Quantum Information Retrieval

Recent developments in Vortex Field Theory (VFT) propose that black hole radiation is coherent, information-rich, and generated by vortex instabilities in a structured quantum vacuum, rather than purely thermal particle-antiparticle separation. This framework suggests a potential resolution to the classical black hole information paradox by allowing radiation to carry imprints of infalling matter. Here, I argue that even if VFT is correct in principle, a secondary information paradox emerges: the practical recoverability of this information may be fundamentally limited. Due to gravitational reabsorption and exponential dilution of earlier signals, much of the encoded information may remain observationally inaccessible, creating a pragmatic barrier to full information recovery.

Techniques for data-mining, latent semantic analysis, contextual search of databases, etc. have long ago been developed by computer scientists working on information retrieval (IR). Experimental scientists, from all disciplines, having to analyse large collections of raw experimental data (astronomical, physical, biological, etc.) have developed powerful methods for their statistical analysis and for clustering, categorising, and classifying objects. Finally, physicists have developed a theory of quantum measurement, unifying the logical, algebraic, and probabilistic aspects of queries into a single formalism. The purpose of this paper is twofold: first to show that when formulated at an abstract level, problems from IR, from statistical data analysis, and from physical measurement theories are very similar and hence can profitably be cross-fertilised, and, secondly, to propose a novel method of fuzzy hierarchical clustering, termed semantic distillation-strongly inspired from the theory of quantum measurement-, we developed to analyse raw data coming from various types of experiments on DNA arrays. We illustrate the method by analysing DNA arrays experiments and clustering the genes of the array according to their specificity.

This paper proposes an investigation about a re-ranking strategy presented at SIGIR 2010. In that work we describe a re-ranking strategy in which the output of a semantic based IR system is used to re-weigh documents by exploiting inter-document similarities computed on a vector space. The space is built using the Random Indexing technique. The effectiveness of the strategy has been evaluated in the context of the CLEF Ad-Hoc Robust-WSD Task, while in this paper we propose new experiments in the TREC Ad-Hoc Robust Track 2004.

Distributed representations of words have shown to be useful to improve the effectiveness of IR systems in many sub-tasks like query expansion, retrieval and ranking. Algorithms like word2vec, GloVe and others are also key factors in many improvements in different NLP tasks. One common issue with such embedding models is that words like happy and sad appear in similar contexts and hence are wrongly clustered close in the embedding space. In this paper we leverage Aff2Vec, a set of word embeddings models which include affect information, in order to better capture the affect aspect in news text to achieve better results in information retrieval tasks, also such embeddings are less hit by the synonym/antonym issue. We evaluate their effectiveness on two IR related tasks (query expansion and ranking) over the New York Times dataset (TREC-core '17) comparing them against other word embeddings based models and classic ranking models.

Summary. Techniques for data-mining, latent semantic analysis, contextual search of databases, etc. have long ago been developed by computer scientists working on information retrieval (IR). Experimental scientists, from all disciplines, havi ng to analyse large collections of raw experimental data (astronomical, physical, biological, e tc.) have developed powerful methods for their statistical analysis and for clustering, categor ising, and classifying

A challenging task for word embeddings is to capture the emergent meaning or polarity of a combination of individual words. For example, existing approaches in word embeddings will assign high probabilities to the words ”Penguin” and ”Fly” if they frequently co-occur, but it fails to capture the fact that they occur in an opposite sense Penguins do not fly. We hypothesize that humans do not associate a single polarity or sentiment to each word. The word contributes to the overall polarity of a combination of words depending upon which other words it is combined with. This is analogous to the behavior of microscopic particles which exist in all possible states at the same time and interfere with each other to give rise to new states depending upon their relative phases. We make use of the Hilbert Space representation of such particles in Quantum Mechanics where we subscribe a relative phase to each word, which is a complex number, and investigate two such quantum inspired models to d...

A challenging task for word embeddings is to capture the emergent meaning or polarity of a combination of individual words. For example, existing approaches in word embeddings will assign high probabilities to the words "Penguin" and "Fly" if they frequently co-occur, but it fails to capture the fact that they occur in an opposite sense-Penguins do not fly. We hypothesize that humans do not associate a single polarity or sentiment to each word. The word contributes to the overall polarity of a combination of words depending upon which other words it is combined with. This is analogous to the behavior of microscopic particles which exist in all possible states at the same time and interfere with each other to give rise to new states depending upon their relative phases. We make use of the Hilbert Space representation of such particles in Quantum Mechanics where we subscribe a relative phase to each word, which is a complex number, and investigate two such quantum inspired models to derive the meaning of a combination of words. The proposed models 1 achieve better performances than state-ofthe-art non-quantum models on the binary sentence classification task.

Neural word embedding approaches, due to their ability to capture semantic meanings of vocabulary terms, have recently gained attention of the information retrieval (IR) community and have shown promising results in improving ad hoc retrieval performance. It has been observed that these approaches are sensitive to various choices made during the learning of word embeddings and their usage, often leading to poor reproducibility. We study the effect of varying following two parameters, viz., i) the term normalization and ii) the choice of training collection, on ad hoc retrieval performance with word2vec and fastText embeddings. We present quantitative estimates of similarity of word vectors obtained under different settings, and use embeddings based query expansion task to understand the effects of these parameters on IR effectiveness.

The availability of different pre-trained semantic models has enabled the quick development of machine learning components for downstream applications. However, even if texts are abundant for low-resource languages, there are very few semantic models publicly available. Most of the publicly available pre-trained models are usually built as a multilingual version of semantic models that will not fit well with the need for low-resource languages. We introduce different semantic models for Amharic, a morphologically complex Ethio-Semitic language. After we investigate the publicly available pre-trained semantic models, we fine-tune two pre-trained models and train seven new different models. The models include Word2Vec embeddings, distributional thesaurus (DT), BERT-like contextual embeddings, and DT embeddings obtained via network embedding algorithms. Moreover, we employ these models for different NLP tasks and study their impact. We find that newly-trained models perform better than...

Word embeddings are an essential component in a wide range of natural language processing applications. However, distributional semantic models are known to struggle when only a small number of context sentences are available. Several methods have been proposed to obtain higher-quality vectors for these words, leveraging both this context information and sometimes the word forms themselves through a hybrid approach. We show that the current tasks do not suffice to evaluate models that use word-form information, as such models can easily leverage word forms in the training data that are related to word forms in the test data. We introduce 3 new tasks, allowing for a more balanced comparison between models. Furthermore, we show that hyperparameters that have largely been ignored in previous work can consistently improve the performance of both baseline and advanced models, achieving a new state of the art on 4 out of 6 tasks.

Distributed representation of words, or word embeddings, have motivated methods for calculating semantic representations of word sequences such as phrases, sentences and paragraphs. Most of the existing methods to do so either use algorithms to learn such representations, or improve on calculating weighted averages of the word vectors. In this work, we experiment with spectral methods of signal representation and summarization as mechanisms for constructing such word-sequence embeddings in an unsupervised fashion. In particular, we explore an algorithm rooted in fluid-dynamics, known as higher-order Dynamic Mode Decomposition, which is designed to capture the eigenfrequencies, and hence the fundamental transition dynamics, of periodic and quasi-periodic systems. It is empirically observed that this approach, which we call EigenSent, can summarize transitions in a sequence of words and generate an embedding that can represent well the sequence itself. To the best of the authors’ knowledge, this is the first application of a spectral decomposition and signal summarization technique on text, to create sentence embeddings. We test the efficacy of this algorithm in creating sentence embeddings on three public datasets, where it performs appreciably well. Moreover it is also shown that, due to the positive combination of their complementary properties, concatenating the embeddings generated
by EigenSent with simple word vector averaging achieves state-of-the-art results.

In this paper, we present an extension, and an evaluation, to existing Quantum like approaches of word embedding for IR tasks that (1) improves complex features detection of word use (e.g., syntax and semantics), (2) enhances how this method extends these aforementioned uses across linguistic contexts (i.e., to model lexical ambiguity)-specifically Question Classification-, and (3) reduces computational resources needed for training and operating Quantum based neural networks, when confronted with existing models. This approach could also be latter applicable to significantly enhance the state-of the-art across Natural Language Processing (NLP) word-level tasks such as entity recognition, part-of-speech tagging, or sentence-level ones such as textual relatedness and entailment, to name a few.

Word embeddings or distributed representations of words are being used in various applications like machine translation, sentiment analysis, topic identification etc. Quality of word embeddings and performance of their applications depends on several factors like training method, corpus size and relevance etc. In this study we compare performance of a dozen of pretrained word embedding models on lyrics sentiment analysis and movie review polarity tasks. According to our results, Twitter Tweets is the best on lyrics sentiment analysis, whereas Google News and Common Crawl are the top performers on movie polarity analysis. Glove trained models slightly outrun those trained with Skipgram. Also, factors like topic relevance and size of corpus significantly impact the quality of the models. When medium or large-sized text sets are available, obtaining word embeddings from same training dataset is usually the best choice.

The formalism of quantum physics is said to provide a sound basis for building a principled information retrieval framework. Such a framework is based on the notion of information need vector spaces, where events, such as document relevance, correspond to subspaces, and user information needs are represented as weighted sets of vectors. In this paper, we look at possible ways to build, using an algebra defined over weighted sets, sophisticated query representations and report on corresponding experiments on TREC.