Search

In the era of rapid paper publications in various venues, automatic citation recommendations would be highly useful to researchers when they write papers. Local citation recommendation aims to recommend possible papers to cite given local citation contexts. Previous work mainly computes the similarity score between citation contexts and cited papers on a one-to-one basis, which is quite time-consuming. We train a pair of neural network encoders that map citation contexts and all possible cited papers to the same vector space, respectively. After that, we index the positions of all cited papers in the vector space. This makes our process for searching recommended papers considerably faster. On the other hand, existing methods tend to recommend papers that are highly similar to each other, which makes recommendations lack diversity. Therefore, we extend our algorithm to perform multi-topic recommendations. We generate multi-topic training examples based on the index we mentioned earlier. Furthermore, we specially design a multi-group contrastive learning method to train our model so that it can distinguish different topics. Empirical experiments show that our model outperforms previous methods by a wide margin. Our model is also light weighted and has been deployed online so that researchers can use it to obtain recommended citations for their own paper in real-time. • Proposed FLCR algorithm with sentence-transformer & k-d tree. • Introduced multi-topic citation recommendation for diverse contexts. • Developed large-scale dataset with 1.7 million citation contexts for evaluation. • Demonstrated significant performance improvement over previous methods. • Deployed demo for real-time citation recommendations. [ABSTRACT FROM AUTHOR]

• Simple first approach based on unsupervised Latent Semantic Indexing lead to state of the art results. • Deep learning approaches help avoid the time consuming step of feature engineering. • Pairwise approaches outperfom pointwise approaches. • Using overlapping terms as inputs to neural networks improve both results and performance. • Using pre-trained word embeddings reduce the overfitting of deep learning models. In this paper we face the problem of Community Question Answering for the Arabic language. In this setting, a member of the community posts an initial query expressed in Natural Language. Other participants post their own interventions: answers, comments, additional questions, etc. contributing to building a rather tangled thread of nodes containing Natural Language short texts. The task consists in answering the initial query using the thread as the space of possible answers. The task can be approached as a classification, a regression or a ranking problem. In our case we select the set of possible candidates, we assign a relevance score to each candidate and we rank them accordingly. We propose a bunch of unsupervised models and show that a model based on Latent Semantic Indexing approach outperforms state of the art models for this task. We also use transfer learning to power the embeddings layer of various deep learning models and prove that the pairwise approaches outperform their pointwise counterparts. All the proposed models have been evaluated on Semeval 2017 Task 3 Subtask D: Arabic Community Question Answering and achieve state of the art or near performance. [ABSTRACT FROM AUTHOR]

• Our approach outperforms previous ones in identifying different query types. • Our approach has practical advantages related to the reduced number of features. • RandomForest outperformed other algorithms with 99.6% accuracy. In real-life classification problems, prior information about the problem and expert knowledge about the domain are often used to obtain reliable and consistent solutions. This is especially true in fields where the data is ambiguous, such as text, in which the same words can be used in seemingly similar texts, but have a different meaning. A promising avenue for text classification is machine learning, which has been shown to perform well in a variety of applications including query classification and sentiment analysis. Many of the proposed approaches rely on the bag-of-words representation, which loses the information about the structure of the text. In this paper, we propose a Customised Grammar Framework for text classification, which exploits domain-related information and a new way to represent text as a series of syntactic categories forming syntactic patterns. The framework employs a formal grammar approach for transforming the text into the syntactic patterns representation. We applied the framework for the query classification problem and our results show that our approach outperforms previous ones in terms of classification performance. [ABSTRACT FROM AUTHOR]

The ubiquitous presence of surveillance systems generates massive amounts of video data. Storage and analysis of this data in real-time is a substantial challenge. There is huge potential in representing data in machine-readable and machine-interpretable format due to the presence of hidden semantics in images and videos. However, such representation requires ontology, which calls for expert domain knowledge. In this paper, a novel NLP-guided approach to generate an ontology for multimedia representation and information retrieval is proposed. A semi-automatic NLP-guided framework, which extracts all possible relations among objects is presented. This framework leverages the textual data of the domain to generate possible descriptions and actions within the domain. Relations among objects get embedded as object properties, whereas the category of an object as a class. Features and attributes of objects encode the data properties of the ontology. The proposed ontology is compared with existing multimedia ontologies and evaluated with regard to its capability to represent relations occurring in benchmark datasets, demonstrating the completeness and thorough coverage of the domain concepts. Spatial reasoning rules are established using Semantic Web Rule Language (SWRL) rules, and information retrieval is demonstrated using Description Logic (DL) and SPARQL queries. The proposed NLP-guided ontology generation approach is general enough to help in the development of ontologies for other domains as well, by providing video and textual data of the domain of interest, with limited human involvement. • Object properties extraction with textbase and NLP-guided approach. • Frequency-based semantic refinement to enhance domain-specific relations. • A novel data-driven video surveillance ontology "VizITS" for the ITS domain. • Semantic information retrieval as events, metadata, and question-answering. [ABSTRACT FROM AUTHOR]

The ubiquitous presence of surveillance systems generates massive amounts of video data. Storage and analysis of this data in real-time is a substantial challenge. There is huge potential in representing data in machine-readable and machine-interpretable format due to the presence of hidden semantics in images and videos. However, such representation requires ontology, which calls for expert domain knowledge. In this paper, a novel NLP-guided approach to generate an ontology for multimedia representation and information retrieval is proposed. A semi-automatic NLP-guided framework, which extracts all possible relations among objects is presented. This framework leverages the textual data of the domain to generate possible descriptions and actions within the domain. Relations among objects get embedded as object properties, whereas the category of an object as a class. Features and attributes of objects encode the data properties of the ontology. The proposed ontology is compared with existing multimedia ontologies and evaluated with regard to its capability to represent relations occurring in benchmark datasets, demonstrating the completeness and thorough coverage of the domain concepts. Spatial reasoning rules are established using Semantic Web Rule Language (SWRL) rules, and information retrieval is demonstrated using Description Logic (DL) and SPARQL queries. The proposed NLP-guided ontology generation approach is general enough to help in the development of ontologies for other domains as well, by providing video and textual data of the domain of interest, with limited human involvement. • Object properties extraction with textbase and NLP-guided approach. • Frequency-based semantic refinement to enhance domain-specific relations. • A novel data-driven video surveillance ontology "VizITS" for the ITS domain. • Semantic information retrieval as events, metadata, and question-answering. [ABSTRACT FROM AUTHOR]

• Propose a hybrid Transformer approach for Chinese NER. • Take the latent words as the additional features to improve NER task. • Find an efficient strategy to fine-tune BERT with other modules. • Apply relative position encodings to improve Transformer. Named entity recognition (NER) plays an important role in many downstream tasks of natural language processing, such as knowledge extraction and information retrieval. NER of Chinese is more challenging than that of English due to lack of the explicit word boundary. Features augmentation is a potential way to improve NER model of Chinese. Pre-trained models can implicitly preserve prior knowledge with additional features. This paper proposes a hybrid Transformer approach, which first utilize the fused additional features embeddings (e.g. char embeddings, bigram embeddings, lattice embeddings and BERT embeddings) as distributed representations to augment the representation ability of model. In addition, a new training strategy named DF strategy is proposed to efficiently fine-tune Bidirectional Encoder Representations from Transformers (BERT) and other embeddings in balance. Then, the proposed model can perceive the relations of features by introducing relative position embeddings to an additional adapted Transformer encoder. Lastly, a standard Conditional Random Field is used to alleviate the obvious tag errors. The proposed model is applied to four representative Chinese datasets to investigate its performance. Experiments results show that the proposed model outperforms the other popular models in terms of accuracy. The proposed BL-BTC model can effectively improve the recognition performance of formal and informal texts. [ABSTRACT FROM AUTHOR]

As e-commerce markets have gradually expanded, online shopping malls have provided various services aiming to secure competitiveness. A service for providing an accurate and prompt response when a customer writes an inquiry regarding a product represents a space directly connected to the customer and plays an important role, as it is directly related to product sales. However, the current online shopping mall answering service has disadvantages, e.g., it takes time for an administrator to write an answer directly, or to provide an answer within a set of answers. In this paper, we propose an answer framework for solving this problem, based on customer reviews. When a user writes a query, the framework provides an appropriate answer in real time through the system's question-and-answer pairs and customer reviews. The framework's performance is verified through a qualitative evaluation. In addition, it is confirmed that a customized model for reflecting the characteristics of each shopping mall can be created by using additional information from the collected data. The proposed framework is expected to support customers' online shopping through more reliable and efficient information retrieval, and to reduce shopping mall operation and maintenance costs. • We proposed an answer framework using Q&A pairs and customer reviews. • We obtained high performance in customer reviews category classification. • We provided customer reviews suitable for users' inquiries along with Q&A data. • A qualitative evaluation was conducted on the system output for any input query. • We provided a customized model framework for the Q&A system. [ABSTRACT FROM AUTHOR]

Rank aggregation mechanisms have been used in solving problems from various domains such as bioinformatics, natural language processing, information retrieval, etc. Metasearch is one such application where a user gives a query to the metasearch engine, and the metasearch engine forwards the query to multiple individual search engines. Results or rankings returned by these individual search engines are combined using rank aggregation algorithms to produce the final result to be displayed to the user. We identify few aspects that should be kept in mind for designing any rank aggregation algorithm for metasearch. For example, generally equal importance is given to the input rankings while performing the aggregation. However, depending on the indexed set of web pages, features considered for ranking, ranking functions used etc. by the individual search engines, the individual rankings may be of different qualities. So, the aggregation algorithm should give more weight to the better rankings while giving less weight to others. Also, since the aggregation is performed when the user is waiting for response, the operations performed in the algorithm need to be light weight. Moreover, getting supervised data for rank aggregation problem is often difficult. In this paper, we present an unsupervised rank aggregation algorithm that is suitable for metasearch and addresses the aspects mentioned above. We also perform detailed experimental evaluation of the proposed algorithm on four different benchmark datasets having ground truth information. Apart from the unsupervised Kendall-Tau distance measure, several supervised evaluation measures are used for performance comparison. Experimental results demonstrate the efficacy of the proposed algorithm over baseline methods in terms of supervised evaluation metrics. Through these experiments we also show that Kendall-Tau distance metric may not be suitable for evaluating rank aggregation algorithms for metasearch. [ABSTRACT FROM AUTHOR]

The Semantic Web has emerged as an extension of the current Web, in which Web content has well-defined meaning through the addition of logic-based metadata. However, current mechanisms for information retrieval from semantic knowledge bases restrict their use to only experienced users. To address this gap, the natural language processing (NLP) is deemed to be very intuitive from a use point of view, due to it hides the formality of a knowledge base as well as the executable query language. This paper presents a novel ontology-based information retrieval system for DBpedia called ONLI (Ontology-based Natural Language Interface). ONLI proposes the use of an ontology model in order to represent both the syntactic question’s structure and the question’s context. This model allows inferring the answer type expected by the user through an established question’s classification. These features allow reducing the search space thus increasing the probability of providing the correct answer. From this perspective, ONLI was evaluated in terms of their ability to find the correct answer into DBpedia’s content, achieving promising results and proving to be very useful to non-experienced users. [ABSTRACT FROM AUTHOR]

The paper presents a novel method of finding a fragment in a long temporal sequence similar to the set of shorter sequences. We are the first to propose an algorithm for such a search that does not rely on computing the average sequence from query examples. Instead, we use query examples as is, utilizing all of them simultaneously. The introduced method based on the Dynamic Time Warping (DTW) technique is suited explicitly for few-shot query-by-example retrieval tasks. We evaluate it on two different few-shot problems from the field of Natural Language Processing. The results show it either outperforms baselines and previous approaches or achieves comparable results when a low number of examples is available. • Varied Information Retrieval problems can be treated as sub-sequence matching. • A new method for finding a fragment of sequence similar to a few examples is proposed. • It can retrieve sequential information from an untrimmed stream, e.g., text and video. • Has good computational complexity and establishes a new direction for few-shot retrieval problems. [ABSTRACT FROM AUTHOR]

• Latent Semantic Analysis is syntactically blind. • LSA is unable to handle negation in sentences. • xLSA uses Syntactic Information to enhance semantic similarity results. • xLSA outperforms neural network-based models on simple inverse sentences. Natural Language Processing (NLP) is the sub-field of Artificial Intelligence that represents and analyses human language automatically. NLP has been employed in many applications, such as information retrieval, information processing and automated answer ranking. Semantic analysis focuses on understanding the meaning of text. Among other proposed approaches, Latent Semantic Analysis (LSA) is a widely used corpus-based approach that evaluates similarity of text based on the semantic relations among words. LSA has been applied successfully in diverse language systems for calculating the semantic similarity of texts. LSA ignores the structure of sentences, i.e., it suffers from a syntactic blindness problem. LSA fails to distinguish between sentences that contain semantically similar words but have opposite meanings. Disregarding sentence structure, LSA cannot differentiate between a sentence and a list of keywords. If the list and the sentence contain similar words, comparing them using LSA would lead to a high similarity score. In this paper, we propose xLSA, an extension of LSA that focuses on the syntactic structure of sentences to overcome the syntactic blindness problem of the original LSA approach. xLSA was tested on sentence pairs that contain similar words but have significantly different meaning. Our results showed that xLSA alleviates the syntactic blindness problem, providing more realistic semantic similarity scores. [ABSTRACT FROM AUTHOR]