Ripple Down Rules for question answering

Nguyen, Dat Quoc; Nguyen, Dai Quoc; Pham, Son Bao

doi:10.3233/sw-150204

Cited by 17 publications

(5 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the last node's rule is the last satisfied rule given the case, the new node is added as its child with the "except" edge; otherwise, the new node is attached with the "if-not" edge. SCRDR has been successfully applied in NLP tasks for temporal relation extraction (Pham and Hoffmann, 2006), word lemmatization (Plisson et al, 2008), POS tagging (Xu and Hoffmann, 2010;Nguyen et al, 2011b;Nguyen et al, 2014;, named entity recognition (Nguyen and Pham, 2012) and question answering (Nguyen et al, 2011a;Nguyen et al, 2013;Nguyen et al, 2017a). The works by Plisson et al (2008), Nguyen et al (2011b), Nguyen et al (2014) and build the tree automatically, while others manually construct the tree.…”

Section: Scrdr Methodologymentioning

confidence: 99%

A Fast and Accurate Vietnamese Word Segmenter

Nguyen¹,

Nguyen²,

Vu³

et al. 2017

Preprint

Self Cite

View full text Add to dashboard Cite

We propose a novel approach to Vietnamese word segmentation. Our approach is based on the Single Classification Ripple Down Rules methodology (Compton and Jansen, 1990), where rules are stored in an exception structure and new rules are only added to correct segmentation errors given by existing rules. Experimental results on the benchmark Vietnamese treebank show that our approach outperforms previous state-of-the-art approaches JVnSegmenter, vnTokenizer, DongDu and UETsegmenter in terms of both accuracy and performance speed. Our code is open-source and available at: https://github.com/datquocnguyen/RDRsegmenter.

show abstract

Section: Scrdr Methodologymentioning

confidence: 99%

A Fast and Accurate Vietnamese Word Segmenter

Nguyen¹,

Nguyen²,

Vu³

et al. 2017

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…A SCRDR tree [15,49,57] is a binary tree with two distinct types of edges. These edges are typically called except and if-not edges.…”

Section: Scrdr Methodologymentioning

confidence: 99%

A robust transformation-based learning approach using ripple down rules for part-of-speech tagging

Nguyen

Pham

et al. 2016

AIC

Self Cite

View full text Add to dashboard Cite

In this paper, we propose a new approach to construct a system of transformation rules for the Part-of-Speech (POS) tagging task. Our approach is based on an incremental knowledge acquisition method where rules are stored in an exception structure and new rules are only added to correct the errors of existing rules; thus allowing systematic control of the interaction between the rules. Experimental results on 13 languages show that our approach is fast in terms of training time and tagging speed. Furthermore, our approach obtains very competitive accuracy in comparison to state-ofthe-art POS and morphological taggers.

show abstract

“…RDRPOSTagger [ (Nguyen et al, 2014), (Nguyen et al, 2016)] is a rule-based tagger, this approach is also called transformation-based error-driven, able to automatically structure the rules in a particular tree structure called Single Classification Ripple Down Rules (SCRDR) [ (Compton and Jansen, 1990), (Richards, 2009), (Nguyen et al, 2015)…”

Section: Rdrpostaggermentioning

confidence: 99%

Jigsaw @ AMI and HaSpeeDe2: Fine-Tuning a Pre-Trained Comment-Domain BERT Model

Lees¹,

Sorensen²,

Kivlichan³

2020

EVALITA Evaluation of NLP and Speech Tools for Italian - December 17th, 2020

View full text Add to dashboard Cite

Welcome to EVALITA 2020! EVALITA is the evaluation campaign of Natural Language Processing and Speech Tools for Italian. EVALITA is an initiative of the Italian Association for Computational Linguistics (AILC, http://www.ai-lc.it) and it is endorsed by the Italian Association for Artificial Intelligence (AIxIA, http://www.aixia.it) and the Italian Association for Speech Sciences (AISV, http://www.aisv.it).This volume includes the reports of both task organisers and participants to all of the EVALITA 2020 challenges. In the 2020 edition, we coordinated the organization of 14 different tasks belonging to five research areas, being: (i) Affect, Hate, and Stance, (ii) Creativity and Style, (iii) New Challenges in Long-standing Tasks, (iv) Semantics and Multimodality, Time and Diachrony.The volume is opened by an overview to the EVALITA 2020 campaign, in which we describe the tasks, provide statistics on the participants and task organizers as well as our supporting sponsors. The abstract of the keynote speech made by Preslav Nakov titled "Flattening the Curve of the COVID-19 Infodemic: These Evaluation Campaigns Can Help!" is also included in this collection.Due to the 2020 COVID-19 pandemic, the traditional workshop was held online, where several members of the Italian NLP Community presented the results of their research. Despite the circumstances, the workshop represented an occasion for all participants from both academic institutions and private companies to disseminate their work and results and to share ideas through online sessions dedicated to each task and a general discussion during the plenary event.We carried on with the tradition of the "Best system across tasks" award. As in 2018, it represented an incentive for students, IT developers and researchers to push the boundaries of the state of the art by facing tasks in new ways, even if not winning.

show abstract

Ripple Down Rules for question answering

Cited by 17 publications

References 50 publications

A Fast and Accurate Vietnamese Word Segmenter

A Fast and Accurate Vietnamese Word Segmenter

A robust transformation-based learning approach using ripple down rules for part-of-speech tagging

Jigsaw @ AMI and HaSpeeDe2: Fine-Tuning a Pre-Trained Comment-Domain BERT Model

Contact Info

Product

Resources

About