Demonyms and Compound Relational Nouns in Nominal Open IE

Pal, Harshata

doi:10.18653/v1/w16-1307

Cited by 67 publications

(58 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Most system focus on extracting verb-mediated relations, and the few exceptions that addressed noun-compounds provided partial solutions. Pal and Mausam (2016) focused on segmenting multi-word nouncompounds and assumed an is-a relation between the parts, as extracting (Francis Collins, is, NIH director) from "NIH director Francis Collins". Xavier and Lima (2014) enriched the corpus with compound definitions from online dictionaries, for example, interpreting oil industry as (industry, produces and delivers, oil) based on the Word-Net definition "industry that produces and delivers oil".…”

Section: Noun-compounds In Other Tasksmentioning

confidence: 99%

Paraphrase to Explicate: Revealing Implicit Noun-Compound Relations

Shwartz¹,

Dagan²

2018

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

Revealing the implicit semantic relation between the constituents of a nouncompound is important for many NLP applications. It has been addressed in the literature either as a classification task to a set of pre-defined relations or by producing free text paraphrases explicating the relations. Most existing paraphrasing methods lack the ability to generalize, and have a hard time interpreting infrequent or new noun-compounds. We propose a neural model that generalizes better by representing paraphrases in a continuous space, generalizing for both unseen noun-compounds and rare paraphrases. Our model helps improving performance on both the noun-compound paraphrasing and classification tasks.

show abstract

Section: Noun-compounds In Other Tasksmentioning

confidence: 99%

Paraphrase to Explicate: Revealing Implicit Noun-Compound Relations

Shwartz¹,

Dagan²

2018

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

show abstract

“…For the three types of sample, KNOWfact+lex has a significant advantage with the lowest MSE in the range of [0, 0.2] and [0. 8,1]. This means that if the confidence value predicted by KNOWfact+lex falls in [0, 0.2], the triple is most likely a negative sample.…”

Section: Metricsmentioning

confidence: 99%

“…Relation extraction (RE) is a primary work of KG construction. With breakthroughs in natural language processing technologies, many RE systems have been developed and are publicly available, for example: Reverb [4], ClausIE [5], OLLIE [6], Stanford OpenIE [7], OpenIE4 [8], and OpenIE5 [9]. These RE systems make it easier to identify relations between geo-entities from web text.…”

Section: Introductionmentioning

confidence: 99%

A Knowledge-Based Filtering Method for Open Relations among Geo-Entities

Qiu

Gao

et al. 2019

IJGI

View full text Add to dashboard Cite

Knowledge graphs (KGs) are crucial resources for supporting geographical knowledge services. Given the vast geographical knowledge in web text, extraction of geo-entity relations from web text has become the core technology for construction of geographical KGs; furthermore, it directly affects the quality of geographical knowledge services. However, web text inevitably contains noise and geographical knowledge can be sparsely distributed, both of which greatly restrict the quality of geo-entity relationship extraction. We propose a method for filtering geo-entity relations based on existing knowledge bases (KBs). Accordingly, ontology knowledge, fact knowledge, and synonym knowledge are integrated to generate geo-related knowledge. Then, the extracted geo-entity relationships and the geo-related knowledge are transferred into vectors, and the maximum similarity between vectors is the confidence value of one extracted geo-entity relationship triple. Our method takes full advantage of existing KBs to assess the quality of geographical information in web text, which is helpful to improve the richness and freshness of geographical KGs. Compared with the Stanford OpenIE method, our method decreased the mean square error (MSE) from 0.62 to 0.06 in the confidence interval [0.7, 1], and improved the area under the receiver operating characteristic (ROC) curve (AUC) from 0.51 to 0.89.

show abstract

“…We also include certain patterns involving named entities: pattern ORG IN LOC for extraction (ORG, is IN, LOC); pattern "Mr." PER for (PER, is, male) (similarly, Ms. or Mrs.); and pattern ORG POS? NP PER for (PER, is NP of, ORG) from RelNoun (Pal and Mausam, 2016). Apart from providing additional high-quality extractions, we use implicit extractions as a signal for minimization (Sec.…”

Section: Implicit Extractionsmentioning

confidence: 99%

MinIE: Minimizing Facts in Open Information Extraction

Gashteovski¹,

Gemulla²,

Corro

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

109

View full text Add to dashboard Cite

The goal of Open Information Extraction (OIE) is to extract surface relations and their arguments from naturallanguage text in an unsupervised, domainindependent manner. In this paper, we propose MinIE, an OIE system that aims to provide useful, compact extractions with high precision and recall. MinIE approaches these goals by (1) representing information about polarity, modality, attribution, and quantities with semantic annotations instead of in the actual extraction, and (2) identifying and removing parts that are considered overly specific. We conducted an experimental study with several real-world datasets and found that MinIE achieves competitive or higher precision and recall than most prior systems, while at the same time producing shorter, semantically enriched extractions.

show abstract

Demonyms and Compound Relational Nouns in Nominal Open IE

Cited by 67 publications

References 9 publications

Paraphrase to Explicate: Revealing Implicit Noun-Compound Relations

Paraphrase to Explicate: Revealing Implicit Noun-Compound Relations

A Knowledge-Based Filtering Method for Open Relations among Geo-Entities

MinIE: Minimizing Facts in Open Information Extraction

Contact Info

Product

Resources

About