arXiv subjects

Evangelos Kanoulas

Publications and source records attributed to Evangelos Kanoulas.

At least 91 records · Page 5Linked to original sources

arXiv2020

An Empirical Study of Clarifying Question-Based Systems

Search and recommender systems that take the initiative to ask clarifying questions to better understand users' information needs are receiving increasing attention from the research community. However, to the best of our knowledge, there is no empirical study to quantify whether and to what extent users are willing or able to answer these questions. In this work, we conduct an online experiment by deploying an experimental system, which interacts with users by asking clarifying questions against a product repository. We collect both implicit interaction behavior data and explicit feedback from users showing that: (a) users are willing to answer a good number of clarifying questions (11-21 on average), but not many more than that; (b) most users answer questions until they reach the target product, but also a fraction of them stops due to fatigue or due to receiving irrelevant questions; (c) part of the users' answers (12-17%) are actually opposite to the description of the target product; while (d) most of the users (66-84%) find the question-based system helpful towards completing their tasks. Some of the findings of the study contradict current assumptions on simulated evaluations in the field, while they point towards improvements in the evaluation framework and can inspire future interactive search/recommender system designs.

cs.IR↗

arXiv2020

Towards Question-based Recommender Systems

Conversational and question-based recommender systems have gained increasing attention in recent years, with users enabled to converse with the system and better control recommendations. Nevertheless, research in the field is still limited, compared to traditional recommender systems. In this work, we propose a novel Question-based recommendation method, Qrec, to assist users to find items interactively, by answering automatically constructed and algorithmically chosen questions. Previous conversational recommender systems ask users to express their preferences over items or item facets. Our model, instead, asks users to express their preferences over descriptive item features. The model is first trained offline by a novel matrix factorization algorithm, and then iteratively updates the user and item latent factors online by a closed-form solution based on the user answers. Meanwhile, our model infers the underlying user belief and preferences over items to learn an optimal question-asking strategy by using Generalized Binary Search, so as to ask a sequence of questions to the user. Our experimental results demonstrate that our proposed matrix factorization model outperforms the traditional Probabilistic Matrix Factorization model. Further, our proposed Qrec model can greatly improve the performance of state-of-the-art baselines, and it is also effective in the case of cold-start user and item recommendations.

cs.IR↗

arXiv2020

Knowledge Graph Simple Question Answering for Unseen Domains

Knowledge graph simple question answering (KGSQA), in its standard form, does not take into account that human-curated question answering training data only cover a small subset of the relations that exist in a Knowledge Graph (KG), or even worse, that new domains covering unseen and rather different to existing domains relations are added to the KG. In this work, we study KGSQA in a previously unstudied setting where new, unseen domains are added during test time. In this setting, question-answer pairs of the new domain do not appear during training, thus making the task more challenging. We propose a data-centric domain adaptation framework that consists of a KGSQA system that is applicable to new domains, and a sequence to sequence question generation method that automatically generates question-answer pairs for the new domain. Since the effectiveness of question generation for KGSQA can be restricted by the limited lexical variety of the generated questions, we use distant supervision to extract a set of keywords that express each relation of the unseen domain and incorporate those in the question generation method. Experimental results demonstrate that our framework significantly improves over zero-shot baselines and is robust across domains.

cs.CL↗

arXiv2020

An Analysis of Mixed Initiative and Collaboration in Information-Seeking Dialogues

The ability to engage in mixed-initiative interaction is one of the core requirements for a conversational search system. How to achieve this is poorly understood. We propose a set of unsupervised metrics, termed ConversationShape, that highlights the role each of the conversation participants plays by comparing the distribution of vocabulary and utterance types. Using ConversationShape as a lens, we take a closer look at several conversational search datasets and compare them with other dialogue datasets to better understand the types of dialogue interaction they represent, either driven by the information seeker or the assistant. We discover that deviations from the ConversationShape of a human-human dialogue of the same type is predictive of the quality of a human-machine dialogue.

cs.IR↗

arXiv2020

Query Resolution for Conversational Search with Limited Supervision

In this work we focus on multi-turn passage retrieval as a crucial component of conversational search. One of the key challenges in multi-turn passage retrieval comes from the fact that the current turn query is often underspecified due to zero anaphora, topic change, or topic return. Context from the conversational history can be used to arrive at a better expression of the current turn query, defined as the task of query resolution. In this paper, we model the query resolution task as a binary term classification problem: for each term appearing in the previous turns of the conversation decide whether to add it to the current turn query or not. We propose QuReTeC (Query Resolution by Term Classification), a neural query resolution model based on bidirectional transformers. We propose a distant supervision method to automatically generate training data by using query-passage relevance labels. Such labels are often readily available in a collection either as human annotations or inferred from user interactions. We show that QuReTeC outperforms state-of-the-art models, and furthermore, that our distant supervision method can be used to substantially reduce the amount of human-curated data required to train QuReTeC. We incorporate QuReTeC in a multi-turn, multi-stage passage retrieval architecture and demonstrate its effectiveness on the TREC CAsT dataset.

cs.IR↗

arXiv2019

Learning to Ask: Question-based Sequential Bayesian Product Search

Product search is generally recognized as the first and foremost stage of online shopping and thus significant for users and retailers of e-commerce. Most of the traditional retrieval methods use some similarity functions to match the user's query and the document that describes a product, either directly or in a latent vector space. However, user queries are often too general to capture the minute details of the specific product that a user is looking for. In this paper, we propose a novel interactive method to effectively locate the best matching product. The method is based on the assumption that there is a set of candidate questions for each product to be asked. In this work, we instantiate this candidate set by making the hypothesis that products can be discriminated by the entities that appear in the documents associated with them. We propose a Question-based Sequential Bayesian Product Search method, QSBPS, which directly queries users on the expected presence of entities in the relevant product documents. The method learns the product relevance as well as the reward of the potential questions to be asked to the user by being trained on the search history and purchase behavior of a specific user together with that of other users. The experimental results show that the proposed method can greatly improve the performance of product search compared to the state-of-the-art baselines.

cs.IR↗

arXiv2019

Global Aggregations of Local Explanations for Black Box models

The decision-making process of many state-of-the-art machine learning models is inherently inscrutable to the extent that it is impossible for a human to interpret the model directly: they are black box models. This has led to a call for research on explaining black box models, for which there are two main approaches. Global explanations that aim to explain a model's decision making process in general, and local explanations that aim to explain a single prediction. Since it remains challenging to establish fidelity to black box models in globally interpretable approximations, much attention is put on local explanations. However, whether local explanations are able to reliably represent the black box model and provide useful insights remains an open question. We present Global Aggregations of Local Explanations (GALE) with the objective to provide insights in a model's global decision making process. Overall, our results reveal that the choice of aggregation matters. We find that the global importance introduced by Local Interpretable Model-agnostic Explanations (LIME) does not reliably represent the model's global behavior. Our proposed aggregations are better able to represent how features affect the model's predictions, and to provide global insights by identifying distinguishing features.

cs.IR↗

arXiv2019

Query Generation for Patent Retrieval with Keyword Extraction based on Syntactic Features

This paper describes a new method to extract relevant keywords from patent claims, as part of the task of retrieving other patents with similar claims (search for prior art). The method combines a qualitative analysis of the writing style of the claims with NLP methods to parse text, in order to represent a legal text as a specialization arborescence of terms. In this setting, the set of extracted keywords are yielding better search results than keywords extracted with traditional methods such as tf-idf. The performance is measured on the search results of a query consisting of the extracted keywords.

cs.IR↗

arXiv2018

Improved and Robust Controversy Detection in General Web Pages Using Semantic Approaches under Large Scale Conditions

Detecting controversy in general web pages is a daunting task, but increasingly essential to efficiently moderate discussions and effectively filter problematic content. Unfortunately, controversies occur across many topics and domains, with great changes over time. This paper investigates neural classifiers as a more robust methodology for controversy detection in general web pages. Current models have often cast controversy detection on general web pages as Wikipedia linking, or exact lexical matching tasks. The diverse and changing nature of controversies suggest that semantic approaches are better able to detect controversy. We train neural networks that can capture semantic information from texts using weak signal data. By leveraging the semantic properties of word embeddings we robustly improve on existing controversy detection methods. To evaluate model stability over time and to unseen topics, we asses model performance under varying training conditions to test cross-temporal, cross-topic, cross-domain performance and annotator congruence. In doing so, we demonstrate that weak-signal based neural approaches are closer to human estimates of controversy and are more robust to the inherent variability of controversies.

cs.IR↗

arXiv2018

Technology Assisted Reviews: Finding the Last Few Relevant Documents by Asking Yes/No Questions to Reviewers

The goal of a technology-assisted review is to achieve high recall with low human effort. Continuous active learning algorithms have demonstrated good performance in locating the majority of relevant documents in a collection, however their performance is reaching a plateau when 80\%-90\% of them has been found. Finding the last few relevant documents typically requires exhaustively reviewing the collection. In this paper, we propose a novel method to identify these last few, but significant, documents efficiently. Our method makes the hypothesis that entities carry vital information in documents, and that reviewers can answer questions about the presence or absence of an entity in the missing relevance documents. Based on this we devise a sequential Bayesian search method that selects the optimal sequence of questions to ask. The experimental results show that our proposed method can greatly improve performance requiring less reviewing effort.

cs.IR↗

arXiv2018

Neural Vector Spaces for Unsupervised Information Retrieval

We propose the Neural Vector Space Model (NVSM), a method that learns representations of documents in an unsupervised manner for news article retrieval. In the NVSM paradigm, we learn low-dimensional representations of words and documents from scratch using gradient descent and rank documents according to their similarity with query representations that are composed from word representations. We show that NVSM performs better at document ranking than existing latent semantic vector space methods. The addition of NVSM to a mixture of lexical language models and a state-of-the-art baseline vector space model yields a statistically significant increase in retrieval effectiveness. Consequently, NVSM adds a complementary relevance signal. Next to semantic matching, we find that NVSM performs well in cases where lexical matching is needed. NVSM learns a notion of term specificity directly from the document collection without feature engineering. We also show that NVSM learns regularities related to Luhn significance. Finally, we give advice on how to deploy NVSM in situations where model selection (e.g., cross-validation) is infeasible. We find that an unsupervised ensemble of multiple models trained with different hyperparameter values performs better than a single cross-validated model. Therefore, NVSM can safely be used for ranking documents without supervised relevance judgments.

cs.IR↗

arXiv2018

ILPS at TREC 2017 Common Core Track

The TREC 2017 Common Core Track aimed at gathering a diverse set of participating runs and building a new test collection using advanced pooling methods. In this paper, we describe the participation of the IlpsUvA team at the TREC 2017 Common Core Track. We submitted runs created using two methods to the track: (1) BOIR uses Bayesian optimization to automatically optimize retrieval model hyperparameters. (2) NVSM is a latent vector space model where representations of documents and query terms are learned from scratch in an unsupervised manner. We find that BOIR is able to optimize hyperparameters as to find a system that performs competitively amongst track participants. NVSM provides rankings that are diverse, as it was amongst the top automated unsupervised runs that provided the most unique relevant documents.

cs.IR↗

arXiv2017

Examining Cooperation in Visual Dialog Models

In this work we propose a blackbox intervention method for visual dialog models, with the aim of assessing the contribution of individual linguistic or visual components. Concretely, we conduct structured or randomized interventions that aim to impair an individual component of the model, and observe changes in task performance. We reproduce a state-of-the-art visual dialog model and demonstrate that our methodology yields surprising insights, namely that both dialog and image information have minimal contributions to task performance. The intervention method presented here can be applied as a sanity check for the strength and robustness of each component in visual dialog systems.

cs.CV↗

arXiv2017

Active Sampling for Large-scale Information Retrieval Evaluation

Evaluation is crucial in Information Retrieval. The development of models, tools and methods has significantly benefited from the availability of reusable test collections formed through a standardized and thoroughly tested methodology, known as the Cranfield paradigm. Constructing these collections requires obtaining relevance judgments for a pool of documents, retrieved by systems participating in an evaluation task; thus involves immense human labor. To alleviate this effort different methods for constructing collections have been proposed in the literature, falling under two broad categories: (a) sampling, and (b) active selection of documents. The former devises a smart sampling strategy by choosing only a subset of documents to be assessed and inferring evaluation measure on the basis of the obtained sample; the sampling distribution is being fixed at the beginning of the process. The latter recognizes that systems contributing documents to be judged vary in quality, and actively selects documents from good systems. The quality of systems is measured every time a new document is being judged. In this paper we seek to solve the problem of large-scale retrieval evaluation combining the two approaches. We devise an active sampling method that avoids the bias of the active selection methods towards good systems, and at the same time reduces the variance of the current sampling approaches by placing a distribution over systems, which varies as judgments become available. We validate the proposed method using TREC data and demonstrate the advantages of this new method compared to past approaches.

cs.IR↗

arXiv2017

Structural Regularities in Text-based Entity Vector Spaces

Entity retrieval is the task of finding entities such as people or products in response to a query, based solely on the textual documents they are associated with. Recent semantic entity retrieval algorithms represent queries and experts in finite-dimensional vector spaces, where both are constructed from text sequences. We investigate entity vector spaces and the degree to which they capture structural regularities. Such vector spaces are constructed in an unsupervised manner without explicit information about structural aspects. For concreteness, we address these questions for a specific type of entity: experts in the context of expert finding. We discover how clusterings of experts correspond to committees in organizations, the ability of expert representations to encode the co-author graph, and the degree to which they encode academic rank. We compare latent, continuous representations created using methods based on distributional semantics (LSI), topic models (LDA) and neural networks (word2vec, doc2vec, SERT). Vector spaces created using neural methods, such as doc2vec and SERT, systematically perform better at clustering than LSI, LDA and word2vec. When it comes to encoding entity relations, SERT performs best.

cs.IR↗

arXiv2017

Semantic Entity Retrieval Toolkit

Unsupervised learning of low-dimensional, semantic representations of words and entities has recently gained attention. In this paper we describe the Semantic Entity Retrieval Toolkit (SERT) that provides implementations of our previously published entity representation models. The toolkit provides a unified interface to different representation learning algorithms, fine-grained parsing configuration and can be used transparently with GPUs. In addition, users can easily modify existing models or implement their own models in the framework. After model training, SERT can be used to rank entities according to a textual query and extract the learned entity/word representation for use in downstream algorithms, such as clustering or recommendation.

cs.CL↗

arXiv2017

Pyndri: a Python Interface to the Indri Search Engine

We introduce pyndri, a Python interface to the Indri search engine. Pyndri allows to access Indri indexes from Python at two levels: (1) dictionary and tokenized document collection, (2) evaluating queries on the index. We hope that with the release of pyndri, we will stimulate reproducible, open and fast-paced IR research.

cs.IR↗

arXiv2016

Learning Latent Vector Spaces for Product Search

We introduce a novel latent vector space model that jointly learns the latent representations of words, e-commerce products and a mapping between the two without the need for explicit annotations. The power of the model lies in its ability to directly model the discriminative relation between products and a particular word. We compare our method to existing latent vector space models (LSI, LDA and word2vec) and evaluate it as a feature in a learning to rank setting. Our latent vector space model achieves its enhanced performance as it learns better product representations. Furthermore, the mapping from words to products and the representations of words benefit directly from the errors propagated back from the product representations during parameter estimation. We provide an in-depth analysis of the performance of our model and analyze the structure of the learned representations.

cs.IR↗