Exploiting the Bipartite Structure of Entity Grids for Document Coherence and Retrieval

Lioma, Christina; Tarissan, Fabien; Simonsen, Jakob Grue; Petersen, Casper; Larsen, Birger

doi:10.1145/2970398.2970413

Cited by 5 publications

(6 citation statements)

References 36 publications

(64 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The entity-based text coherence analysis model is one of the most popular methods that analyses the grammatical role of words in adjacent sentences and evaluates the local coherence [25] by extracting a pattern from adjacent sentences. Initially, R. Barzilay, M. Lapata [12,14,26] proposed the model but in recent years some modern approaches such as neural network models [27] and original bipartite graph [28] models, were proposed to overcome the limitation ability of entity grade to detect consistency in just neighbor sentences [29].…”

Section: Related Workmentioning

confidence: 99%

Text Coherence Analysis based on Misspelling Oblivious Word Embeddings and Deep Neural Network

Wadud¹,

Rashadul²

2021

IJACSA

View full text Add to dashboard Cite

Text coherence analysis is the most challenging task in Natural Language Processing (NLP) than other subfields of NLP, such as text generation, translation, or text summarization. There are many text coherence methods in NLP, most of them are graph-based or entity-based text coherence methods for short text documents. However, for long text documents, the existing methods perform low accuracy results which is the biggest challenge in text coherence analysis in both English and Bengali. This is because existing methods do not consider misspelled words in a sentence and cannot accurately assess text coherence. In this paper, a text coherence analysis method has been proposed based on the Misspelling Oblivious Word Embedding Model (MOEM) and deep neural network. The MOEM model replaces all misspelled words with the correct words and captures the interaction between different sentences by calculating their matches using word embedding. Then, the deep neural network architecture is used to train and test the model. This study examines two different types of datasets, one in Bengali and the other in English, to analyze text consistency based on sentence sequence activities and to evaluate the effectiveness of this model. In the Bengali language dataset, 7121 Bengali text documents have been used where 5696 (80%) documents have been used for training and 1425 (20%) documents for testing. And in the English language dataset, 6000 (80%) documents have been used for training and 1500 (20%) documents for model evaluation out of 7500 text documents. The efficiency of the proposed model is compared with existing text coherence analysis techniques. Experimental results show that the proposed model significantly improves automatic text coherence detection with 98.1% accuracy in English and 89.67% accuracy in Bengali. Finally, comparisons with other existing text coherence models of the proposed model are shown for both English and Bengali datasets.

show abstract

Section: Related Workmentioning

confidence: 99%

Text Coherence Analysis based on Misspelling Oblivious Word Embeddings and Deep Neural Network

Wadud¹,

Rashadul²

2021

IJACSA

View full text Add to dashboard Cite

show abstract

“…• for each node v, [27] and [30] consider all triplets (u, v, w) of distinct nodes with u and w in N (v) and define the redundancy rc(v) as the fraction of such triplets such that there exists an other node in N (u) ∩ N (w).…”

Section: Bipartite Stream Graphsmentioning

confidence: 99%

“…Several bipartite generalizations of the clustering coefficient have been proposed [27,29,55,38,30]. In particular:…”

Section: Bipartite Stream Graphsmentioning

confidence: 99%

Weighted, Bipartite, or Directed Stream Graphs for the Modeling of Temporal Networks

Latapy

Magnien²,

Viard³

2019

Computational Social Sciences

View full text Add to dashboard Cite

We recently introduced a formalism for the modeling of temporal networks, that we call stream graphs. It emphasizes the streaming nature of data and allows rigorous definitions of many important concepts generalizing classical graphs. This includes in particular size, density, clique, neighborhood, degree, clustering coefficient, and transitivity. In this contribution, we show that, like graphs, stream graphs may be extended to cope with bipartite structures, with node and link weights, or with link directions. We review the main bipartite, weighted or directed graph concepts proposed in the literature, we generalize them to the cases of bipartite, weighted, or directed stream graphs, and we show that obtained concepts are consistent with graph and stream graph ones. This provides a formal ground for an accurate modeling of the many temporal networks that have one or several of these features.

show abstract

“…FACTUALITY-BASED RERANKING .1310 (28) .1141 (90) .2242 (11) .3235 (68) 5.0-10% .2355 (16) .1626 (20) .3202 (12) .3084 (11) 0.1-4.9% .2760 (40) .1528 (61) .5503 (59) .3163 (66) <0%…”

Section: Early Vs Deep Precisionmentioning

confidence: 99%

“…The above approaches are developed stand-alone, not as an integral part of IR systems. However, methods for potentially integrating such text quality metrics into IR systems abound, for instance when text quality is interpreted as ratios of (combinations of) stopwords over content words per document [4,64,65]; term length [27] or part-of-speech (for ranking [38,41], but also for index pruning [38]); technical [33] or ambiguous scientific terminology [36]; non-compositional multiword expressions [39,47]; document readability [9,19,29,43,44]; document discourse [37] or coherence [52,40].…”

Section: Related Workmentioning

confidence: 99%

A study of factuality, objectivity and relevance

Lioma

Larsen

et al. 2016

Proceedings of the 3rd IEEE/ACM International Conference on Big Data Computing, Applications and Technologies

Self Cite

View full text Add to dashboard Cite

Much of the information processed by Information Retrieval (IR) systems is unreliable, biased, and generally untrustworthy [15,45,48]. Yet, factuality & objectivity detection is not a standard component of IR systems, even though it has been possible in Natural Language Processing (NLP) in the last decade. Motivated by this, we ask if and how factuality & objectivity detection may benefit IR. We answer this in two parts. First, we use state-of-the-art NLP to compute the probability of document factuality & objectivity in two TREC collections, and analyse its relation to document relevance. We find that factuality is strongly and positively correlated to document relevance, but objectivity is not. Second, we study the impact of factuality & objectivity to retrieval effectiveness by treating them as query independent features that we combine with a competitive language modelling baseline. Experiments with 450 TREC queries show that factuality improves precision by more than 10% over strong baselines, especially for the type of uncurated data typically used in web search; objectivity gives mixed results. An overall clear trend is that document factuality & objectivity is much more beneficial to IR when searching uncurated (e.g. web) documents vs. curated (e.g. state documentation and newswire articles).To our knowledge, this is the first study of factuality & objectivity for back-end IR, contributing novel findings about the relation between relevance and factuality/objectivity, and statistically significant gains to retrieval effectiveness in the competitive web search task.

show abstract

Exploiting the Bipartite Structure of Entity Grids for Document Coherence and Retrieval

Cited by 5 publications

References 36 publications

Text Coherence Analysis based on Misspelling Oblivious Word Embeddings and Deep Neural Network

Text Coherence Analysis based on Misspelling Oblivious Word Embeddings and Deep Neural Network

Weighted, Bipartite, or Directed Stream Graphs for the Modeling of Temporal Networks

A study of factuality, objectivity and relevance

Contact Info

Product

Resources

About