Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Sentiment": models, code, and papers

Team Neuro at SemEval-2020 Task 8: Multi-Modal Fine Grain Emotion Classification of Memes using Multitask Learning

May 21, 2020
Sourya Dipta Das, Soumil Mandal

In this article, we describe the system that we used for the memotion analysis challenge, which is Task 8 of SemEval-2020. This challenge had three subtasks where affect based sentiment classification of the memes was required along with intensities. The system we proposed combines the three tasks into a single one by representing it as multi-label hierarchical classification problem.Here,Multi-Task learning or Joint learning Procedure is used to train our model.We have used dual channels to extract text and image based features from separate Deep Neural Network Backbone and aggregate them to create task specific features. These task specific aggregated feature vectors ware then passed on to smaller networks with dense layers, each one assigned for predicting one type of fine grain sentiment label. Our Proposed method show the superiority of this system in few tasks to other best models from the challenge.

* Proceedings of the International Workshop on Semantic Evaluation (SemEval) 

  Access Paper or Ask Questions

The Woman Worked as a Babysitter: On Biases in Language Generation

Sep 03, 2019
Emily Sheng, Kai-Wei Chang, Premkumar Natarajan, Nanyun Peng

We present a systematic study of biases in natural language generation (NLG) by analyzing text generated from prompts that contain mentions of different demographic groups. In this work, we introduce the notion of the regard towards a demographic, use the varying levels of regard towards different demographics as a defining metric for bias in NLG, and analyze the extent to which sentiment scores are a relevant proxy metric for regard. To this end, we collect strategically-generated text from language models and manually annotate the text with both sentiment and regard scores. Additionally, we build an automatic regard classifier through transfer learning, so that we can analyze biases in unseen text. Together, these methods reveal the extent of the biased nature of language model generations. Our analysis provides a study of biases in NLG, bias metrics and correlated human judgments, and empirical evidence on the usefulness of our annotated dataset.

* EMNLP 2019 short paper (5 pages) 

  Access Paper or Ask Questions

A Convolutional Neural Network for Modelling Sentences

Apr 08, 2014
Nal Kalchbrenner, Edward Grefenstette, Phil Blunsom

The ability to accurately represent sentences is central to language understanding. We describe a convolutional architecture dubbed the Dynamic Convolutional Neural Network (DCNN) that we adopt for the semantic modelling of sentences. The network uses Dynamic k-Max Pooling, a global pooling operation over linear sequences. The network handles input sentences of varying length and induces a feature graph over the sentence that is capable of explicitly capturing short and long-range relations. The network does not rely on a parse tree and is easily applicable to any language. We test the DCNN in four experiments: small scale binary and multi-class sentiment prediction, six-way question classification and Twitter sentiment prediction by distant supervision. The network achieves excellent performance in the first three tasks and a greater than 25% error reduction in the last task with respect to the strongest baseline.

  Access Paper or Ask Questions

Identifying Spurious Correlations for Robust Text Classification

Oct 06, 2020
Zhao Wang, Aron Culotta

The predictions of text classifiers are often driven by spurious correlations -- e.g., the term `Spielberg' correlates with positively reviewed movies, even though the term itself does not semantically convey a positive sentiment. In this paper, we propose a method to distinguish spurious and genuine correlations in text classification. We treat this as a supervised classification problem, using features derived from treatment effect estimators to distinguish spurious correlations from "genuine" ones. Due to the generic nature of these features and their small dimensionality, we find that the approach works well even with limited training examples, and that it is possible to transport the word classifier to new domains. Experiments on four datasets (sentiment classification and toxicity detection) suggest that using this approach to inform feature selection also leads to more robust classification, as measured by improved worst-case accuracy on the samples affected by spurious correlations.

* Findings of EMNLP-2020 
* Findings of EMNLP-2020 

  Access Paper or Ask Questions

Adaptation of Deep Bidirectional Multilingual Transformers for Russian Language

May 17, 2019
Yuri Kuratov, Mikhail Arkhipov

The paper introduces methods of adaptation of multilingual masked language models for a specific language. Pre-trained bidirectional language models show state-of-the-art performance on a wide range of tasks including reading comprehension, natural language inference, and sentiment analysis. At the moment there are two alternative approaches to train such models: monolingual and multilingual. While language specific models show superior performance, multilingual models allow to perform a transfer from one language to another and solve tasks for different languages simultaneously. This work shows that transfer learning from a multilingual model to monolingual model results in significant growth of performance on such tasks as reading comprehension, paraphrase detection, and sentiment analysis. Furthermore, multilingual initialization of monolingual model substantially reduces training time. Pre-trained models for the Russian language are open sourced.

  Access Paper or Ask Questions

A Deeper Look into Sarcastic Tweets Using Deep Convolutional Neural Networks

Jul 27, 2017
Soujanya Poria, Erik Cambria, Devamanyu Hazarika, Prateek Vij

Sarcasm detection is a key task for many natural language processing tasks. In sentiment analysis, for example, sarcasm can flip the polarity of an "apparently positive" sentence and, hence, negatively affect polarity detection performance. To date, most approaches to sarcasm detection have treated the task primarily as a text categorization problem. Sarcasm, however, can be expressed in very subtle ways and requires a deeper understanding of natural language that standard text categorization techniques cannot grasp. In this work, we develop models based on a pre-trained convolutional neural network for extracting sentiment, emotion and personality features for sarcasm detection. Such features, along with the network's baseline features, allow the proposed models to outperform the state of the art on benchmark datasets. We also address the often ignored generalizability issue of classifying data that have not been seen by the models at learning phase.

* Published in COLING 2016 

  Access Paper or Ask Questions

Breaking the News: First Impressions Matter on Online News

Apr 16, 2015
Julio Reis, Fabrıcio Benevenuto, Pedro O. S. Vaz de Melo, Raquel Prates, Haewoon Kwak, Jisun An

A growing number of people are changing the way they consume news, replacing the traditional physical newspapers and magazines by their virtual online versions or/and weblogs. The interactivity and immediacy present in online news are changing the way news are being produced and exposed by media corporations. News websites have to create effective strategies to catch people's attention and attract their clicks. In this paper we investigate possible strategies used by online news corporations in the design of their news headlines. We analyze the content of 69,907 headlines produced by four major global media corporations during a minimum of eight consecutive months in 2014. In order to discover strategies that could be used to attract clicks, we extracted features from the text of the news headlines related to the sentiment polarity of the headline. We discovered that the sentiment of the headline is strongly related to the popularity of the news and also with the dynamics of the posted comments on that particular news.

* The paper appears in ICWSM 2015 

  Access Paper or Ask Questions

Knowledge Distillation for BERT Unsupervised Domain Adaptation

Oct 23, 2020
Minho Ryu, Kichun Lee

A pre-trained language model, BERT, has brought significant performance improvements across a range of natural language processing tasks. Since the model is trained on a large corpus of diverse topics, it shows robust performance for domain shift problems in which data distributions at training (source data) and testing (target data) differ while sharing similarities. Despite its great improvements compared to previous models, it still suffers from performance degradation due to domain shifts. To mitigate such problems, we propose a simple but effective unsupervised domain adaptation method, adversarial adaptation with distillation (AAD), which combines the adversarial discriminative domain adaptation (ADDA) framework with knowledge distillation. We evaluate our approach in the task of cross-domain sentiment classification on 30 domain pairs, advancing the state-of-the-art performance for unsupervised domain adaptation in text sentiment classification.

  Access Paper or Ask Questions

"Let me convince you to buy my product ... ": A Case Study of an Automated Persuasive System for Fashion Products

Sep 25, 2017
Vitobha Munigala, Srikanth Tamilselvam, Anush Sankaran

Persuasivenes is a creative art aimed at making people believe in certain set of beliefs. Many a times, such creativity is about adapting richness of one domain into another to strike a chord with the target audience. In this research, we present PersuAIDE! - A persuasive system based on linguistic creativity to transform given sentence to generate various forms of persuading sentences. These various forms cover multiple focus of persuasion such as memorability and sentiment. For a given simple product line, the algorithm is composed of several steps including: (i) select an appropriate well-known expression for the target domain to add memorability, (ii) identify keywords and entities in the given sentence and expression and transform it to produce creative persuading sentence, and (iii) adding positive or negative sentiment for further persuasion. The persuasive conversion were manually verified using qualitative results and the effectiveness of the proposed approach is empirically discussed.

* ML4Creativity workshop at SIGKDD 2017 

  Access Paper or Ask Questions

Document Embedding with Paragraph Vectors

Jul 29, 2015
Andrew M. Dai, Christopher Olah, Quoc V. Le

Paragraph Vectors has been recently proposed as an unsupervised method for learning distributed representations for pieces of texts. In their work, the authors showed that the method can learn an embedding of movie review texts which can be leveraged for sentiment analysis. That proof of concept, while encouraging, was rather narrow. Here we consider tasks other than sentiment analysis, provide a more thorough comparison of Paragraph Vectors to other document modelling algorithms such as Latent Dirichlet Allocation, and evaluate performance of the method as we vary the dimensionality of the learned representation. We benchmarked the models on two document similarity data sets, one from Wikipedia, one from arXiv. We observe that the Paragraph Vector method performs significantly better than other methods, and propose a simple improvement to enhance embedding quality. Somewhat surprisingly, we also show that much like word embeddings, vector operations on Paragraph Vectors can perform useful semantic results.

* 8 pages 

  Access Paper or Ask Questions