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.
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.
Recently, Quantum Theory (QT) has been employed to advance the theory of Information Retrieval (IR). Various analogies between QT and IR have been established. Among them, a typical one is applying the idea of photon polarization in IR tasks, e.g., for document ranking and query expansion. In this paper, we aim to further extend this work by constructing a new superposed state of each document in the information need space, based on which we can incorporate the quantum interference idea in query expansion. We then apply the new quantum query expansion model to session search, which is a typical Web search task. Empirical evaluation on the large-scale Clueweb12 dataset has shown that the proposed model is effective in the session search tasks, demonstrating the potential of developing novel and effective IR models based on intuitions and formalisms of QT.
Language Modeling (LM) is a fundamental research topic in a range of areas. Recently, inspired by quantum theory, a novel Quantum Language Model (QLM) has been proposed for Information Retrieval (IR). In this paper, we aim to broaden the theoretical and practical basis of QLM. We develop a Neural Network based Quantum-like Language Model (NNQLM) and apply it to Question Answering. Specifically, based on word embeddings, we design a new density matrix, which represents a sentence (e.g., a question or an answer) and encodes a mixture of semantic subspaces. Such a density matrix, together with a joint representation of the question and the answer, can be integrated into neural network architectures (e.g., 2-dimensional convolutional neural networks). Experiments on the TREC-QA and WIKIQA datasets have verified the effectiveness of our proposed models.
Even the best information retrieval model cannot always identify the most useful answers to a user query. This is in particular the case with web search systems, where it is known that users tend to minimise their effort to access relevant information. It is, however, believed that the interaction between users and a retrieval system, such as a web search engine, can be exploited to provide better answers to users. Interactive Information Retrieval (IR) systems, in which users access information through a series of interactions with the search system, are concerned with building models for IR, where interaction plays a central role. There are many possible interactions between a user and a search system, ranging from query (re)formulation to relevance feedback. However, capturing them within a single framework is difficult and previously proposed approaches have mostly focused on relevance feedback. In this paper, we propose a general framework for interactive IR that is able to capture the full interaction process in a principled way. Our approach relies upon a generalisation of the probability framework of quantum physics, whose strong geometric component can be a key towards a successful interactive IR model.
The probabilistic formalism of quantum physics is said to provide a sound basis for building a principled information retrieval framework. Such a framework can be based on the notion of information need vector spaces where events, such as document relevance or observed user interactions, correspond to subspaces. As in quantum theory, a probability distribution over these subspaces is defined through weighted sets of state vectors (density operators), and used to represent the current view of the retrieval system on the user information need. Tensor spaces can be used to capture different aspects of information needs. Our evaluation shows that the framework can lead to acceptable performance in an ad-hoc retrieval task. Going beyond this, we discuss the potential of the framework for three active challenges in information retrieval, namely, interaction, novelty and diversity.
Language modeling is essential in Natural Language Processing and Information Retrieval related tasks. After the statistical language models, Quantum Language Model (QLM) has been proposed to unify both single words and compound terms in the same probability space without extending term space exponentially. Although QLM achieved good performance in ad hoc retrieval, it still has two major limitations: (1) QLM cannot make use of supervised information, mainly due to the iterative and non-differentiable estimation of the density matrix, which represents both queries and documents in QLM. (2) QLM assumes the exchangeability of words or word dependencies, neglecting the order or position information of words. This article aims to generalize QLM and make it applicable to more complicated matching tasks (e.g., Question Answering) beyond ad hoc retrieval. We propose a complex-valued neural network-based QLM solution called C-NNQLM to employ an end-to-end approach to build and train density matrices in a light-weight and differentiable manner, and it can therefore make use of external well-trained word vectors and supervised labels. Furthermore, C-NNQLM adopts complex-valued word vectors whose phase vectors can directly encode the order (or position) information of words. Note that complex numbers are also essential in the quantum theory. We show that the real-valued NNQLM (R-NNQLM) is a special case of C-NNQLM. The experimental results on the QA task show that both R-NNQLM and C-NNQLM achieve much better performance than the vanilla QLM, and C-NNQLM’s performance is on par with state-of-the-art neural network models. We also evaluate the proposed C-NNQLM on text classification and document retrieval tasks. The results on most datasets show that the C-NNQLM can outperform R-NNQLM, which demonstrates the usefulness of the complex representation for words and sentences in C-NNQLM.
This thesis is fundamentally about using conceptual and mathematical constructs from the area of Quantum Theory in Information Retrieval (IR). The need and motivation for this is two-fold – firstly, it has been increasingly shown in decision sciences that human decision-making does not always conform to the norms of traditional probability and logic framework. The quantum framework offers a generalised probability and logic framework which can model decisions or judgements under dynamic context and ambiguity. Secondly, there is a need in IR for theories and models which improve our understanding of user behaviour. Hence it is worth exploring the combination of the quantum framework and IR, especially focused on the user aspects of IR. The overarching research question is whether there is evidence of user behaviour in IR scenarios which warrants the need for a quantum based approach by way of showing the limitations of the traditional (classical) approach. The methodology involves analysing data to detect quantum-like phenomena of interference, contextuality, incompatibility, etc. from two common data sources in IR–standard datasets like query log data, and through crowdsourced user studies designed similar to some quantum physics or cognitive science experiments. While the evidence of quantum-like phenomena from standard datasets is not convincing, we find that some of the user studies reveal the quantum-like structure of document judgements. One of the key findings which has implication for IR is the dynamic interactions between the different dimensions of relevance. For example, a user’s judgement of reliability of a document depends significantly on whether they found it understandable or not. Thus, the consideration of one relevance dimension or document feature can provide a context for another dimension, contrary to the current IR models which consider these features to be independent of each other and an objective property of the document. The quantum framework has been especially designed to deal with such scenarios where properties of systems or objects do not exist independent of measurement context. The thesis concludes with suggestions about incorporating quantum mathematical constructs into state-of-art IR algorithms.