KLUEless: Polarity Classification and Association

Плотнікова, Н. В.; Kohl, Micha; Volkert, Kevin; Evert, Stefan; Lerner, Andreas; Dykes, Natalie; Ermer, Heiko

doi:10.18653/v1/s15-2103

Cited by 14 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…de/˜sascha/Ultradense/. τ system all ∩ 1 Amir et al (2015) .626 † 2 Hamdan et al (2015) .621 † 3 Zhang et al (2015) .591 † 4Özdemir and Bergler (2015) .584 † 5 Plotnikova et al (2015) . tively.…”

Section: Quality Of Predictionsmentioning

confidence: 99%

Ultradense Word Embeddings by Orthogonal Transformation

Rothe

Ebert

Schütze

2016

Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

Embeddings are generic representations that are useful for many NLP tasks. In this paper, we introduce DENSIFIER, a method that learns an orthogonal transformation of the embedding space that focuses the information relevant for a task in an ultradense subspace of a dimensionality that is smaller by a factor of 100 than the original space. We show that ultradense embeddings generated by DENSI-FIER reach state of the art on a lexicon creation task in which words are annotated with three types of lexical information -sentiment, concreteness and frequency. On the SemEval2015 10B sentiment analysis task we show that no information is lost when the ultradense subspace is used, but training is an order of magnitude more efficient due to the compactness of the ultradense space.

show abstract

Section: Quality Of Predictionsmentioning

confidence: 99%

Ultradense Word Embeddings by Orthogonal Transformation

Rothe

Ebert

Schütze

2016

Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

show abstract

“…For example, a question mark may indicate a rhetorical question, and an exclamation mark is an indication that the expressed feeling is emphasized. In [46], nine kinds of text statistics are defined, such as the sum or average of positive and negative scores over all words. The score of each word is derived from the sentiment lexicons (e.g., SentiWordnet).…”

Section: Textual Featuresmentioning

confidence: 99%

Sentiment Analysis on Multi-View Social Data

Niu

Zhu

Pang

et al. 2016

Lecture Notes in Computer Science

127

View full text Add to dashboard Cite

With the proliferation of social networks, people are likely to share their opinions about news, social events and products on the Web. There is an increasing interest in understanding users' attitude or sentiment from the large repository of opinion-rich data on the Web. This can benefit many commercial and political applications. Primarily, the researchers concentrated on the documents such as users' comments on the purchased products. Recent works show that visual appearance also conveys rich human affection that can be predicted. While great efforts have been devoted on the single media, either text or image, little attempts are paid for the joint analysis of multi-view data which is becoming a prevalent form in the social media. For example, paired with the posted textual messages on Twitter, users are likely to upload images and videos which may carry their affective states. One common obstacle is the lack of sufficient manually annotated instances for model learning and performance evaluation. To prompt the researches on this problem, we introduce a multi-view sentiment analysis dataset (MVSA) including a set of manually annotated image-text pairs collected from Twitter. The dataset can be utilized as a valuable benchmark for both single-view and multi-view sentiment analysis. In this thesis, we further conduct a comprehensive study on computational analysis of sentiment from the multi-view data. The state-of-the-art approaches on single view (image or text) or multiview (image and text) data are introduced, and compared through extensive experiments conducted on our constructed dataset and other public datasets. More importantly, the effectiveness of the correlation between different views is also studied using the widely used fusion strategies and advanced multi-view feature extraction methods.Index Terms: Sentiment analysis, social media, multi-view data, textual feature, visual feature, joint feature learning.

show abstract

“…Eventually, with the introduction of the SemEval corpus (Nakov et al, 2013), a great deal of automatic systems and resources have appeared on the scene. Though most of these systems typically rely on traditional supervised classification methods, such as SVM (Mohammad et al, 2013;Becker et al, 2013) or logistic regression (Hamdan et al, 2015;Plotnikova et al, 2015), in recent years, the deep learning (DL) tsunami (Manning, 2015) has also started hitting the shores of this "battlefield".…”

Section: Related Workmentioning

confidence: 99%

PotTS at SemEval-2016 Task 4: Sentiment Analysis of Twitter Using Character-level Convolutional Neural Networks.

Sidarenka

2016

Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)

View full text Add to dashboard Cite

This paper presents an alternative approach to polarity and intensity classification of sentiments in microblogs. In contrast to previous works, which either relied on carefully designed hand-crafted feature sets or automatically derived neural embeddings for words, our method harnesses character embeddings as its main input units. We obtain task-specific vector representations of characters by training a deep multi-layer convolutional neural network on the labeled dataset provided to the participants of the SemEval-2016 Shared Task 4 (Sentiment Analysis in Twitter; Nakov et al., 2016b) and subsequently evaluate our classifiers on subtasks B (two-way polarity classification) and C (joint five-way prediction of polarity and intensity) of this competition. Our first system, which uses three manifold convolution sets followed by four non-linear layers, ranks 16 in the former track; while our second network, which consists of a single convolutional filter set followed by a highway layer and three non-linearities with linear mappings in-between, attains the 10-th place on subtask C.

show abstract

KLUEless: Polarity Classification and Association

Cited by 14 publications

References 6 publications

Ultradense Word Embeddings by Orthogonal Transformation

Ultradense Word Embeddings by Orthogonal Transformation

Sentiment Analysis on Multi-View Social Data

PotTS at SemEval-2016 Task 4: Sentiment Analysis of Twitter Using Character-level Convolutional Neural Networks.

Contact Info

Product

Resources

About