A Generative Language Model for Few-shot Aspect-Based Sentiment Analysis

  title={A Generative Language Model for Few-shot Aspect-Based Sentiment Analysis},
  author={Ehsan Hosseini-Asl and Wenhao Liu and Caiming Xiong},
Sentiment analysis is an important task in nat- 001 ural language processing. In recent works, 002 pre-trained language models are often used 003 to achieve state-of-the-art results, especially 004 when training data is scarce. It is common to 005 fine-tune on the downstream task, usually by 006 adding task-specific layers on top of the model. 007 In this paper, we focus on aspect-based sen- 008 timent analysis, which involves extracting as- 009 pect term, category, and predicting their corre… 



Does BERT Understand Sentiment? Leveraging Comparisons Between Contextual and Non-Contextual Embeddings to Improve Aspect-Based Sentiment Models

This work shows that training a comparison of a contextual embedding from BERT and a generic word embedding can be used to infer sentiment and shows that if a subset of weights the model built on comparison of BERT is finetune, it can get state of the art results for Polarity Detection in Aspect Based Sentiment Classification datasets.

SemEval-2014 Task 4: Aspect Based Sentiment Analysis

SemEval2014 Task 4 aimed to foster research in the field of aspect-based sentiment analysis, where the goal is to identify the aspects of given target entities and the sentiment expressed for each aspect.

Mining and summarizing customer reviews

This research aims to mine and to summarize all the customer reviews of a product, and proposes several novel techniques to perform these tasks.

BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis

A novel post-training approach on the popular language model BERT to enhance the performance of fine-tuning of BERT for RRC and is applied to some other review-based tasks such as aspect extraction and aspect sentiment classification in aspect-based sentiment analysis.

SemEval-2016 Task 5: Aspect Based Sentiment Analysis

This paper describes the SemEval 2016 shared task on Aspect Based Sentiment Analysis (ABSA), a continuation of the respective tasks of 2014 and 2015, which attracted 245 submissions from 29 teams and provided 19 training and 20 testing datasets.

Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank

A Sentiment Treebank that includes fine grained sentiment labels for 215,154 phrases in the parse trees of 11,855 sentences and presents new challenges for sentiment compositionality, and introduces the Recursive Neural Tensor Network.

Solving Aspect Category Sentiment Analysis as a Text Generation Task

This work considers a more direct way of making use of pre-trained language models, by casting the ACSA tasks into natural language generation tasks, using natural language sentences to represent the output.

Author’s Sentiment Prediction

PerSenT, a crowd-sourced dataset that captures the sentiment of an author towards the mainentity in a news article, and presents empirical and qualitative analyses that illustrate the specific challenges posed by this dataset.

Improving BERT Performance for Aspect-Based Sentiment Analysis

Two simple modules called Parallel Aggregation and Hierarchical Aggregation are proposed to be utilized on top of BERT for two main ABSA tasks namely Aspect Extraction (AE) and Aspect Sentiment Classification (ASC) in order to improve the model's performance.

Language Models are Few-Shot Learners

GPT-3 achieves strong performance on many NLP datasets, including translation, question-answering, and cloze tasks, as well as several tasks that require on-the-fly reasoning or domain adaptation, such as unscrambling words, using a novel word in a sentence, or performing 3-digit arithmetic.