Related papers: Generating Long and Informative Reviews with Aspec…

The rapid growth of information on the Internet has led to an overwhelming amount of opinions and comments on various activities, products, and services. This makes it difficult and time-consuming for users to process all the available…

We propose an end-to-end, domain-independent neural encoder-aligner-decoder model for selective generation, i.e., the joint task of content selection and surface realization. Our model first encodes a full set of over-determined database…

Rich high-quality annotated data is critical for semantic segmentation learning, yet acquiring dense and pixel-wise ground-truth is both labor- and time-consuming. Coarse annotations (e.g., scribbles, coarse polygons) offer an economical…

This paper proposes a structure-aware decoding method based on large language models to address the difficulty of traditional approaches in maintaining both semantic integrity and structural consistency in nested and overlapping entity…

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…

We present a novel summarization framework for reviews of products and services by selecting informative and concise text segments from the reviews. Our method consists of two major steps. First, we identify five frequently occurring…

Autoregressive models for text sometimes generate repetitive and low-quality output because errors accumulate during the steps of generation. This issue is often attributed to exposure bias - the difference between how a model is trained,…

Code comment generation which aims to automatically generate natural language descriptions for source code, is a crucial task in the field of automatic software development. Traditional comment generation methods use manually-crafted…

Recent models can generate fluent and grammatical synthetic reviews while accurately predicting user ratings. The generated reviews, expressing users' estimated opinions towards related products, are often viewed as natural language…

With the development of the Internet, natural language processing (NLP), in which sentiment analysis is an important task, became vital in information processing.Sentiment analysis includes aspect sentiment classification. Aspect sentiment…

Modern code review is a ubiquitous software quality assurance process aimed at identifying potential issues within newly written code. Despite its effectiveness, the process demands large amounts of effort from the human reviewers involved.…

The World Wide Web holds a wealth of information in the form of unstructured texts such as customer reviews for products, events and more. By extracting and analyzing the expressed opinions in customer reviews in a fine-grained way,…

End-to-end dialogue generation has achieved promising results without using handcrafted features and attributes specific for each task and corpus. However, one of the fatal drawbacks in such approaches is that they are unable to generate…

When generating text from probabilistic models, the chosen decoding strategy has a profound effect on the resulting text. Yet the properties elicited by various decoding strategies do not always transfer across natural language generation…

Decoding from the output distributions of large language models to produce high-quality text is a complex challenge in language modeling. Various approaches, such as beam search, sampling with temperature, $k-$sampling, nucleus…

Text-to-image synthesis refers to generating an image from a given text description, the key goal of which lies in photo realism and semantic consistency. Previous methods usually generate an initial image with sentence embedding and then…

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…

Generative Networks have proved to be extremely effective in image restoration and reconstruction in the past few years. Generating faces from textual descriptions is one such application where the power of generative algorithms can be…

Explainable recommendation systems provide explanations for recommendation results to improve their transparency and persuasiveness. The existing explainable recommendation methods generate textual explanations without explicitly…

To assist human review process, we build a novel ReviewRobot to automatically assign a review score and write comments for multiple categories such as novelty and meaningful comparison. A good review needs to be knowledgeable, namely that…