Adversarial examples, generated by applying small perturbations to input features, are widely used to fool classifiers and measure their robustness to noisy inputs. However, little work has been done to evaluate the robustness of ranking models through adversarial examples. In this work, we present a systematic approach of leveraging adversarial examples to measure the robustness of popular ranking models. We explore a simple method to generate adversarial examples that forces a ranker to incorrectly rank the documents. Using this approach, we analyze the robustness of various ranking models and the quality of perturbations generated by the adversarial attacker across two datasets. Our findings suggest that with very few token changes (1-3), the attacker can yield semantically similar perturbed documents that can fool different rankers into changing a document's score, lowering its rank by several positions.
This survey paper discusses different forms of malicious techniques that can affect how an information retrieval model retrieves documents for a query and their remedies.
We propose a document retrieval method for question answering that represents documents and questions as weighted centroids of word embeddings and reranks the retrieved documents with a relaxation of Word Mover's Distance. Using biomedical questions and documents from BIOASQ, we show that our method is competitive with PUBMED. With a top-k approximation, our method is fast, and easily portable to other domains and languages.
In this paper, we explore the usage of Word Embedding semantic resources for Information Retrieval (IR) task. This embedding, produced by a shallow neural network, have been shown to catch semantic similarities between words (Mikolov et al., 2013). Hence, our goal is to enhance IR Language Models by addressing the term mismatch problem. To do so, we applied the model presented in the paper Integrating and Evaluating Neural Word Embedding in Information Retrieval by Zuccon et al. (2015) that proposes to estimate the translation probability of a Translation Language Model using the cosine simila…
It is known that humans can easily read words where the letters have been jumbled in a certain way. This paper examines this problem by associating a distance measure with the jumbling process. Modifications to text were generated according to the Damerau-Levenshtein distance and it was checked if the users are able to read it. Graphical representations of the results are provided.
Word embeddings are vital descriptors of words in unigram representations of documents for many tasks in natural language processing and information retrieval. The representation of queries has been one of the most critical challenges in this area because it consists of a few terms and has little descriptive capacity. Strategies such as average word embeddings can enrich the queries' descriptive capacity since they favor the identification of related terms from the continuous vector representations that characterize these approaches. We propose a data-driven strategy to combine word embeddings…
We introduce a generalised multivariate Polya process for document language modelling. The framework outlined here generalises a number of statistical language models used in information retrieval for modelling document generation. In particular, we show that the choice of replacement matrix M ultimately defines the type of random process and therefore defines a particular type of document language model. We show that a particular variant of the general model is useful for modelling term-specific burstiness. Furthermore, via experimentation we show that this variant significantly improves retr…
Recently pre-trained language representation models such as BERT have shown great success when fine-tuned on downstream tasks including information retrieval (IR). However, pre-training objectives tailored for ad-hoc retrieval have not been well explored. In this paper, we propose Pre-training with Representative wOrds Prediction (PROP) for ad-hoc retrieval. PROP is inspired by the classical statistical language model for IR, specifically the query likelihood model, which assumes that the query is generated as the piece of text representative of the "ideal" document. Based on this idea, we con…
The continuous increasing in the amount of the published and stored information requires a special Information Retrieval (IR) frameworks to search and get information accurately and speedily. Currently, keywords-based techniques are commonly used in information retrieval. However, a major drawback of the keywords approach is its inability of handling the polysemy and synonymy phenomenon of the natural language. For instance, the meanings of words and understanding of concepts differ in different communities. Same word use for different concepts (polysemy) or use different words for the same co…
Pre-training and fine-tuning have achieved remarkable success in many downstream natural language processing (NLP) tasks. Recently, pre-training methods tailored for information retrieval (IR) have also been explored, and the latest success is the PROP method which has reached new SOTA on a variety of ad-hoc retrieval benchmarks. The basic idea of PROP is to construct the \textit{representative words prediction} (ROP) task for pre-training inspired by the query likelihood model. Despite its exciting performance, the effectiveness of PROP might be bounded by the classical unigram language model…
Université de Grenoble（格勒诺布尔大学）；CNRS（法国国家科学研究中心）；Université de Saint-Étienne（圣艾蒂安大学）
This paper presents preliminary works on using Word Embedding (word2vec) for query expansion in the context of Personalized Information Retrieval. Traditionally, word embeddings are learned on a general corpus, like Wikipedia. In this work we try to personalize the word embeddings learning, by achieving the learning on the user's profile. The word embeddings are then in the same context than the user interests. Our proposal is evaluated on the CLEF Social Book Search 2016 collection. The results obtained show that some efforts should be made in the way to apply Word Embedding in the context of…
Cross-modal information retrieval aims to find heterogeneous data of various modalities from a given query of one modality. The main challenge is to map different modalities into a common semantic space, in which distance between concepts in different modalities can be well modeled. For cross-modal information retrieval between images and texts, existing work mostly uses off-the-shelf Convolutional Neural Network (CNN) for image feature extraction. For texts, word-level features such as bag-of-words or word2vec are employed to build deep learning models to represent texts. Besides word-level s…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
This article gives a survey for bag-of-words (BoW) or bag-of-features model in image retrieval system. In recent years, large-scale image retrieval shows significant potential in both industry applications and research problems. As local descriptors like SIFT demonstrate great discriminative power in solving vision problems like object recognition, image classification and annotation, more and more state-of-the-art large scale image retrieval systems are trying to rely on them. A common way to achieve this is first quantizing local descriptors into visual words, and then applying scalable text…
Despite advances in neural machine translation, cross-lingual retrieval tasks in which queries and documents live in different natural language spaces remain challenging. Although neural translation models may provide an intuitive approach to tackle the cross-lingual problem, their resource-consuming training and advanced model structures may complicate the overall retrieval pipeline and reduce users engagement. In this paper, we build our end-to-end Cross-Lingual Arabic Information REtrieval (CLAIRE) system based on the cross-lingual word embedding where searchers are assumed to have a passab…
A major difficulty in applying word vector embeddings in IR is in devising an effective and efficient strategy for obtaining representations of compound units of text, such as whole documents, (in comparison to the atomic words), for the purpose of indexing and scoring documents. Instead of striving for a suitable method for obtaining a single vector representation of a large document of text, we rather aim for developing a similarity metric that makes use of the similarities between the individual embedded word vectors in a document and a query. More specifically, we represent a document and …
Latent semantic representations of words or paragraphs, namely the embeddings, have been widely applied to information retrieval (IR). One of the common approaches of utilizing embeddings for IR is to estimate the document-to-query (D2Q) similarity in their embeddings. As words with similar syntactic usage are usually very close to each other in the embeddings space, although they are not semantically similar, the D2Q similarity approach may suffer from the problem of "multiple degrees of similarity". To this end, this paper proposes a novel approach that estimates a semantic relevance score (…
Word obfuscation or substitution means replacing one word with another word in a sentence to conceal the textual content or communication. Word obfuscation is used in adversarial communication by terrorist or criminals for conveying their messages without getting red-flagged by security and intelligence agencies intercepting or scanning messages (such as emails and telephone conversations). ConceptNet is a freely available semantic network represented as a directed graph consisting of nodes as concepts and edges as assertions of common sense about these concepts. We present a solution approach…
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…
Huawei Research America（华为美国研究院）；School of Artificial Intelligence, Jilin University（吉林大学人工智能学院）
Ad-hoc retrieval models with implicit feedback often have problems, e.g., the imbalanced classes in the data set. Too few clicked documents may hurt generalization ability of the models, whereas too many non-clicked documents may harm effectiveness of the models and efficiency of training. In addition, recent neural network-based models are vulnerable to adversarial examples due to the linear nature in them. To solve the problems at the same time, we propose an adversarial sampling and training framework to learn ad-hoc retrieval models with implicit feedback. Our key idea is (i) to augment cl…
University of Pittsburgh（匹兹堡大学）；University of Waterloo（滑铁卢大学）
Recent research works have shown that image retrieval models are vulnerable to adversarial attacks, where slightly modified test inputs could lead to problematic retrieval results. In this paper, we aim to design a provably robust image retrieval model which keeps the most important evaluation metric Recall@1 invariant to adversarial perturbation. We propose the first 1-nearest neighbor (NN) image retrieval algorithm, RetrievalGuard, which is provably robust against adversarial perturbations within an $\ell_2$ ball of calculable radius. The challenge is to design a provably robust algorithm th…
Code retrieval is a key task aiming to match natural and programming languages. In this work, we propose adversarial learning for code retrieval, that is regularized by question-description relevance. First, we adapt a simple adversarial learning technique to generate difficult code snippets given the input question, which can help the learning of code retrieval that faces bi-modal and data-scarce challenges. Second, we propose to leverage question-description relevance to regularize adversarial learning, such that a generated code snippet should contribute more to the code retrieval training …
HCMC University of Technology（胡志明市理工大学）；John von Neumann Institute（约翰·冯·诺依曼研究所）
Text search based on lexical matching of keywords is not satisfactory due to polysemous and synonymous words. Semantic search that exploits word meanings, in general, improves search performance. In this paper, we survey WordNet-based information retrieval systems, which employ a word sense disambiguation method to process queries and documents. The problem is that in many cases a word has more than one possible direct sense, and picking only one of them may give a wrong sense for the word. Moreover, the previous systems use only word forms to represent word senses and their hypernyms. We prop…
The effectiveness of three stop words lists for Arabic Information Retrieval---General Stoplist, Corpus-Based Stoplist, Combined Stoplist ---were investigated in this study. Three popular weighting schemes were examined: the inverse document frequency weight, probabilistic weighting, and statistical language modelling. The Idea is to combine the statistical approaches with linguistic approaches to reach an optimal performance, and compare their effect on retrieval. The LDC (Linguistic Data Consortium) Arabic Newswire data set was used with the Lemur Toolkit. The Best Match weighting scheme use…
University of Arkansas（阿肯色大学）；Google LLC.（谷歌有限责任公司）
Deep language models learning a hierarchical representation proved to be a powerful tool for natural language processing, text mining and information retrieval. However, representations that perform well for retrieval must capture semantic meaning at different levels of abstraction or context-scopes. In this paper, we propose a new method to generate multi-resolution word embeddings that represent documents at multiple resolutions in terms of context-scopes. In order to investigate its performance,we use the Stanford Question Answering Dataset (SQuAD) and the Question Answering by Search And R…
In the context of arabic Information Retrieval Systems (IRS) guided by arabic ontology and to enable those systems to better respond to user requirements, this paper aims to representing documents and queries by the best concepts extracted from Arabic Wordnet. Identified concepts belonging to Arabic WordNet synsets are extracted from documents and queries, and those having a single sense are expanded. The expanded query is then used by the IRS to retrieve the relevant documents searched. Our experiments are based primarily on a medium size corpus of arabic text. The results obtained shown us t…
Beijing University of Posts and Telecommunications（北京邮电大学）；Didi Research Institute, Didi Chuxing（滴滴出行滴滴研究院）
In the field of car evaluation, more and more netizens choose to express their opinions on the Internet platform, and these comments will affect the decision-making of buyers and the trend of car word-of-mouth. As an important branch of natural language processing (NLP), sentiment analysis provides an effective research method for analyzing the sentiment types of massive car review texts. However, due to the lexical professionalism and large text noise of review texts in the automotive field, when a general sentiment analysis model is applied to car reviews, the accuracy of the model will be p…
Tables contain valuable knowledge in a structured form. We employ neural language modeling approaches to embed tabular data into vector spaces. Specifically, we consider different table elements, such caption, column headings, and cells, for training word and entity embeddings. These embeddings are then utilized in three particular table-related tasks, row population, column population, and table retrieval, by incorporating them into existing retrieval models as additional semantic similarity signals. Evaluation results show that table embeddings can significantly improve upon the performance …
Research Studio Data Science, RSA FG（RSA FG数据科学研究工作室）
We replicate recent experiments attempting to demonstrate an attractive hypothesis about the use of the Fisher kernel framework and mixture models for aggregating word embeddings towards document representations and the use of these representations in document classification, clustering, and retrieval. Specifically, the hypothesis was that the use of a mixture model of von Mises-Fisher (VMF) distributions instead of Gaussian distributions would be beneficial because of the focus on cosine distances of both VMF and the vector space model traditionally used in information retrieval. Previous exp…
National Institute of Technology Karnataka（卡纳塔克邦国家理工学院）
Medical Image Retrieval is a challenging field in Visual information retrieval, due to the multi-dimensional and multi-modal context of the underlying content. Traditional models often fail to take the intrinsic characteristics of data into consideration, and have thus achieved limited accuracy when applied to medical images. The Bag of Visual Words (BoVW) is a technique that can be used to effectively represent intrinsic image features in vector space, so that applications like image classification and similar-image search can be optimized. In this paper, we present a MedIR approach based on …
Generative adversarial nets (GANs) have been widely studied during the recent development of deep learning and unsupervised learning. With an adversarial training mechanism, GAN manages to train a generative model to fit the underlying unknown real data distribution under the guidance of the discriminative model estimating whether a data instance is real or generated. Such a framework is originally proposed for fitting continuous data distribution such as images, thus it is not straightforward to be directly applied to information retrieval scenarios where the data is mostly discrete, such as …
Princeton University（普林斯顿大学）；Indian Institute of Technology, Madras（马德拉斯印度理工学院）
Recent advances in Generative Adversarial Networks (GANs) have resulted in its widespread applications to multiple domains. A recent model, IRGAN, applies this framework to Information Retrieval (IR) and has gained significant attention over the last few years. In this focused work, we critically analyze multiple components of IRGAN, while providing experimental and theoretical evidence of some of its shortcomings. Specifically, we identify issues with the constant baseline term in the policy gradients optimization and show that the generator harms IRGAN's performance. Motivated by our finding…
An adversarial query is an image that has been modified to disrupt content-based image retrieval (CBIR) while appearing nearly untouched to the human eye. This paper presents an analysis of adversarial queries for CBIR based on neural, local, and global features. We introduce an innovative neural image perturbation approach, called Perturbations for Image Retrieval Error (PIRE), that is capable of blocking neural-feature-based CBIR. PIRE differs significantly from existing approaches that create images adversarial with respect to CNN classifiers because it is unsupervised, i.e., it needs no la…
Neural retrieval models have acquired significant effectiveness gains over the last few years compared to term-based methods. Nevertheless, those models may be brittle when faced to typos, distribution shifts or vulnerable to malicious attacks. For instance, several recent papers demonstrated that such variations severely impacted models performances, and then tried to train more resilient models. Usual approaches include synonyms replacements or typos injections -- as data-augmentation -- and the use of more robust tokenizers (characterBERT, BPE-dropout). To further complement the literature,…
In this paper, we propose a new approach to learn multimodal multilingual embeddings for matching images and their relevant captions in two languages. We combine two existing objective functions to make images and captions close in a joint embedding space while adapting the alignment of word embeddings between existing languages in our model. We show that our approach enables better generalization, achieving state-of-the-art performance in text-to-image and image-to-text retrieval task, and caption-caption similarity task. Two multimodal multilingual datasets are used for evaluation: Multi30k …
Generating qualitative responses has always been a challenge for human-computer dialogue systems. Existing dialogue systems generally derive from either retrieval-based or generative-based approaches, both of which have their own pros and cons. Despite the natural idea of an ensemble model of the two, existing ensemble methods only focused on leveraging one approach to enhance another, we argue however that they can be further mutually enhanced with a proper training strategy. In this paper, we propose ensembleGAN, an adversarial learning framework for enhancing a retrieval-generation ensemble…
Dense retrieval (DR) methods conduct text retrieval by first encoding texts in the embedding space and then matching them by nearest neighbor search. This requires strong locality properties from the representation space, i.e, the close allocations of each small group of relevant texts, which are hard to generalize to domains without sufficient training data. In this paper, we aim to improve the generalization ability of DR models from source training domains with rich supervision signals to target domains without any relevant labels, in the zero-shot setting. To achieve that, we propose Momen…
Continuous space word embeddings have received a great deal of attention in the natural language processing and machine learning communities for their ability to model term similarity and other relationships. We study the use of term relatedness in the context of query expansion for ad hoc information retrieval. We demonstrate that word embeddings such as word2vec and GloVe, when trained globally, underperform corpus and query specific embeddings for retrieval tasks. These results suggest that other tasks benefiting from global embeddings may also benefit from local embeddings.
IR models using a pretrained language model significantly outperform lexical approaches like BM25. In particular, SPLADE, which encodes texts to sparse vectors, is an effective model for practical use because it shows robustness to out-of-domain datasets. However, SPLADE still struggles with exact matching of low-frequency words in training data. In addition, domain shifts in vocabulary and word frequencies deteriorate the IR performance of SPLADE. Because supervision data are scarce in the target domain, addressing the domain shifts without supervision data is necessary. This paper proposes a…
Most approaches for similar text retrieval and ranking with long natural language queries rely at some level on queries and responses having words in common with each other. Recent applications of transformer-based neural language models to text retrieval and ranking problems have been very promising, but still involve a two-step process in which result candidates are first obtained through bag-of-words-based approaches, and then reranked by a neural transformer. In this paper, we introduce novel approaches for effectively applying neural transformer models to similar text retrieval and rankin…
Cross-modal retrieval aims to retrieve relevant data across different modalities (e.g., texts vs. images). The common strategy is to apply element-wise constraints between manually labeled pair-wise items to guide the generators to learn the semantic relationships between the modalities, so that the similar items can be projected close to each other in the common representation subspace. However, such constraints often fail to preserve the semantic structure between unpaired but semantically similar items (e.g. the unpaired items with the same class label are more similar than items with diffe…
Document retrieval enables users to find their required documents accurately and quickly. To satisfy the requirement of retrieval efficiency, prevalent deep neural methods adopt a representation-based matching paradigm, which saves online matching time by pre-storing document representations offline. However, the above paradigm consumes vast local storage space, especially when storing the document as word-grained representations. To tackle this, we present TGTR, a Topic-Grained Text Representation-based Model for document retrieval. Following the representation-based matching paradigm, TGTR s…
Computer Vision Center（计算机视觉中心）；Universitat Autònoma de Barcelona（巴塞罗那自治大学）
In this paper, we explore and evaluate the use of ranking-based objective functions for learning simultaneously a word string and a word image encoder. We consider retrieval frameworks in which the user expects a retrieval list ranked according to a defined relevance score. In the context of a word spotting problem, the relevance score has been set according to the string edit distance from the query string. We experimentally demonstrate the competitive performance of the proposed model on query-by-string word spotting for both, handwritten and real scene word images. We also provide the resul…
Nowadays on E-commerce platforms, products are presented to the customers with multiple modalities. These multiple modalities are significant for a retrieval system while providing attracted products for customers. Therefore, how to take into account those multiple modalities simultaneously to boost the retrieval performance is crucial. This problem is a huge challenge to us due to the following reasons: (1) the way of extracting patch features with the pre-trained image model (e.g., CNN-based model) has much inductive bias. It is difficult to capture the efficient information from the product…
Neural Information Retrieval models hold the promise to replace lexical matching models, e.g. BM25, in modern search engines. While their capabilities have fully shone on in-domain datasets like MS MARCO, they have recently been challenged on out-of-domain zero-shot settings (BEIR benchmark), questioning their actual generalization capabilities compared to bag-of-words approaches. Particularly, we wonder if these shortcomings could (partly) be the consequence of the inability of neural IR models to perform lexical matching off-the-shelf. In this work, we propose a measure of discrepancy betwee…
GESIS - Leibniz Institute for the Social Sciences（莱布尼茨社会科学研究所（GESIS））；Cologne（科隆）
Concepts are used to solve the term-mismatch problem. However, we need an effective similarity measure between concepts. Word embedding presents a promising solution. We present in this study three approaches to build concepts vectors based on words vectors. We use a vector-based measure to estimate inter-concepts similarity. Our experiments show promising results. Furthermore, words and concepts become comparable. This could be used to improve conceptual indexing process.
