still suffer from excessive repetition, sometimes repeating words from…
Automatically describing video content with text description is challenging but important task, which has been attracting a lot of attention in computer vision community. Previous works mainly strive for the accuracy of the generated…
Studies on grammatical error correction (GEC) have reported the effectiveness of pretraining a Seq2Seq model with a large amount of pseudodata. However, this approach requires time-consuming pretraining for GEC because of the size of the…
Modern models for text generation show state-of-the-art results in many natural language processing tasks. In this work, we explore the effectiveness of abstractive text summarization models for keyphrase selection. A list of keyphrases is…
This work introduces {\it PrahokBART}, a compact pre-trained sequence-to-sequence model trained from scratch for Khmer using carefully curated Khmer and English corpora. We focus on improving the pre-training corpus quality and addressing…
In this paper, we propose a novel pretraining-based encoder-decoder framework, which can generate the output sequence based on the input sequence in a two-stage manner. For the encoder of our model, we encode the input sequence into context…
Although significant progress has been made in many tasks within the field of Natural Language Processing (NLP), Controlled Text Generation (CTG) continues to face numerous challenges, particularly in achieving fine-grained conditional…
Hallucination of text ungrounded in the input is a well-known problem in neural data-to-text generation. Many methods have been proposed to mitigate it, but they typically require altering model architecture or collecting additional data,…
Automatic construction of relevant Knowledge Bases (KBs) from text, and generation of semantically meaningful text from KBs are both long-standing goals in Machine Learning. In this paper, we present ReGen, a bidirectional generation of…
Neural conversation models tend to generate safe, generic responses for most inputs. This is due to the limitations of likelihood-based decoding objectives in generation tasks with diverse outputs, such as conversation. To address this…
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…
The recently introduced Controlled Text Reduction (CTR) task isolates the text generation step within typical summarization-style tasks. It does so by challenging models to generate coherent text conforming to pre-selected content within…
A latent-variable model is introduced for text matching, inferring sentence representations by jointly optimizing generative and discriminative objectives. To alleviate typical optimization challenges in latent-variable models for text, we…