scholarly journals DEEP LEARNING FOR SEMANTIC MATCHING: A SURVEY

2021 ◽  
Vol 37 (4) ◽  
pp. 365-402
Author(s):  
Han Li ◽  
Yash Govind ◽  
Sidharth Mudgal ◽  
Theodoros Rekatsinas ◽  
AnHai Doan
Keyword(s):  
Deep Learning ◽  
Semantic Web ◽  
Question Answering ◽  
Ontology Matching ◽  
Coreference Resolution ◽  
Semantic Matching ◽  
Entity Linking ◽  
Matching Problem ◽  
Semantic Relationships ◽  
Textual Entailment

Semantic matching finds certain types of semantic relationships among schema/data constructs. Examples include entity matching, entity linking, coreference resolution, schema/ontology matching, semantic text similarity, textual entailment, question answering, tagging, etc. Semantic matching has received much attention in the database, AI, KDD, Web, and Semantic Web communities. Recently, many works have also applied deep learning (DL) to semantic matching. In this paper we survey this fast growing topic. We define the semantic matching problem, categorize its variations into a taxonomy, and describe important applications. We describe DL solutions for important variations of semantic matching. Finally, we discuss future R\&D directions.

scholarly journals Exploring Knowledge Graphs in an Interpretable Composite Approach for Text Entailment

2019 ◽  
Vol 33 ◽  
pp. 7023-7030
Author(s):  
Vivian S. Silva ◽  
André Freitas ◽  
Siegfried Handschuh
Keyword(s):  
Question Answering ◽  
Text Summarization ◽  
World Knowledge ◽  
Semantic Relationship ◽  
Syntactic Variation ◽  
Semantic Relationships ◽  
Composite Approach ◽  
Textual Entailment ◽  
Knowledge Graphs ◽  
Recognizing Textual Entailment

Recognizing textual entailment is a key task for many semantic applications, such as Question Answering, Text Summarization, and Information Extraction, among others. Entailment scenarios can range from a simple syntactic variation to more complex semantic relationships between pieces of text, but most approaches try a one-size-fits-all solution that usually favors some scenario to the detriment of another. We propose a composite approach for recognizing text entailment which analyzes the entailment pair to decide whether it must be resolved syntactically or semantically. We also make the answer interpretable: whenever an entailment is solved semantically, we explore a knowledge base composed of structured lexical definitions to generate natural language humanlike justifications, explaining the semantic relationship holding between the pieces of text. Besides outperforming wellestablished entailment algorithms, our composite approach gives an important step towards Explainable AI, using world knowledge to make the semantic reasoning process explicit and understandable.

Application of the Agent-Based Ontology Matching Technology in the Relational Database

2013 ◽  
Vol 846-847 ◽  
pp. 1701-1706
Author(s):  
Jian Long Ding
Keyword(s):  
Data Storage ◽  
Relational Database ◽  
Data Retrieval ◽  
Domain Ontology ◽  
Ontology Matching ◽  
Semantic Matching ◽  
Semantic Retrieval ◽  
Matching Problem ◽  
Specific Level ◽  
Quantitative Calculation

As the relational database be the main data storage mode, but the traditional keyword based syntactic matching defects in precision and recall. This paper provides a ontology matching mechanisms for relational database, which realizes the semantic level of the data retrieval by using the intelligent search technology from Agent and Ontology. The mechanism using DCL domain ontology, SQC services query policy, SearchPolicyMap mapping to solve the problems as data object description, retrieval conditions description, and the mapping between those two description. And provided the preconditions for the semantic matching under the relational database. Solve the semantic matching problem of interaction between human and Agent by the WI interface and CM mechanism . Solve the problem of interaction between Agent and relational database by the service customization Interface SBI. Finally, solve the problem of semantic retrieval and quantitative calculation by querying adapter QA and core algorithm CMA. The mechanism has a strong practicality and application domains independent. Can implement a specific level semantics of relational database retrieval through the application domain ontology creation and mapping configuration.

Question Answering

2012 ◽  
pp. 304-343 ◽  
Author(s):  
Ivan Habernal ◽  
Miloslav Konopík ◽  
Ondrej Rohlík
Keyword(s):  
Information Retrieval ◽  
Semantic Web ◽  
Information Needs ◽  
World Wide ◽  
Question Answering ◽  
Future Research ◽  
Semantic Relationships ◽  
The World ◽  
Standard Information ◽  
Data Source

Question Answering is an area of information retrieval with the added challenge of applying sophisticated techniques to identify the complex syntactic and semantic relationships present in text in order to provide a more sophisticated and satisfactory response to the user’s information needs. For this reason, the authors see question answering as the next step beyond standard information retrieval. In this chapter state of the art question answering is covered focusing on providing an overview of systems, techniques and approaches that are likely to be employed in the next generations of search engines. Special attention is paid to question answering using the World Wide Web as the data source and to question answering exploiting the possibilities of Semantic Web. Considerations about the current issues and prospects for promising future research are also provided.

Recognizing textual entailment: Rational, evaluation and approaches

2009 ◽  
Vol 15 (4) ◽  
pp. i-xvii ◽  
Author(s):  
IDO DAGAN ◽  
BILL DOLAN ◽  
BERNARDO MAGNINI ◽  
DAN ROTH
Keyword(s):  
Natural Language ◽  
Question Answering ◽  
Natural Language Understanding ◽  
Language Understanding ◽  
Knowledge Representations ◽  
Semantic Relationships ◽  
Textual Entailment ◽  
Inference Methods ◽  
Recognizing Textual Entailment ◽  
Core Problem

AbstractThe goal of identifying textual entailment – whether one piece of text can be plausibly inferred from another – has emerged in recent years as a generic core problem in natural language understanding. Work in this area has been largely driven by the PASCAL Recognizing Textual Entailment (RTE) challenges, which are a series of annual competitive meetings. The current work exhibits strong ties to some earlier lines of research, particularly automatic acquisition of paraphrases and lexical semantic relationships and unsupervised inference in applications such as question answering, information extraction and summarization. It has also opened the way to newer lines of research on more involved inference methods, on knowledge representations needed to support this natural language understanding challenge and on the use of learning methods in this context. RTE has fostered an active and growing community of researchers focused on the problem of applied entailment. This special issue of the JNLE provides an opportunity to showcase some of the most important work in this emerging area.

Hybrid Deep Neural Model for Duplicate Question Detection in Transliterated Bi-lingual Data

2019 ◽  
Vol 12 ◽  
Author(s):  
Seema Rani ◽  
Avadhesh Kumar ◽  
Naresh Kumar
Keyword(s):  
Question Answering ◽  
Neural Model ◽  
Manhattan Distance ◽  
Semantic Matching ◽  
English Only ◽  
Detection Model ◽  
Proposed Model ◽  
Reported Study ◽  
Social Media Platforms ◽  
Efficient Information

Background: Duplicate content often corrupts the filtering mechanism in online question answering. Moreover, as users are usually more comfortable conversing in their native language questions, transliteration adds to the challenges in detecting duplicate questions. This compromises with the response time and increases the answer overload. Thus, it has now become crucial to build clever, intelligent and semantic filters which semantically match linguistically disparate questions. Objective: Most of the research on duplicate question detection has been done on mono-lingual, majorly English Q&A platforms. The aim is to build a model which extends the cognitive capabilities of machines to interpret, comprehend and learn features for semantic matching in transliterated bi-lingual Hinglish (Hindi + English) data acquired from different Q&A platforms. Method: In the proposed DQDHinglish (Duplicate Question Detection) Model, firstly language transformation (transliteration & translation) is done to convert the bi-lingual transliterated question into a mono-lingual English only text. Next a hybrid of Siamese neural network containing two identical Long-term-Short-memory (LSTM) models and Multi-layer perceptron network is proposed to detect semantically similar question pairs. Manhattan distance function is used as the similarity measure. Result: A dataset was prepared by scrapping 100 question pairs from various social media platforms, such as Quora and TripAdvisor. The performance of the proposed model on the basis of accuracy and F-score. The proposed DQDHinglish achieves a validation accuracy of 82.40%. Conclusion: A deep neural model was introduced to find semantic match between English question and a Hinglish (Hindi + English) question such that similar intent questions can be combined to enable fast and efficient information processing and delivery. A dataset was created and the proposed model was evaluated on the basis of performance accuracy. To the best of our knowledge, this work is the first reported study on transliterated Hinglish semantic question matching.

Single-shot Semantic Matching Network for Moment Localization in Videos

2021 ◽  
Vol 17 (3) ◽  
pp. 1-14
Author(s):  
Xinfang Liu ◽  
Xiushan Nie ◽  
Junya Teng ◽  
Li Lian ◽  
Yilong Yin
Keyword(s):  
Natural Language ◽  
Fixed Number ◽  
Single Shot ◽  
Semantic Matching ◽  
Matching Network ◽  
Attention Model ◽  
Semantic Relationships ◽  
Natural Language Query ◽  
Benchmark Datasets ◽  
Short Memory

Moment localization in videos using natural language refers to finding the most relevant segment from videos given a natural language query. Most of the existing methods require video segment candidates for further matching with the query, which leads to extra computational costs, and they may also not locate the relevant moments under any length evaluated. To address these issues, we present a lightweight single-shot semantic matching network (SSMN) to avoid the complex computations required to match the query and the segment candidates, and the proposed SSMN can locate moments of any length theoretically. Using the proposed SSMN, video features are first uniformly sampled to a fixed number, while the query sentence features are generated and enhanced by GloVe, long-term short memory (LSTM), and soft-attention modules. Subsequently, the video features and sentence features are fed to an enhanced cross-modal attention model to mine the semantic relationships between vision and language. Finally, a score predictor and a location predictor are designed to locate the start and stop indexes of the query moment. We evaluate the proposed method on two benchmark datasets and the experimental results demonstrate that SSMN outperforms state-of-the-art methods in both precision and efficiency.

scholarly journals Technology-Powered Strategies to Rethink the Pedagogy of History and Cultural Heritage through Symmetries and Narratives

Symmetry ◽  
2019 ◽  
Vol 11 (3) ◽  
pp. 367 ◽  
Author(s):  
Martín López-Nores ◽  
Omar Bravo-Quezada ◽  
Maddalena Bassani ◽  
Angeliki Antoniou ◽  
Ioanna Lykourentzou ◽  
...  
Keyword(s):  
Deep Learning ◽  
Semantic Web ◽  
Cultural Heritage ◽  
Digital Humanities ◽  
Teaching And Learning ◽  
Computational Analysis ◽  
Learning Technologies ◽  
Cross Border ◽  
New Information ◽  
New Strategies

Recent advances in semantic web and deep learning technologies enable new means for the computational analysis of vast amounts of information from the field of digital humanities. We discuss how some of the techniques can be used to identify historical and cultural symmetries between different characters, locations, events or venues, and how these can be harnessed to develop new strategies to promote intercultural and cross-border aspects that support the teaching and learning of history and heritage. The strategies have been put to the test in the context of the European project CrossCult, revealing enormous potential to encourage curiosity to discover new information and increase retention of learned information.

An Integer Linear Programming-Based Method for the Extraction of Ontology Alignment

2021 ◽  
Vol 16 (2) ◽  
pp. 25-44
Author(s):  
Naima El Ghandour ◽  
Moussa Benaissa ◽  
Yahia Lebbah
Keyword(s):  
Linear Programming ◽  
Semantic Web ◽  
Integer Linear Programming ◽  
New Method ◽  
Ontology Matching ◽  
Ontology Alignment ◽  
Programming Techniques ◽  
Data Heterogeneity ◽  
Series Of Experiments

The Semantic Web uses ontologies to cope with the data heterogeneity problem. However, ontologies become themselves heterogeneous; this heterogeneity may occur at the syntactic, terminological, conceptual, and semantic levels. To solve this problem, alignments between entities of ontologies must be identified. This process is called ontology matching. In this paper, the authors propose a new method to extract alignment with multiple cardinalities using integer linear programming techniques. The authors conducted a series of experiments and compared them with currently used methods. The obtained results show the efficiency of the proposed method.

Sign in / Sign up

Export Citation Format

Share Document