相关论文: A Context-Sensitive Word Embedding Approach for Th…

Humour detection from sentences has been an interesting and challenging task in the last few years. In attempts to highlight humour detection, most research was conducted using traditional approaches of embedding, e.g., Word2Vec or Glove.…

Sentiment analysis is one of the well-known tasks and fast growing research areas in natural language processing (NLP) and text classifications. This technique has become an essential part of a wide range of applications including politics,…

Click-through rate (CTR) estimation is a fundamental task in personalized advertising and recommender systems and it's important for ranking models to effectively capture complex high-order features.Inspired by the success of ELMO and Bert…

The success of bidirectional encoders using masked language models, such as BERT, on numerous natural language processing tasks has prompted researchers to attempt to incorporate these pre-trained models into neural machine translation…

Twitter is among the most prevalent social media platform being used by millions of people all over the world. It is used to express ideas and opinions about political, social, business, sports, health, religion, and various other…

The first two tasks of the CLEF 2019 ProtestNews events focused on distinguishing between protest and non-protest related news articles and sentences in a binary classification task. Among the submissions, two well performing models have…

We propose BERMo, an architectural modification to BERT, which makes predictions based on a hierarchy of surface, syntactic and semantic language features. We use linear combination scheme proposed in Embeddings from Language Models (ELMo)…

Emojis are being frequently used in todays digital world to express from simple to complex thoughts more than ever before. Hence, they are also being used in sentiment analysis and targeted marketing campaigns. In this work, we performed…

The hashtag recommendation problem addresses recommending (suggesting) one or more hashtags to explicitly tag a post made on a given social network platform, based upon the content and context of the post. In this work, we propose a novel…

Most of existing work learn sentiment-specific word representation for improving Twitter sentiment classification, which encoded both n-gram and distant supervised tweet sentiment information in learning process. They assume all words…

Enhancing machine capabilities to answer questions has been a topic of considerable focus in recent years of NLP research. Language models like Embeddings from Language Models (ELMo)[1] and Bidirectional Encoder Representations from…

We analyze the process of creating word embedding feature representations designed for a learning task when annotated data is scarce, for example, in depressive language detection from Tweets. We start with a rich word embedding pre-trained…

Recently, the pre-trained language model, BERT (and its robustly optimized version RoBERTa), has attracted a lot of attention in natural language understanding (NLU), and achieved state-of-the-art accuracy in various NLU tasks, such as…

Research in analysis of microblogging platforms is experiencing a renewed surge with a large number of works applying representation learning models for applications like sentiment analysis, semantic textual similarity computation, hashtag…

Cyberbullying significantly contributes to mental health issues in communities by negatively impacting the psychology of victims. It is a prevalent problem on social media platforms, necessitating effective, real-time detection and…

The enormous amount of data being generated on the web and social media has increased the demand for detecting online hate speech. Detecting hate speech will reduce their negative impact and influence on others. A lot of effort in the…

Although considerable attention has been given to neural ranking architectures recently, far less attention has been paid to the term representations that are used as input to these models. In this work, we investigate how two pretrained…

Recent advances in automatic evaluation metrics for text have shown that deep contextualized word representations, such as those generated by BERT encoders, are helpful for designing metrics that correlate well with human judgements. At the…

Processing of raw text is the crucial first step in text classification and sentiment analysis. However, text processing steps are often performed using off-the-shelf routines and pre-built word dictionaries without optimizing for domain,…

Text embedding models from Natural Language Processing can map text data (e.g. words, sentences, documents) to supposedly meaningful numerical representations (a.k.a. text embeddings). While such models are increasingly applied in social…