A deep-learning approach to mining conditions

Gallego, Fernando O.; Corchuelo, Rafael

doi:10.1016/j.knosys.2019.105422

Cited by 3 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To improve the understanding of sentences, recently developed pattern-based methods can be used. 77 Alternative embedding-based schemes, such as GloVe, fast-Text, Sentence-BERT, Universal Sentence Encoder and Word Mover's Embedding, can serve to generate word-emotion association. The proposed model should also be used in multi-class sentiment analysis, and new powerful supervised machine learning methods should be employed to automate the design of neural network models, such as neural dynamic classification 78 and dynamic ensembles of neural networks.…”

Section: Discussionmentioning

confidence: 99%

Neural Networks with Emotion Associations, Topic Modeling and Supervised Term Weighting for Sentiment Analysis

Hájek

Barushka

Munk

2021

Int. J. Neur. Syst.

View full text Add to dashboard Cite

Automated sentiment analysis is becoming increasingly recognized due to the growing importance of social media and e-commerce platform review websites. Deep neural networks outperform traditional lexicon-based and machine learning methods by effectively exploiting contextual word embeddings to generate dense document representation. However, this representation model is not fully adequate to capture topical semantics and the sentiment polarity of words. To overcome these problems, a novel sentiment analysis model is proposed that utilizes richer document representations of word-emotion associations and topic models, which is the main computational novelty of this study. The sentiment analysis model integrates word embeddings with lexicon-based sentiment and emotion indicators, including negations and emoticons, and to further improve its performance, a topic modeling component is utilized together with a bag-of-words model based on a supervised term weighting scheme. The effectiveness of the proposed model is evaluated using large datasets of Amazon product reviews and hotel reviews. Experimental results prove that the proposed document representation is valid for the sentiment analysis of product and hotel reviews, irrespective of their class imbalance. The results also show that the proposed model improves on existing machine learning methods.

show abstract

Section: Discussionmentioning

confidence: 99%

Neural Networks with Emotion Associations, Topic Modeling and Supervised Term Weighting for Sentiment Analysis

Hájek

Barushka

Munk

2021

Int. J. Neur. Syst.

View full text Add to dashboard Cite

show abstract

“…Unfortunately, the need to introduce machine-learnt components to perform POS tagging or dependency analysis results in a proposal that cannot attain perfect parsing accuracy, which is a strong requirement. The proposals by Aiello et al, 16 Hatano et al, 17 Chittimalli et al, 21 Gallego and Corchuelo, 22,23 and Haj et al 24 used similar approaches and have the same problem. Only the proposals by Zámečníková and Kreslíková 18 and Hnatkowska and Gaweda 19 can achieve perfect parsing accuracy because they rely on grammars that can either parse a piece of text perfectly or report an error so that the user can correct it; unfortunately, none of them provide full support for SBVR-SE and the authors did not explore languages other than English; furthermore, it is not clear whether Zámečníková and Kreslíková's 18 proposal is open-domain or not and it produces non-executable decision tables.…”

Section: Decisionrules Digifi Hyperon Ibm Inrule Microsoft Oracle Peg...mentioning

confidence: 99%

“…Chittimalli et al 21 presented a recent follow‐up that uses a pipeline with three stages: first, two three‐gram statistical models are used to compute the probability that each sentence in the input text contains a rule or noise; second, the sentences that contain rules are POS tagged and transformed into dependency trees to which several heuristics are applied in order to extract the business domain (entities and relationships); third, several additional heuristics are used to extract the rules; note that the result consists in SBVR‐compliant rules in natural language. Gallego and Corchuelo 22,23 followed up on Hatano et al's 17 or Chittimalli et al's 21 proposals, but they used a neural‐based deep‐learning approach instead of using dependency parsing; their results proved to be promising since they were far more resilient than the competitors, but they did not put their focus on generating rules, but on parsing unusual forms of conditionals that might introduce business rules. Haj et al 24 presented the most recent approach of which we are aware; they use a pipeline in which the input document is first lemmatized, POS tagged, named entities are identified, and dependencies are identified; next, the business model is identified by using a number of pre‐defined patterns; finally, the system outputs SBVR‐compliant rules.…”

Section: Related Workmentioning

confidence: 99%

On the design of an advanced business rule engine

Jiménez

Corchuelo

2022

Softw Pract Exp

Self Cite

View full text Add to dashboard Cite

Business rules govern how well‐managed companies perform every day. They are expected to be written in natural language because they are devised by business people. That makes it difficult to translate them automatically into executable rules that can be integrated into typical information systems. Our industrial and academic research concludes that the current tools have a number of problems, namely: many of them do not pay any attention to the SBVR standard; some of them are not multi‐language; most of them cannot achieve perfect parsing accuracy; some of them are not domain agnostic; some of them use proprietary technologies; some of them do not produce executable rules; and none supports exploratory what‐if analyses natively. In this article, we present Tier‐Rules, which is a system that overcomes the previous problems. We also report on an industrial case study that helps illustrate it in practice.

show abstract

An Experimental Study of Neural Approaches to Multi-Hop Inference in Question Answering

Jiménez

Corchuelo

2022

Int. J. Neur. Syst.

View full text Add to dashboard Cite

Question answering aims at computing the answer to a question given a context with facts. Many proposals focus on questions whose answer is explicit in the context; lately, there has been an increasing interest in questions whose answer is not explicit and requires multi-hop inference to be computed. Our analysis of the literature reveals that there is a seminal proposal with increasingly complex follow-ups. Unfortunately, they were presented without an extensive study of their hyper-parameters, the experimental studies focused exclusively on English, and no statistical analysis to sustain the conclusions was ever performed. In this paper, we report on our experience devising a very simple neural approach to address the problem, on our extensive grid search over the space of hyper-parameters, on the results attained with English, Spanish, Hindi, and Portuguese, and sustain our conclusions with statistically sound analyses. Our findings prove that it is possible to beat many of the proposals in the literature with a very simple approach that was likely overlooked due to the difficulty to perform an extensive grid search, that the language does not have a statistically significant impact on the results, and that the empirical differences found among some existing proposals are not statistically significant.

show abstract

A deep-learning approach to mining conditions

Cited by 3 publications

References 35 publications

Neural Networks with Emotion Associations, Topic Modeling and Supervised Term Weighting for Sentiment Analysis

Neural Networks with Emotion Associations, Topic Modeling and Supervised Term Weighting for Sentiment Analysis

On the design of an advanced business rule engine

An Experimental Study of Neural Approaches to Multi-Hop Inference in Question Answering

Contact Info

Product

Resources

About