首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献，搜索用时 468 毫秒
1.
Pseudo-relevance feedback (PRF) is a well-known method for addressing the mismatch between query intention and query representation. Most current PRF methods consider relevance matching only from the perspective of terms used to sort feedback documents, thus possibly leading to a semantic gap between query representation and document representation. In this work, a PRF framework that combines relevance matching and semantic matching is proposed to improve the quality of feedback documents. Specifically, in the first round of retrieval, we propose a reranking mechanism in which the information of the exact terms and the semantic similarity between the query and document representations are calculated by bidirectional encoder representations from transformers (BERT); this mechanism reduces the text semantic gap by using the semantic information and improves the quality of feedback documents. Then, our proposed PRF framework is constructed to process the results of the first round of retrieval by using probability-based PRF methods and language-model-based PRF methods. Finally, we conduct extensive experiments on four Text Retrieval Conference (TREC) datasets. The results show that the proposed models outperform the robust baseline models in terms of the mean average precision (MAP) and precision P at position 10 (P@10), and the results also highlight that using the combined relevance matching and semantic matching method is more effective than using relevance matching or semantic matching alone in terms of improving the quality of feedback documents.  相似文献   

2.
The effectiveness of query expansion methods depends essentially on identifying good candidates, or prospects, semantically related to query terms. Word embeddings have been used recently in an attempt to address this problem. Nevertheless query disambiguation is still necessary as the semantic relatedness of each word in the corpus is modeled, but choosing the right terms for expansion from the standpoint of the un-modeled query semantics remains an open issue. In this paper we propose a novel query expansion method using word embeddings that models the global query semantics from the standpoint of prospect vocabulary terms. The proposed method allows to explore query-vocabulary semantic closeness in such a way that new terms, semantically related to more relevant topics, are elicited and added in function of the query as a whole. The method includes candidates pooling strategies that address disambiguation issues without using exogenous resources. We tested our method with three topic sets over CLEF corpora and compared it across different Information Retrieval models and against another expansion technique using word embeddings as well. Our experiments indicate that our method achieves significant results that outperform the baselines, improving both recall and precision metrics without relevance feedback.  相似文献   

3.
Existing approaches in online health question answering (HQA) communities to identify the quality of answers either address it subjectively by human assessment or mainly using textual features. This process may be time-consuming and lose the semantic information of answers. We present an automatic approach for predicting answer quality that combines sentence-level semantics with textual and non-textual features in the context of online healthcare. First, we extend the knowledge adoption model (KAM) theory to obtain the six dimensions of quality measures for textual and non-textual features. Then we apply the Bidirectional Encoder Representations from Transformers (BERT) model for extracting semantic features. Next, the multi-dimensional features are processed for dimensionality reduction using linear discriminant analysis (LDA). Finally, we incorporate the preprocessed features into the proposed BK-XGBoost method to automatically predict the answer quality. The proposed method is validated on a real-world dataset with 48121 question-answer pairs crawled from the most popular online HQA communities in China. The experimental results indicate that our method competes against the baseline models on various evaluation metrics. We found up to 2.9% and 5.7% improvement in AUC value in comparison with BERT and XGBoost models respectively.  相似文献   

4.
As an effective technique for improving retrieval effectiveness, relevance feedback (RF) has been widely studied in both monolingual and translingual information retrieval (TLIR). The studies of RF in TLIR have been focused on query expansion (QE), in which queries are reformulated before and/or after they are translated. However, RF in TLIR actually not only can help select better query terms, but also can enhance query translation by adjusting translation probabilities and even resolving some out-of-vocabulary terms. In this paper, we propose a novel relevance feedback method called translation enhancement (TE), which uses the extracted translation relationships from relevant documents to revise the translation probabilities of query terms and to identify extra available translation alternatives so that the translated queries are more tuned to the current search. We studied TE using pseudo-relevance feedback (PRF) and interactive relevance feedback (IRF). Our results show that TE can significantly improve TLIR with both types of relevance feedback methods, and that the improvement is comparable to that of query expansion. More importantly, the effects of translation enhancement and query expansion are complementary. Their integration can produce further improvement, and makes TLIR more robust for a variety of queries.  相似文献   

5.
Aspect-based sentiment analysis aims to determine sentiment polarities toward specific aspect terms within the same sentence or document. Most recent studies adopted attention-based neural network models to implicitly connect aspect terms with context words. However, these studies were limited by insufficient interaction between aspect terms and opinion words, leading to poor performance on robustness test sets. In addition, we have found that robustness test sets create new sentences that interfere with the original information of a sentence, which often makes the text too long and leads to the problem of long-distance dependence. Simultaneously, these new sentences produce more non-target aspect terms, misleading the model because of the lack of relevant knowledge guidance. This study proposes a knowledge guided multi-granularity graph convolutional neural network (KMGCN) to solve these problems. The multi-granularity attention mechanism is designed to enhance the interaction between aspect terms and opinion words. To address the long-distance dependence, KMGCN uses a graph convolutional network that relies on a semantic map based on fine-tuning pre-trained models. In particular, KMGCN uses a mask mechanism guided by conceptual knowledge to encounter more aspect terms (including target and non-target aspect terms). Experiments are conducted on 12 SemEval-2014 variant benchmarking datasets, and the results demonstrated the effectiveness of the proposed framework.  相似文献   

6.
Automatically assessing academic papers has enormous potential to reduce peer-review burden and individual bias. Existing studies strive for building sophisticated deep neural networks to identify academic value based on comprehensive data, e.g., academic graphs and full papers. However, these data are not always easy to access. And the content of the paper rather than other features outside the paper should matter in a fair assessment. Furthermore, while BERT models can maintain general semantics by pre-training on large-scale corpora, they tend to be over-smoothing due to stacked self-attention layers among unfiltered input tokens. Therefore, it is nontrivial to figure out distinguishable value of an academic paper from its limited content. In this study, we propose a novel deep neural network, namely Dual-view Graph Convolutions Enhanced BERT (DGC-BERT), for academic paper acceptance estimation. We combine the title and abstract of the paper as input. Then, a pre-trained BERT model is employed to extract the paper’s general representations. Apart from hidden representations of the final layer, we highlight the first and last few layers as lexical and semantic views. In particular, we re-examine the dual-view filtered self-attention matrices via constructing two graphs, respectively. After that, two multi-hop Graph Convolutional Networks (GCNs) are separately employed to capture pivotal and distant dependencies between the tokens. Moreover, the dual-view representations are facilitated by each other with biaffine attention modules. And a re-weighting gate is proposed to further streamline the dual-view representations with the help of the original BERT representation. Finally, whether the submitted paper could be acceptable is predicted based on the original language model features cooperated with the dual-view dependencies. Extensive data analyses and the full paper based MHCNN studies provide insights into the task and structural functions. Comparison experiments on two benchmark datasets demonstrate that the proposed DGC-BERT significantly outperforms alternative approaches, especially the state-of-the-art models like MHCNN and BERT variants. Additional analyses reveal significance and explainability of the proposed modules in the DGC-BERT. Our codes and settings have been released on Github (https://github.com/ECNU-Text-Computing/DGC-BERT).  相似文献   

7.
We demonstrate effective new methods of document ranking based on lexical cohesive relationships between query terms. The proposed methods rely solely on the lexical relationships between original query terms, and do not involve query expansion or relevance feedback. Two types of lexical cohesive relationship information between query terms are used in document ranking: short-distance collocation relationship between query terms, and long-distance relationship, determined by the collocation of query terms with other words. The methods are evaluated on TREC corpora, and show improvements over baseline systems.  相似文献   

8.
Automatic text classification is the task of organizing documents into pre-determined classes, generally using machine learning algorithms. Generally speaking, it is one of the most important methods to organize and make use of the gigantic amounts of information that exist in unstructured textual format. Text classification is a widely studied research area of language processing and text mining. In traditional text classification, a document is represented as a bag of words where the words in other words terms are cut from their finer context i.e. their location in a sentence or in a document. Only the broader context of document is used with some type of term frequency information in the vector space. Consequently, semantics of words that can be inferred from the finer context of its location in a sentence and its relations with neighboring words are usually ignored. However, meaning of words, semantic connections between words, documents and even classes are obviously important since methods that capture semantics generally reach better classification performances. Several surveys have been published to analyze diverse approaches for the traditional text classification methods. Most of these surveys cover application of different semantic term relatedness methods in text classification up to a certain degree. However, they do not specifically target semantic text classification algorithms and their advantages over the traditional text classification. In order to fill this gap, we undertake a comprehensive discussion of semantic text classification vs. traditional text classification. This survey explores the past and recent advancements in semantic text classification and attempts to organize existing approaches under five fundamental categories; domain knowledge-based approaches, corpus-based approaches, deep learning based approaches, word/character sequence enhanced approaches and linguistic enriched approaches. Furthermore, this survey highlights the advantages of semantic text classification algorithms over the traditional text classification algorithms.  相似文献   

9.
Fact verification aims to retrieve relevant evidence from a knowledge base, e.g., Wikipedia, to verify the given claims. Existing methods only consider the sentence-level semantics for evidence representations, which typically neglect the importance of fine-grained features in the evidence-related sentences. In addition, the interpretability of the reasoning process has not been well studied in the field of fact verification. To address such issues, we propose an entity-graph based reasoning method for fact verification abbreviated as RoEG, which generates the fine-grained features of evidence at the entity-level and models the human reasoning paths based on an entity graph. In detail, to capture the semantic relations of retrieved evidence, RoEG introduces the entities as nodes and constructs the edges in the graph based on three linking strategies. Then, RoEG utilizes a selection gate to constrain the information propagation in the sub-graph of relevant entities and applies a graph neural network to propagate the entity-features for reasoning. Finally, RoEG employs an attention aggregator to gather the information of entities for label prediction. Experimental results on a large-scale benchmark dataset FEVER demonstrate the effectiveness of our proposal by beating the competitive baselines in terms of label accuracy and FEVER Score. In particular, for a task of multiple-evidence fact verification, RoEG produces 5.48% and 4.35% improvements in terms of label accuracy and FEVER Score against the state-of-the-art baseline. In addition, RoEG shows a better performance when more entities are involved for fact verification.  相似文献   

10.
Pseudo-relevance feedback is the basis of a category of automatic query modification techniques. Pseudo-relevance feedback methods assume the initial retrieved set of documents to be relevant. Then they use these documents to extract more relevant terms for the query or just re-weigh the user's original query. In this paper, we propose a straightforward, yet effective use of pseudo-relevance feedback method in detecting more informative query terms and re-weighting them. The query-by-query analysis of our results indicates that our method is capable of identifying the most important keywords even in short queries. Our main idea is that some of the top documents may contain a closer context to the user's information need than the others. Therefore, re-examining the similarity of those top documents and weighting this set based on their context could help in identifying and re-weighting informative query terms. Our experimental results in standard English and Persian test collections show that our method improves retrieval performance, in terms of MAP criterion, up to 7% over traditional query term re-weighting methods.  相似文献   

11.
Rocchio relevance feedback and latent semantic indexing (LSI) are well-known extensions of the vector space model for information retrieval (IR). This paper analyzes the statistical relationship between these extensions. The analysis focuses on each method’s basis in least-squares optimization. Noting that LSI and Rocchio relevance feedback both alter the vector space model in a way that is in some sense least-squares optimal, we ask: what is the relationship between LSI’s and Rocchio’s notions of optimality? What does this relationship imply for IR? Using an analytical approach, we argue that Rocchio relevance feedback is optimal if we understand retrieval as a simplified classification problem. On the other hand, LSI’s motivation comes to the fore if we understand it as a biased regression technique, where projection onto a low-dimensional orthogonal subspace of the documents reduces model variance.  相似文献   

12.
The disambiguation of abbreviations is a crucial step in medical knowledge organization. In the past, most scholars have focused on the problem of disambiguating medical abbreviations in single sentences; they have not systematically considered full-article abbreviation disambiguation tasks. In this work, we present a research framework for full-article medical abbreviation disambiguation (FMADRF) based on the structural characteristics of abbreviation–definition pairs in a full scientific medical article. Our method utilizes the information including context semantic information, external linguistic features, and the mapping relationships and structural similarities between abbreviations and their expansions. The model includes a four-pronged approach, identification of abbreviations and abbreviation–definition pairs, alignment and complementation of abbreviations and abbreviation expansions. The results show that our novel BBF-BLC-R model improves the recognition and modification effects of abbreviation–definition pairs, achieving the best F1 score of 91.83%. Furthermore, our new strategy combines semantic and structural information to significantly improve the effects of term alignment, with an F1 score of 97.11%. In our test, a thesaurus of abbreviations and their expansions was constructed from 13,472 full-text medical articles, resulting in 14,742 abbreviations, with 31,327 corresponding expansions. This work enhances the semantic association of terms in full medical texts, eliminating the problems of “rich” semantics and association–relation roadblocks caused by term misalignments. It further provides technical and methodological support for the organization of medical knowledge, facilitating the deep knowledge-mining capabilities of full-text medical articles.  相似文献   

13.
Today, due to a vast amount of textual data, automated extractive text summarization is one of the most common and practical techniques for organizing information. Extractive summarization selects the most appropriate sentences from the text and provide a representative summary. The sentences, as individual textual units, usually are too short for major text processing techniques to provide appropriate performance. Hence, it seems vital to bridge the gap between short text units and conventional text processing methods.In this study, we propose a semantic method for implementing an extractive multi-document summarizer system by using a combination of statistical, machine learning based, and graph-based methods. It is a language-independent and unsupervised system. The proposed framework learns the semantic representation of words from a set of given documents via word2vec method. It expands each sentence through an innovative method with the most informative and the least redundant words related to the main topic of sentence. Sentence expansion implicitly performs word sense disambiguation and tunes the conceptual densities towards the central topic of each sentence. Then, it estimates the importance of sentences by using the graph representation of the documents. To identify the most important topics of the documents, we propose an inventive clustering approach. It autonomously determines the number of clusters and their initial centroids, and clusters sentences accordingly. The system selects the best sentences from appropriate clusters for the final summary with respect to information salience, minimum redundancy, and adequate coverage.A set of extensive experiments on DUC2002 and DUC2006 datasets was conducted for investigating the proposed scheme. Experimental results showed that the proposed sentence expansion algorithm and clustering approach could considerably enhance the performance of the summarization system. Also, comparative experiments demonstrated that the proposed framework outperforms most of the state-of-the-art summarizer systems and can impressively assist the task of extractive text summarization.  相似文献   

14.
Sentiment analysis concerns the study of opinions expressed in a text. This paper presents the QMOS method, which employs a combination of sentiment analysis and summarization approaches. It is a lexicon-based method to query-based multi-documents summarization of opinion expressed in reviews.QMOS combines multiple sentiment dictionaries to improve word coverage limit of the individual lexicon. A major problem for a dictionary-based approach is the semantic gap between the prior polarity of a word presented by a lexicon and the word polarity in a specific context. This is due to the fact that, the polarity of a word depends on the context in which it is being used. Furthermore, the type of a sentence can also affect the performance of a sentiment analysis approach. Therefore, to tackle the aforementioned challenges, QMOS integrates multiple strategies to adjust word prior sentiment orientation while also considers the type of sentence. QMOS also employs the Semantic Sentiment Approach to determine the sentiment score of a word if it is not included in a sentiment lexicon.On the other hand, the most of the existing methods fail to distinguish the meaning of a review sentence and user's query when both of them share the similar bag-of-words; hence there is often a conflict between the extracted opinionated sentences and users’ needs. However, the summarization phase of QMOS is able to avoid extracting a review sentence whose similarity with the user's query is high but whose meaning is different. The method also employs the greedy algorithm and query expansion approach to reduce redundancy and bridge the lexical gaps for similar contexts that are expressed using different wording, respectively. Our experiment shows that the QMOS method can significantly improve the performance and make QMOS comparable to other existing methods.  相似文献   

15.
Information filtering (IF) systems usually filter data items by correlating a set of terms representing the user’s interest (a user profile) with similar sets of terms representing the data items. Many techniques can be employed for constructing user profiles automatically, but they usually yield large sets of term. Various dimensionality-reduction techniques can be applied in order to reduce the number of terms in a user profile. We describe a new terms selection technique including a dimensionality-reduction mechanism which is based on the analysis of a trained artificial neural network (ANN) model. Its novel feature is the identification of an optimal set of terms that can classify correctly data items that are relevant to a user. The proposed technique was compared with the classical Rocchio algorithm. We found that when using all the distinct terms in the training set to train an ANN, the Rocchio algorithm outperforms the ANN based filtering system, but after applying the new dimensionality-reduction technique, leaving only an optimal set of terms, the improved ANN technique outperformed both the original ANN and the Rocchio algorithm.  相似文献   

16.
Query Expansion (QE) is one of the most important mechanisms in the information retrieval field. A typical short Internet query will go through a process of refinement to improve its retrieval power. Most of the existing QE techniques suffer from retrieval performance degradation due to imprecise choice of query’s additive terms in the QE process. In this paper, we introduce a novel automated QE mechanism. The new expansion process is guided by the semantics relations between the original query and the expanding words, in the context of the utilized corpus. Experimental results of our “controlled” query expansion, using the Arabic TREC-10 data, show a significant enhancement of recall and precision over current existing mechanisms in the field.  相似文献   

17.
Existing unsupervised keyphrase extraction methods typically emphasize the importance of the candidate keyphrase itself, ignoring other important factors such as the influence of uninformative sentences. We hypothesize that the salient sentences of a document are particularly important as they are most likely to contain keyphrases, especially for long documents. To our knowledge, our work is the first attempt to exploit sentence salience for unsupervised keyphrase extraction by modeling hierarchical multi-granularity features. Specifically, we propose a novel position-aware graph-based unsupervised keyphrase extraction model, which includes two model variants. The pipeline model first extracts salient sentences from the document, followed by keyphrase extraction from the extracted salient sentences. In contrast to the pipeline model which models multi-granularity features in a two-stage paradigm, the joint model accounts for both sentence and phrase representations of the source document simultaneously via hierarchical graphs. Concretely, the sentence nodes are introduced as an inductive bias, injecting sentence-level information for determining the importance of candidate keyphrases. We compare our model against strong baselines on three benchmark datasets including Inspec, DUC 2001, and SemEval 2010. Experimental results show that the simple pipeline-based approach achieves promising results, indicating that keyphrase extraction task benefits from the salient sentence extraction task. The joint model, which mitigates the potential accumulated error of the pipeline model, gives the best performance and achieves new state-of-the-art results while generalizing better on data from different domains and with different lengths. In particular, for the SemEval 2010 dataset consisting of long documents, our joint model outperforms the strongest baseline UKERank by 3.48%, 3.69% and 4.84% in terms of F1@5, F1@10 and F1@15, respectively. We also conduct qualitative experiments to validate the effectiveness of our model components.  相似文献   

18.
Pseudo-relevance feedback (PRF) is a classical technique to improve search engine retrieval effectiveness, by closing the vocabulary gap between users’ query formulations and the relevant documents. While PRF is typically applied on the same target corpus as the final retrieval, in the past, external expansion techniques have sometimes been applied to obtain a high-quality pseudo-relevant feedback set using the external corpus. However, such external expansion approaches have only been studied for sparse (BoW) retrieval methods, and its effectiveness for recent dense retrieval methods remains under-investigated. Indeed, dense retrieval approaches such as ANCE and ColBERT, which conduct similarity search based on encoded contextualised query and document embeddings, are of increasing importance. Moreover, pseudo-relevance feedback mechanisms have been proposed to further enhance dense retrieval effectiveness. In particular, in this work, we examine the application of dense external expansion to improve zero-shot retrieval effectiveness, i.e. evaluation on corpora without further training. Zero-shot retrieval experiments with six datasets, including two TREC datasets and four BEIR datasets, when applying the MSMARCO passage collection as external corpus, indicate that obtaining external feedback documents using ColBERT can significantly improve NDCG@10 for the sparse retrieval (by upto 28%) and the dense retrieval (by upto 12%). In addition, using ANCE on the external corpus brings upto 30% NDCG@10 improvements for the sparse retrieval and upto 29% for the dense retrieval.  相似文献   

19.
In this paper, a new robust relevance model is proposed that can be applied to both pseudo and true relevance feedback in the language-modeling framework for document retrieval. There are at least three main differences between our new relevance model and other relevance models. The proposed model brings back the original query into the relevance model by treating it as a short, special document, in addition to a number of top-ranked documents returned from the first round retrieval for pseudo feedback, or a number of relevant documents for true relevance feedback. Second, instead of using a uniform prior as in the original relevance model proposed by Lavrenko and Croft, documents are assigned with different priors according to their lengths (in terms) and ranks in the first round retrieval. Third, the probability of a term in the relevance model is further adjusted by its probability in a background language model. In both pseudo and true relevance cases, we have compared the performance of our model to that of the two baselines: the original relevance model and a linear combination model. Our experimental results show that the proposed new model outperforms both of the two baselines in terms of mean average precision.  相似文献   

20.
This paper examines the meaning of context in relation to ontology based query expansion and contains a review of query expansion approaches. The various query expansion approaches include relevance feedback, corpus dependent knowledge models and corpus independent knowledge models. Case studies detailing query expansion using domain-specific and domain-independent ontologies are also included. The penultimate section attempts to synthesise the information obtained from the review and provide success factors in using an ontology for query expansion. Finally the area of further research in applying context from an ontology to query expansion within a newswire domain is described.  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号