Related papers: Attend and select: A segment selective transformer…
Automatic hashtag annotation plays an important role in content understanding for microblog posts. To date, progress made in this field has been restricted to phrase selection from limited candidates, or word-level hashtag discovery using…
Hashtag annotation for microblog posts has been recently formulated as a sequence generation problem to handle emerging hashtags that are unseen in the training set. The state-of-the-art method leverages conversations initiated by posts to…
Hashtag segmentation is the task of breaking a hashtag into its constituent tokens. Hashtags often encode the essence of user-generated posts, along with information like topic and sentiment, which are useful in downstream tasks. Hashtags…
Hashtags are semantico-syntactic constructs used across various social networking and microblogging platforms to enable users to start a topic specific discussion or classify a post into a desired category. Segmenting and linking the…
Hashtags are often employed on social media and beyond to add metadata to a textual utterance with the goal of increasing discoverability, aiding search, or providing additional semantics. However, the semantic content of hashtags is not…
Previous CCG supertaggers usually predict categories using multi-class classification. Despite their simplicity, internal structures of categories are usually ignored. The rich semantics inside these structures may help us to better handle…
Hashtag segmentation, also known as hashtag decomposition, is a common step in preprocessing pipelines for social media datasets. It usually precedes tasks such as sentiment analysis and hate speech detection. For sentiment analysis in…
Large Transformer-based language models can aid human authors by suggesting plausible continuations of text written so far. However, current interactive writing assistants do not allow authors to guide text generation in desired topical…
Semantic segmentation based on sparse annotation has advanced in recent years. It labels only part of each object in the image, leaving the remainder unlabeled. Most of the existing approaches are time-consuming and often necessitate a…
Social media classification tasks (e.g., tweet sentiment analysis, tweet stance detection) are challenging because social media posts are typically short, informal, and ambiguous. Thus, training on tweets is challenging and demands…
The rise in popularity of microblogging services like Twitter has led to increased use of content annotation strategies like the hashtag. Hashtags provide users with a tagging mechanism to help organize, group, and create visibility for…
Recognizing human actions from untrimmed videos is an important task in activity understanding, and poses unique challenges in modeling long-range temporal relations. Recent works adopt a predict-and-refine strategy which converts an…
Text semantic segmentation involves partitioning a document into multiple paragraphs with continuous semantics based on the subject matter, contextual information, and document structure. Traditional approaches have typically relied on…
We explore the abilities of character recurrent neural network (char-RNN) for hashtag segmentation. Our approach to the task is the following: we generate synthetic training dataset according to frequent n-grams that satisfy predefined…
Highlighting is a powerful tool to pick out important content and emphasize. Creating summary highlights at the sub-sentence level is particularly desirable, because sub-sentences are more concise than whole sentences. They are also better…
The problem of categorizing short speech sentences according to their semantic features with high accuracy is a subject studied in natural language processing. In this study, a data set created with samples classified in 46 different…
Automatic mainstream hashtag recommendation aims to accurately provide users with concise and popular topical hashtags before publication. Generally, mainstream hashtag recommendation faces challenges in the comprehensive difficulty of…
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…
In this study, we introduce \textbf{AttendSeg}, a low-precision, highly compact deep neural network tailored for on-device semantic segmentation. AttendSeg possesses a self-attention network architecture comprising of light-weight attention…
Due to the fact that fully supervised semantic segmentation methods require sufficient fully-labeled data to work well and can not generalize to unseen classes, few-shot segmentation has attracted lots of research attention. Previous arts…