This paper provides a unified account of two schools of thinking in information retrieval modelling: the generative retrieval focusing on predicting relevant documents given a query, and the discriminative retrieval focusing on predicting relevancy given a query-document pair. We propose a game theoretical minimax game to iteratively optimise both models. On one hand, the discriminative model, aiming to mine signals from labelled and unlabelled data, provides guidance to train the generative model towards fitting the underlying relevance distribution over documents given the query. On the other hand, the generative model, acting as an attacker to the current discriminative model, generates difficult examples for the discriminative model in an adversarial way by minimising its discrimination objective. With the competition between these two models, we show that the unified framework takes advantage of both schools of thinking: (i) the generative model learns to fit the relevance distribution over documents via the signals from the discriminative model, and (ii) the discriminative model is able to exploit the unlabelled data selected by the generative model to achieve a better estimation for document ranking. Our experimental results have demonstrated significant performance gains as much as 23.96% on Precision@5 and 15.50% on MAP over strong baselines in a variety of applications including web search, item recommendation, and question answering.

/pdf/irgan-a-minimax-game-for-unifying-generative-and-1351hzqk42.pdf

IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models

/pdf/irgan-a-minimax-game-for-unifying-generative-and-3tsyurys9c.pdf

Social media is a powerful source of communication among people to share their sentiments in the form of opinions and views about any topic or article, which results in an enormous amount of unstructured information. Business organizations need to process and study these sentiments to investigate data and to gain business insights. Hence, to analyze these sentiments, various machine learning, and natural language processing-based approaches have been used in the past. However, deep learning-based methods are becoming very popular due to their high performance in recent times. This paper provides a detailed survey of popular deep learning models that are increasingly applied in sentiment analysis. We present a taxonomy of sentiment analysis and discuss the implications of popular deep learning architectures. The key contributions of various researchers are highlighted with the prime focus on deep learning approaches. The crucial sentiment analysis tasks are presented, and multiple languages are identified on which sentiment analysis is done. The survey also summarizes the popular datasets, key features of the datasets, deep learning model applied on them, accuracy obtained from them, and the comparison of various deep learning models. The primary purpose of this survey is to highlight the power of deep learning architectures for solving sentiment analysis problems.

Sentiment analysis using deep learning architectures: a review

The letter and/or sound combinations that make up a human language are limited by the human's ability to pronounce tnese sounds° Therefore, the standard library search, which as a rule looks for all possible combinations of letters to find a word, is wasteful. Certain letters simply cannot be followed by certain other letters and a search for them is senseless. Following this same line of reasoning, letters very frequently occur in the combinations that are germane to the particular language. The growing amount of alphanumeric information presently being stored on magnetic tape presents increasingly difficult problems in both the number of tape reels used and the time necessary to search this mass of information in order to extract pertinent literature. At the present time most of this literature on tape utilizes the standard IBM 6-bit code to express alphanumeric symbols. ~t is entirely feasible to record standard English literature on tape -be it professional abstracts or novels -using only approximately two-thirds of the binary bits utilized to represent the same piece of written material in the conventional code. This can be accomplished by setting up, in a 9-bit code, the 400-odd letter combinations occurring most frequently. A 9-bit representation allows the programmer to set up as many as 512 symbols, thus leaving sufficient leeway to assign symbols to the most frequentlyused words, mathematical symbols, professional expressions, that are expected to be encountered in the literature to be recorded. In addition, these relatively short 9-bit symbols can be assigned to all key words that it may be necessary to look for later, thereby accelerating any future library search.

Information storage and retrieval

I do not recall having met an educated person who claims to know less about contemporary physics than I do. Nevertheless, it has been my contention that as physicians living in the early part of the second half of the twentieth century we have very strong obligations to understand as much as we can of the world we live in. Perhaps if this could be done on a large scale events might be bent somewhat to wise purposes rather than just letting them happen. The introduction of the uncertainty principle, for which Heisenberg received the Nobel Prize, may be of some comfort in its oversimplified form as applied to research in biology. As I understand it, his essential belief is that by the very act of measuring a variable factor is introduced which disqualifies the evidence by virtue of altering the thing measured. Certainly, in clinical investigation and in biology

Physics and Philosophy, the Revolution in Modern Science.

A quantum-inspired multimodal sentiment analysis framework

Quantum theory has been applied in a number of fields outside physics, e.g., cognitive science and information retrieval (IR). Recently, it has been shown that quantum theory can subsume various key IR models into a single mathematical formalism of Hilbert vector spaces. While a series of quantum-inspired IR models has been proposed, limited effort has been devoted to verify the existence of the quantum-like phenomenon in real users’ information retrieval processes, from a real user study perspective. In this paper, we aim to explore and model the quantum interference in users’ relevance judgement about documents, caused by the presentation order of documents. A user study in the context of IR tasks have been carried out. The existence of the quantum interference is tested by the violation of the law of total probability and the validity of the order effect. Our main findings are: (1) there is an apparent judging discrepancy across different users and document presentation orders, and empirical data have violated the law of total probability; (2) most search trials recorded in the user study show the existence of the order effect, and the incompatible decision perspectives in the quantum question (QQ) model are valid in some trials. We further explain the judgement discrepancy in more depth, in terms of four effects (comparison, unfamiliarity, attraction and repulsion) and also analyse the dynamics of document relevance judgement in terms of the evolution of the information need subspace.

Exploration of Quantum Interference in Document Relevance Judgement Discrepancy

The quantum probabilistic framework has recently been applied to Information Retrieval (IR). A representative is the Quantum Language Model (QLM), which is developed for the ad-hoc retrieval with single queries and has achieved significant improvements over traditional language models. In QLM, a density matrix, defined on the quantum probabilistic space, is estimated as a representation of user's search intention with respect to a specific query. However, QLM is unable to capture the dynamics of user's information need in query history. This limitation restricts its further application on the dynamic search tasks, e.g., session search. In this paper, we propose a Session-based Quantum Language Model (SQLM) that deals with multi-query session search task. In SQLM, a transformation model of density matrices is proposed to model the evolution of user's information need in response to the user's interaction with search engine, by incorporating features extracted from both positive feedback (clicked documents) and negative feedback (skipped documents). Extensive experiments conducted on TREC 2013 and 2014 session track data demonstrate the effectiveness of SQLM in comparison with the classic QLM.

/pdf/modeling-multi-query-retrieval-tasks-using-density-matrix-6t27ud9jkn.pdf

Modeling Multi-query Retrieval Tasks Using Density Matrix Transformation

Recent research has shown that the performance of search engines can be improved by enriching a user's personal profile with information about other users with shared interests. In the existing approaches, groups of similar users are often statically determined, e.g., based on the common documents that users clicked. However, these static grouping methods are query-independent and neglect the fact that users in a group may have different interests with respect to different topics. In this paper, we argue that common interest groups should be dynamically constructed in response to the user's input query. We propose a personalisation framework in which a user profile is enriched using information from other users dynamically grouped with respect to an input query. The experimental results on query logs from a major commercial web search engine demonstrate that our framework improves the performance of the web search engine and also achieves better performance than the static grouping method.

/pdf/improving-search-personalisation-with-dynamic-group-49vx5jaa4e.pdf

Improving search personalisation with dynamic group formation

Recently, a Quantum Language Model (QLM) was proposed to model term dependencies upon Quantum Theory (QT) framework and successively applied in Information Retrieval (IR). Nevertheless, QLM's dependency is based on co-occurrences of terms and has not yet taken into account the Quantum Entanglement (QE), which is a key quantum concept and has a significant cognitive implication. In QT, an entangled state can provide a more complete description for the nature of realities, and determine intrinsic correlations of considered objects globally, rather than those co-occurrences on the surface. It is, however, a real challenge to decide and measure QE using the classical statistics of texts in a post-measurement configuration. In order to circumvent this problem, we theoretically prove the connection between QE and statistically Unconditional Pure Dependence (UPD). Since UPD has an implementable deciding algorithm, we can in turn characterize QE by extracting the UPD patterns from texts. This leads to a measurable QE, based on which we further advance the existing QLM framework. We empirically compare our model with related models, and the results demonstrate the effectiveness of our model.

Jingfei Li

Papers

A quantum-inspired multimodal sentiment analysis framework

Exploration of Quantum Interference in Document Relevance Judgement Discrepancy

Modeling Multi-query Retrieval Tasks Using Density Matrix Transformation

Improving search personalisation with dynamic group formation

Modeling quantum entanglements in quantum language models