An Empirical Study of Massively Parallel Bayesian Networks Learning for Sentiment Extraction from Unstructured Text

Chen, Wei; Zong, Lang; Huang, Weijing; Ou, Gaoyan; Wang, Yue; Yang, Dongqing

doi:10.1007/978-3-642-20291-9_47

Cited by 8 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As contextualized language models develop nowadays, we also try the BERT [11] 7 to generate the contextualized embeddings but it decreases the performance by 9.8%. It is not surprising because the context in each node is very limited 8 and the huge size of parameters (110M in BERT-BASE) for fine-tuning can easily cause an over-fitting problem.…”

Section: Ablation Studymentioning

confidence: 99%

See 1 more Smart Citation

Simplified DOM Trees for Transferable Attribute Extraction from the Web

Zhou,

Sheng,

et al. 2021

Preprint

View full text Add to dashboard Cite

There has been a steady need to precisely extract structured knowledge from the web (i.e. HTML documents). Given a web page, extracting a structured object along with various attributes of interest (e.g. price, publisher, author, and genre for a book) can facilitate a variety of downstream applications such as large-scale knowledge base construction, e-commerce product search, and personalized recommendation. Considering each web page is rendered from an HTML DOM tree, existing approaches formulate the problem as a DOM tree node tagging task. However, they either rely on computationally expensive visual feature engineering or are incapable of modeling the relationship among the tree nodes. In this paper, we propose a novel transferable method, Simplified DOM Trees for Attribute Extraction (SimpDOM), to tackle the problem by efficiently retrieving useful context for each node by leveraging the tree structure. We study two challenging experimental settings: (i) intra-vertical few-shot extraction, and (ii) cross-vertical fewshot extraction with out-of-domain knowledge, to evaluate our approach. Extensive experiments on the SWDE public dataset show that SimpDOM outperforms the state-of-the-art (SOTA) method by 1.44% on the F1 score. We also find that utilizing knowledge from a different vertical (cross-vertical extraction) is surprisingly useful and helps beat the SOTA by a further 1.37%.

show abstract

Section: Ablation Studymentioning

confidence: 99%

“…We choose BERT without loss of generality. It can be replaced by its alternatives like ELMo[30] or XLNet[42] 8. On average, each variable node contains only 2-5 words in different verticals.…”

mentioning

confidence: 99%

Simplified DOM Trees for Transferable Attribute Extraction from the Web

Zhou,

Sheng,

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…[3] introduces a method for accelerating Bayesian network parameter learning using Hadoop and MapReduce. Other relevant work on parallelization of learning Bayesian network from data include [10], [6], [14], [4] and [7]. In this paper, we describe a parallel version of the PC algorithm for learning the structure of a Bayesian network from large data sets on a shared memory computer using threads.…”

Section: Introductionmentioning

confidence: 99%

Parallelisation of the PC Algorithm

Madsen

Jensen

Salmerón

et al. 2015

Advances in Artificial Intelligence

View full text Add to dashboard Cite

This paper describes a parallel version of the PC algorithm for learning the structure of a Bayesian network from data. The PC algorithm is a constraint-based algorithm consisting of five steps where the first step is to perform a set of (conditional) independence tests while the remaining four steps relate to identifying the structure of the Bayesian network using the results of the (conditional) independence tests. In this paper, we describe a new approach to parallelization of the (conditional) independence testing as experiments illustrate that this is by far the most time consuming step. The proposed parallel PC algorithm is evaluated on data sets generated at random from five di↵erent realworld Bayesian networks. The results demonstrate that significant time performance improvements are possible using the proposed algorithm.

show abstract