Learning-Based Pseudo-Relevance Feedback for Patent Retrieval

Vocabulary mismatch in Information retrieval can be solved by Query Expansion (QE) techniques. Relevance feedback is a prominent solution to improve recall of retrieval system. Sometimes user may be reluctant and novice in providing feedback to improve the retrieval performance. Pseudo Relevance Feedback (PRF) automates the process. PRF treats top ranked resultant items are relevant and uses them to expand the query, which is not always correct. PRF by local analysis does not give guarantee to feedback positive terms to the system. Use of global analysis to capture the positive feedback is a regular practice in information retrieval process. This paper addresses the limitations of local analysis and global analysis alone by a novel approach that integrates both PRF and WordNet to select good expansion terms. The proposed solution filters the expansion terms and optimizes the expanded query. The proposed work is carried out on a huge Telugu text corpus collected from Wikipedia and other Telugu daily news portals.

The First International Workshop on Graph-Based Approaches in Information Retrieval (IRonGraphs 2024) was held as a physical (in-person) event on March 24, 2024, in conjunction with the 46th European Conference on Information Retrieval (ECIR 2024) in Glasgow (Scotland). The scientific program included paper, spotlight, and poster presentations. Two keynote talks were delivered by Francesco Fabbri (Spotify, Spain) and Ruihong Qiu (University of Queensland, Australia). This report presents an overview of the activities conducted during the workshop and the main topics covered. Date : 24 March 2024. Website : https://irongraphs.github.io/ecir2024/.

Microblog retrieval has received much attention in recent years due to the wide spread of social microblogging platforms such as Twitter. Many research studies investigated different approaches for microblog retrieval. Query expansion is one of the approaches that showed stable performance for improving microblog retrieval effectiveness. In this paper we comprehensively investigate query expansion for microblog retrieval using pseudo relevance feedback (PRF) with different configurations. In addition, we propose a hyperlink-extended PRF by expanding queries using embedded hyperlinks in retrieved microblogs. Our experimental results on TREC microblog data showed that PRF alone could outperform many retrieval approaches if configured properly. Results also showed that utilizing hyperlinked documents in tweets for query expansion improves results over traditional PRF. Our best results achieved using hyperlink-extended PRF outperformed most of the reported results using other approaches.

Queries in patent prior art search are full patent applications and much longer than standard ad hoc search and web search topics. Standard information retrieval (IR) techniques are not entirely effective for patent prior art search because of ambiguous terms in these massive queries. Reducing patent queries by extracting key terms has been shown to be ineffective mainly because it is not clear what the focus of the query is. An optimal query reduction algorithm must thus seek to retain the useful terms for retrieval favouring recall of relevant patents, but remove terms which impair IR effectiveness. We propose a new query reduction technique decomposing a patent application into constituent text segments and computing the Language Modeling (LM) similarities by calculating the probability of generating each segment from the top ranked documents. We reduce a patent query by removing the least similar segments from the query, hypothesising that removal of these segments can increase the precision of retrieval, while still retaining the useful context to achieve high recall. Experiments on the patent prior art search collection CLEF-IP 2010 show that the proposed method outperforms standard pseudo-relevance feedback (PRF) and a naive method of query reduction based on removal of unit frequency terms (UFTs).

In this paper, we propose a novel information retrieval approach based on the pragmatic information for Chinese patents. At present, patent retrieval is becoming more and more important. Not only because patents are always can an important resource in all kinds of field, but patent retrieval save a great deal of time and funds for corporations and researchers. However, with available methods the precision of retrieval results for patents is not very high. What's more, through analyzed the patent documentations we found that except the literal meanings, there are deeper meanings which can be concluded from the patents. Here we call the deeper meanings as pragmatic information. Therefore we established a patent retrieval system to integrate the pragmatic information with classical information retrieval technique to improve the retrieval accuracy. Some experiments using the proposed method have carried out, and the results show that the precision of patent retrieval based on the pragmatic information is higher than the one without using it.

Pseudo-relevance feedback (PRF) is a very effective query expansion approach, which reformulates queries by selecting expansion terms from top k pseudo-relevant documents. Although standard PRF models have been proven effective to deal with vocabulary mismatch between users’ queries and relevant documents, expansion terms are selected without considering their similarity to the original query terms. In this article, we propose a method to incorporate word embedding (WE) similarity into PRF models for Arabic information retrieval (IR). The main idea is to select expansion terms using their distribution in the set of top pseudo-relevant documents along with their similarity to the original query terms. Experiments are conducted on the standard Arabic TREC 2001/2002 collection using three neural WE models. The obtained results show that our PRF extensions significantly outperform their baseline PRF models. Moreover, they enhanced the baseline IR model by 22% and 68% for the mean average precision (MAP) and the robustness index (RI), respectively.

Query-document vocabulary mismatch, the lack of query expressiveness for user needs and the phenomenon of short queries are the main issues associated with information retrieval systems. Query Expansion (QE) is one of the well-known alternative for overcoming these problems. It mainly involves finding synonyms or related words for the query terms. There are several approaches in the query expansion field such as statistical and semantic approaches; they focus on expanding the individual query terms rather than the entire query during the expansion process. An other category of approaches deals with the whole query by using a neural approach based on Pseudo Relevance feedback (PRF) documents. In this work, we carried out an ablation study to measure the impact of the classical and semantic (word embedding, order, context) based query expansion on the retrieval performance. The experiments conducted on the Arabic EveTAR dataset reveal that our hybrid proposed approach combining classical (PRF) and transformer (AraBERT) is competitive with the state-of-the-art methods. In fact, the obtained result in terms of the Mean Average Precision (MAP) is up to 0.72.

A semantic framework for enhancing pseudo-relevance feedback with soft negative sampling and contrastive learning

This paper introduced a LDA-based pseudo relevance feedback (PRF) model for cross language information retrieval. To validate the performance of PRF techniques in CLIR task, we conducted cross language query expansion experiments based on a self-constructed CLIR system, the LDA-based PRF model was applied before or after the query translating process, namely the pre-translation-PRF, the post-translation-PRF, and the combined-PRF strategy. We also compared this model with the classical VSM-based PRF algorithm. Experiment results showed that the proposed LDA-based PRF method was effective for improving the performance of CLIR.

Along with the exponential growth of text data on the Web, particularly of the user-generated content, comes an increasing need for hierarchically organizing documents, retrieving documents accurately, and discovering evolutionary trends of various popular topics from the data. However, all of these are challenging due to the diversity, heterogeneity, noisiness and time-sensitivity of Web 2.0 data. Motivated by this, we tackle the challenges at a fundamental level, by proposing a novel topic modeling method with ontological guidance. It may be used to discover topic language models formalizing various terms relevant to given topics using the Web data. The topic model takes into account both the ontological relationships amongst the topics defined in a topic taxonomy and also word co-occurrence patterns in the data to automatically identify the portions in the data relevant to the topics. Then, it estimates language models for these topics from these relevant portions. At an application level, we use the topic model to propose novel approaches for three different tasks, namely hierarchical text classification without labeled data, information retrieval with pseudo-relevance feedback, and discovering topic evolutionary trends. Our classification experiment on the IPTC (International Press and Telecommunications Council) taxonomy, containing more than 1100 topics, shows that our approach achieves a performance of 67% in terms of the hierarchical version of the F-1 measure, without using any labeled data. Our retrieval experiments on five benchmark datasets show that compared to baseline retrieval (without pseudo-relevance feed-back), our approach improves on average 39% in terms of mean average precision. Finally, for the last task, using blog data, our approach discovers meaningful insights on how the crowd responds to various news topics such as the language used to discuss each topic, how this language drifts over time, and when the crowd’s focus on a topic increases, reaches a peak, and declines.

Information retrieval using word senses is emerging as a good research challenge on semantic information retrieval. In this paper, we propose a new method using word senses in information retrieval: root sense tagging method. This method assigns coarse-grained word senses defined in WordNet to query terms and document terms by unsupervised way using co-occurrence information constructed automatically. Our sense tagger is crude, but performs consistent disambiguation by considering only the single most informative word as evidence to disambiguate the target word. We also allow multiple-sense assignment to alleviate the problem caused by incorrect disambiguation.Experimental results on a large-scale TREC collection show that our approach to improve retrieval effectiveness is successful, while most of the previous work failed to improve performances even on small text collection. Our method also shows promising results when is combined with pseudo relevance feedback and state-of-the-art retrieval function such as BM25.

Geographic Information Retrieval (GIR) is a specialized Information Retrieval (IR) branch that deals with information related to geographical locations. Traditional IR engines are perfectly able to retrieve the majority of the relevant documents for most geographical queries, but they have severe difficulties generating a pertinent ranking of the retrieved results, which leads to poor performance. A key reason for this ranking problem has been a lack of information. Therefore, previous GIR research has tried to fill this gap using robust geographical resources (i.e. a geographical ontology), while other research with the same aim has used relevant feedback techniques instead. This paper explores the use of Bag of Concepts (BoC; a representation where documents are considered as the union of the meanings of its terms) and Holographic Reduced Representation (HRR; a novel representation for textual structure) as re-ranking mechanisms for GIR. Our results reveal an improvement in mean average precision (MAP) when compared to the traditional vector space model, even if Pseudo Relevance Feedback is employed.

Although transportation practitioners nowadays have an unprecedented level of access to massive information, there still exist substantial gaps in their ability to efficiently and reliably find the right information, at the right time, and for the task/decision at hand. To address this gap, this paper proposes a context-aware information retrieval (IR) approach, which can capture and exploit the conceptualization of user needs, decision context, and content meanings to support the retrieval of information that is more relevant to decision making. The proposed IR approach includes three primary components: semantic annotation (SA), semantic query processing (SQP), and semantic document ranking (SDR). This paper focuses on SA for IR for supporting the Transportation Project Environmental Review (TPER) decision-making process. The paper proposes an epistemology-based SA algorithm for automatically annotating webpages in the TPER domain with contextual concepts from an epistemological model. The TPER epistemology is a semantic model for representing and reasoning about information and information retrieval in the TPER domain. In developing the proposed algorithm, a number of syntactic-based and semantic-based annotation methods/algorithms were developed and tested. For the syntactic-based algorithms, the effect of syntactic expansion and filtering was investigated. For the semantic-based algorithms, different semantic similarity calculation methods were evaluated. All the algorithms were tested on a testing data set of 1,328 webpages, which were collected from the FHWA Environmental Review Toolkit Website, and evaluated in terms of Mean Average Precision (MAP) and average precision. The final, proposed SA algorithm achieved 84.07% MAP and 90.67% average precision at top 50 documents, on the testing data.

Relevance Feedback (RF) is an important technique to improve information retrieval and has emerged as one of the hottest topics for both the industry and academic researchers. The performance of RF depends on feedback information. As the volume of feedback information gradually increases, Explicit Relevance Feedback (ERF) is attractive. In this paper, we focus on the ERF in which Feedback information is given. With regards to the lack of information in ERF, we apply Pseudo Relevance Feedback (PRF) to enhance retrieval effectiveness. However, the instability of PRF can result in a negative impact on retrieval performance. We use feedback information to define features and propose a classification model to predict which query can benefit from PRF. Then, we form relevance feedback fusion by the prediction of PRF performance. This method is designed to exploit the strengths of PRF and ERF while avoiding some weaknesses of these approaches. Experiment results show that our approach is feasible and effective.

Latent Semantic Indexing (LSI) and Relevance Feedback (RF) have been shown to be extremely useful in information retrieval respectively. But at the context of Web image retrieval, LSI is limited for the Single Value Decomposition (SVD) computation cost to large dataset while RF is confused with the reluctance of interaction for most Web users. In this paper, a Pseudo Relevance Feedback approach based on Local Latent Semantic Indexing (PRF-LLSI) is proposed, which integrating the LSI and RF, and making use of the benefit of them while solving the limitation of them. The Local LSI (LLSI) method performs a low-dimensional SVD on the local region of initial retrieved results. Both keywords and image contents of the Web images are computed by LLSI to re-rank the initial retrieval results automatically. The PRF-LLSI contribute to the following: 1) Local LSI resolves the heavy computation cost of LSI; 2) Pseudo Relevance Feedback doesn’t need the user’s interaction; 3) LLSI combine the textual and visual features, which improves the precision of the system. The experiments are done in our VAST (VisuAl & SemanTic image search) system, and the results show the effectiveness of the proposed method.