EliXa: A Modular and Flexible ABSA Platform

@inproceedings{SanVicente2015EliXaAM,
  title={EliXa: A Modular and Flexible ABSA Platform},
  author={I{\~n}aki San Vicente and Xabier Saralegi and Rodrigo Agerri},
  booktitle={*SEMEVAL},
  year={2015}
}
This paper presents a supervised Aspect Based Sentiment Analysis (ABSA) system. Our aim is to develop a modular platform which allows to easily conduct experiments by replacing the modules or adding new features. We obtain the best result in the Opinion Target Extraction (OTE) task (slot 2) using an off-the-shelf sequence labeler. The target polarity classification (slot 3) is addressed by means of a multiclass SVM algorithm which includes lexical based features such as the polarity values… 
[PDF] Semantic Reader
56 Citations
Highly Influential Citations
4
Background Citations
17
Methods Citations
23

Tables from this paper

56 Citations

Language Independent Sequence Labelling for Opinion Target Extraction (Extended Abstract)
TLDR
A language independent system to model Opinion Target Extraction (OTE) as a sequence labelling task that consists of a combination of clustering features implemented on top of a simple set of shallow local features, providing further insights into the behaviour of clustining features for sequence labeling tasks.
Towards an integrated pipeline for aspect-based sentiment analysis in various domains
TLDR
An integrated ABSA pipeline for Dutch that has been developed and tested on qualitative user feedback coming from three domains: retail, banking and human resources and shows promising results for the three ABSA subtasks, aspect term extraction, aspect category classification and aspect polarity classification.
Enhancing Aspect-Based Sentiment Analysis of Arabic Hotels' reviews using morphological, syntactic and semantic features
Language independent sequence labelling for Opinion Target Extraction
Aspect-Based Sentiment Analysis Using a Two-Step Neural Network Architecture
TLDR
A neural network based system to address the task of Aspect-Based Sentiment Analysis to compete in Task 2 of the ESWC-2016 Challenge on Semantic Sentiment analysis is proposed and proves to be an effective approach.
Extracting Opinion Targets Using Attention-Based Neural Model
TLDR
A deep learning model is proposed, which operates at the sentence level, which is designed to extract opinion targets for the Arabic language and outperforms the baseline and the prior works.
A hybrid unsupervised method for aspect term and opinion target extraction
Using long short-term memory deep neural networks for aspect-based sentiment analysis of Arabic reviews
TLDR
This paper proposes a state-of-the-art research for aspect-based sentiment analysis of Arabic Hotels’ reviews using two implementations of long short-term memory (LSTM) neural networks and shows that the approaches outperform baseline research on both tasks.
The many aspects of fine-grained sentiment analysis : an overview of the task and its main challenges
TLDR
In this survey paper, the task of aspect-based sentiment analysis is defined in close detail and how this fine-grained task actually comprises several subtasks is explained, which illustrate that this task is far from being solved.
Enhancing Aspect Term Extraction with Soft Prototypes
TLDR
This paper proposes to tackle aspect term extraction by correlating words with each other through soft prototypes, generated by a soft retrieval process, and shows that this model boosts the performance of three typical ATE methods by a large margin.
...
...

References

SHOWING 1-10 OF 33 REFERENCES
SemEval-2014 Task 4: Aspect Based Sentiment Analysis
TLDR
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.
Simple, Robust and (almost) Unsupervised Generation of Polarity Lexicons for Multiple Languages
TLDR
It is shown that qwn-ppv outperforms other automatically generated lexicons for the four extrinsic evaluations presented here and that the intrinsic evaluation of polarity lexicons is not a good performance indicator on a Sentiment Analysis task.
TASS - Workshop on Sentiment Analysis at SEPLN
TLDR
TASS, an experimental evaluation workshop within SEPLN, is described to foster the research in the field of sentiment analysis in social media, specifically focused on Spanish language to promote the application of existing state-of-the-art algorithms and techniques.
TASS - Workshop on Sentiment Analysis at SEPLN
TLDR
TASS, an experimental evaluation workshop within SEPLN, is described to foster the research in the field of sentiment analysis in social media, specifically focused on Spanish language to promote the application of existing state-of-the-art algorithms and techniques.
Aspect and sentiment unification model for online review analysis
TLDR
This paper proposes Sentence-LDA and extends it to Aspect and Sentiment Unification Model (ASUM), which incorporates aspect and sentiment together to model sentiments toward different aspects and shows that ASUM outperforms other generative models and comes close to supervised classification methods.
TASS 2013 - A Second Step in Reputation Analysis in Spanish
TLDR
This paper fully describes the proposed tasks, the contents, format and main figures of the generated corpus, the participant groups and their different approaches, and, finally, the overall results achieved and lessons learned in these two years.
NRC-Canada-2014: Detecting Aspects and Sentiment in Customer Reviews
TLDR
Submissions to SemEval-2014 stood first in detecting aspect categories, first in detects sentiment towards aspects categories, third in detecting aspects terms, and first and second in detecting sentiment towards aspect terms in the laptop and restaurant domains, respectively.
SentiWordNet 3.0: An Enhanced Lexical Resource for Sentiment Analysis and Opinion Mining
TLDR
This work discusses SENTIWORDNET 3.0, a lexical resource explicitly devised for supporting sentiment classification and opinion mining applications, and reports on the improvements concerning aspect (b) that it embodies with respect to version 1.0.
SemEval-2013 Task 2: Sentiment Analysis in Twitter
TLDR
Crowdourcing on Amazon Mechanical Turk was used to label a large Twitter training dataset along with additional test sets of Twitter and SMS messages for both subtasks, which included two subtasks: A, an expression-level subtask, and B, a message level subtask.
SemEval-2014 Task 9: Sentiment Analysis in Twitter
TLDR
The Sentiment Analysis in Twitter task is described, a continuation of the last year’s task that ran successfully as part of SemEval2013 and introduced three new test sets: regular tweets, sarcastic tweets, and LiveJournal sentences.
...
...