arXiv subjects

Krisztian Balog

Publications and source records attributed to Krisztian Balog.

At least 55 records · Page 3Linked to original sources

arXiv2023

Towards Filling the Gap in Conversational Search: From Passage Retrieval to Conversational Response Generation

Research on conversational search has so far mostly focused on query rewriting and multi-stage passage retrieval. However, synthesizing the top retrieved passages into a complete, relevant, and concise response is still an open challenge. Having snippet-level annotations of relevant passages would enable both (1) the training of response generation models that are able to ground answers in actual statements and (2) the automatic evaluation of the generated responses in terms of completeness. In this paper, we address the problem of collecting high-quality snippet-level answer annotations for two of the TREC Conversational Assistance track datasets. To ensure quality, we first perform a preliminary annotation study, employing different task designs, crowdsourcing platforms, and workers with different qualifications. Based on the outcomes of this study, we refine our annotation protocol before proceeding with the full-scale data collection. Overall, we gather annotations for 1.8k question-paragraph pairs, each annotated by three independent crowd workers. The process of collecting data at this magnitude also led to multiple insights about the problem that can inform the design of future response-generation methods. This is an extended version of the article published with the same title in the Proceedings of CIKM'23.

cs.IR↗

arXiv2023

Large Language Models are Competitive Near Cold-start Recommenders for Language- and Item-based Preferences

Traditional recommender systems leverage users' item preference history to recommend novel content that users may like. However, modern dialog interfaces that allow users to express language-based preferences offer a fundamentally different modality for preference input. Inspired by recent successes of prompting paradigms for large language models (LLMs), we study their use for making recommendations from both item-based and language-based preferences in comparison to state-of-the-art item-based collaborative filtering (CF) methods. To support this investigation, we collect a new dataset consisting of both item-based and language-based preferences elicited from users along with their ratings on a variety of (biased) recommended items and (unbiased) random items. Among numerous experimental results, we find that LLMs provide competitive recommendation performance for pure language-based preferences (no item preferences) in the near cold-start case in comparison to item-based CF methods, despite having no supervised training for this specific task (zero-shot) or only a few labels (few-shot). This is particularly promising as language-based preference representations are more explainable and scrutable than item-based or vector-based representations.

cs.IR↗

arXiv2023

Beyond Single Items: Exploring User Preferences in Item Sets with the Conversational Playlist Curation Dataset

Users in consumption domains, like music, are often able to more efficiently provide preferences over a set of items (e.g. a playlist or radio) than over single items (e.g. songs). Unfortunately, this is an underexplored area of research, with most existing recommendation systems limited to understanding preferences over single items. Curating an item set exponentiates the search space that recommender systems must consider (all subsets of items!): this motivates conversational approaches-where users explicitly state or refine their preferences and systems elicit preferences in natural language-as an efficient way to understand user needs. We call this task conversational item set curation and present a novel data collection methodology that efficiently collects realistic preferences about item sets in a conversational setting by observing both item-level and set-level feedback. We apply this methodology to music recommendation to build the Conversational Playlist Curation Dataset (CPCD), where we show that it leads raters to express preferences that would not be otherwise expressed. Finally, we propose a wide range of conversational retrieval models as baselines for this task and evaluate them on the dataset.

cs.IR↗

arXiv2023

MG-ShopDial: A Multi-Goal Conversational Dataset for e-Commerce

Conversational systems can be particularly effective in supporting complex information seeking scenarios with evolving information needs. Finding the right products on an e-commerce platform is one such scenario, where a conversational agent would need to be able to provide search capabilities over the item catalog, understand and make recommendations based on the user's preferences, and answer a range of questions related to items and their usage. Yet, existing conversational datasets do not fully support the idea of mixing different conversational goals (i.e., search, recommendation, and question answering) and instead focus on a single goal. To address this, we introduce MG-ShopDial: a dataset of conversations mixing different goals in the domain of e-commerce. Specifically, we make the following contributions. First, we develop a coached human-human data collection protocol where each dialogue participant is given a set of instructions, instead of a specific script or answers to choose from. Second, we implement a data collection tool to facilitate the collection of multi-goal conversations via a web chat interface, using the above protocol. Third, we create the MG-ShopDial collection, which contains 64 high-quality dialogues with a total of 2,196 utterances for e-commerce scenarios of varying complexity. The dataset is additionally annotated with both intents and goals on the utterance level. Finally, we present an analysis of this dataset and identify multi-goal conversational patterns.

cs.IR↗

arXiv2023

Measuring the Impact of Explanation Bias: A Study of Natural Language Justifications for Recommender Systems

Despite the potential impact of explanations on decision making, there is a lack of research on quantifying their effect on users' choices. This paper presents an experimental protocol for measuring the degree to which positively or negatively biased explanations can lead to users choosing suboptimal recommendations. Key elements of this protocol include a preference elicitation stage to allow for personalizing recommendations, manual identification and extraction of item aspects from reviews, and a controlled method for introducing bias through the combination of both positive and negative aspects. We study explanations in two different textual formats: as a list of item aspects and as fluent natural language text. Through a user study with 129 participants, we demonstrate that explanations can significantly affect users' selections and that these findings generalize across explanation formats.

cs.HC↗

arXiv2023

From Baseline to Top Performer: A Reproducibility Study of Approaches at the TREC 2021 Conversational Assistance Track

This paper reports on an effort of reproducing the organizers' baseline as well as the top performing participant submission at the 2021 edition of the TREC Conversational Assistance track. TREC systems are commonly regarded as reference points for effectiveness comparison. Yet, the papers accompanying them have less strict requirements than peer-reviewed publications, which can make reproducibility challenging. Our results indicate that key practical information is indeed missing. While the results can be reproduced within a 19% relative margin with respect to the main evaluation measure, the relative difference between the baseline and the top performing approach shrinks from the reported 18% to 5%. Additionally, we report on a new set of experiments aimed at understanding the impact of various pipeline components. We show that end-to-end system performance can indeed benefit from advanced retrieval techniques in either stage of a two-stage retrieval pipeline. We also measure the impact of the dataset used for fine-tuning the query rewriter and find that employing different query rewriting methods in different stages of the retrieval pipeline might be beneficial. Moreover, these results are shown to generalize across the 2020 and 2021 editions of the track. We conclude our study with a list of lessons learned and practical suggestions.

cs.IR↗

arXiv2023

UserSimCRS: A User Simulation Toolkit for Evaluating Conversational Recommender Systems

We present an extensible user simulation toolkit to facilitate automatic evaluation of conversational recommender systems. It builds on an established agenda-based approach and extends it with several novel elements, including user satisfaction prediction, persona and context modeling, and conditional natural language generation. We showcase the toolkit with a pre-existing movie recommender system and demonstrate its ability to simulate dialogues that mimic real conversations, while requiring only a handful of manually annotated dialogues as training data.

cs.IR↗

arXiv2022

DAGFiNN: A Conversational Conference Assistant

DAGFiNN is a conversational conference assistant that can be made available for a given conference both as a chatbot on the website and as a Furhat robot physically exhibited at the conference venue. Conference participants can interact with the assistant to get advice on various questions, ranging from where to eat in the city or how to get to the airport to which sessions we recommend them to attend based on the information we have about them. The overall objective is to provide a personalized and engaging experience and allow users to ask a broad range of questions that naturally arise before and during the conference.

cs.IR↗

arXiv2022

Would You Ask it that Way? Measuring and Improving Question Naturalness for Knowledge Graph Question Answering

Knowledge graph question answering (KGQA) facilitates information access by leveraging structured data without requiring formal query language expertise from the user. Instead, users can express their information needs by simply asking their questions in natural language (NL). Datasets used to train KGQA models that would provide such a service are expensive to construct, both in terms of expert and crowdsourced labor. Typically, crowdsourced labor is used to improve template-based pseudo-natural questions generated from formal queries. However, the resulting datasets often fall short of representing genuinely natural and fluent language. In the present work, we investigate ways to characterize and remedy these shortcomings. We create the IQN-KGQA test collection by sampling questions from existing KGQA datasets and evaluating them with regards to five different aspects of naturalness. Then, the questions are rewritten to improve their fluency. Finally, the performance of existing KGQA models is compared on the original and rewritten versions of the NL questions. We find that some KGQA systems fare worse when presented with more realistic formulations of NL questions. The IQN-KGQA test collection is a resource to help evaluate KGQA systems in a more realistic setting. The construction of this test collection also sheds light on the challenges of constructing large-scale KGQA datasets with genuinely NL questions.

cs.IR↗

arXiv2022

On Natural Language User Profiles for Transparent and Scrutable Recommendation

Natural interaction with recommendation and personalized search systems has received tremendous attention in recent years. We focus on the challenge of supporting people's understanding and control of these systems and explore a fundamentally new way of thinking about representation of knowledge in recommendation and personalization systems. Specifically, we argue that it may be both desirable and possible for algorithms that use natural language representations of users' preferences to be developed. We make the case that this could provide significantly greater transparency, as well as affordances for practical actionable interrogation of, and control over, recommendations. Moreover, we argue that such an approach, if successfully applied, may enable a major step towards systems that rely less on noisy implicit observations while increasing portability of knowledge of one's interests.

cs.IR↗

arXiv2022

Analyzing and Simulating User Utterance Reformulation in Conversational Recommender Systems

User simulation has been a cost-effective technique for evaluating conversational recommender systems. However, building a human-like simulator is still an open challenge. In this work, we focus on how users reformulate their utterances when a conversational agent fails to understand them. First, we perform a user study, involving five conversational agents across different domains, to identify common reformulation types and their transition relationships. A common pattern that emerges is that persistent users would first try to rephrase, then simplify, before giving up. Next, to incorporate the observed reformulation behavior in a user simulator, we introduce the task of reformulation sequence generation: to generate a sequence of reformulated utterances with a given intent (rephrase or simplify). We develop methods by extending transformer models guided by the reformulation type and perform further filtering based on estimated reading difficulty. We demonstrate the effectiveness of our approach using both automatic and human evaluation.

cs.IR↗

arXiv2022

Diverse Reviewer Suggestion for Extending Conference Program Committees

Automated reviewer recommendation for scientific conferences currently relies on the assumption that the program committee has the necessary expertise to handle all submissions. However, topical discrepancies between received submissions and reviewer candidates might lead to unreliable reviews or overburdening of reviewers, and may result in the rejection of high-quality papers. In this work, we present DiveRS, an explainable flow-based reviewer assignment approach, which automatically generates reviewer assignments as well as suggestions for extending the current program committee with new reviewer candidates. Our algorithm focuses on the diversity of the set of reviewers assigned to papers, which has been mostly disregarded in prior work. Specifically, we consider diversity in terms of professional background, location and seniority. Using two real world conference datasets for evaluation, we show that DiveRS improves diversity compared to both real assignments and a state-of-the-art flow-based reviewer assignment approach. Further, based on human assessments by former PC chairs, we find that DiveRS can effectively trade off some of the topical suitability in order to construct more diverse reviewer assignments.

cs.DL↗

arXiv2021

Semantic Answer Type Prediction using BERT: IAI at the ISWC SMART Task 2020

This paper summarizes our participation in the SMART Task of the ISWC 2020 Challenge. A particular question we are interested in answering is how well neural methods, and specifically transformer models, such as BERT, perform on the answer type prediction task compared to traditional approaches. Our main finding is that coarse-grained answer types can be identified effectively with standard text classification methods, with over 95% accuracy, and BERT can bring only marginal improvements. For fine-grained type detection, on the other hand, BERT clearly outperforms previous retrieval-based approaches.

cs.CL↗

arXiv2021

On Interpretation and Measurement of Soft Attributes for Recommendation

We address how to robustly interpret natural language refinements (or critiques) in recommender systems. In particular, in human-human recommendation settings people frequently use soft attributes to express preferences about items, including concepts like the originality of a movie plot, the noisiness of a venue, or the complexity of a recipe. While binary tagging is extensively studied in the context of recommender systems, soft attributes often involve subjective and contextual aspects, which cannot be captured reliably in this way, nor be represented as objective binary truth in a knowledge base. This also adds important considerations when measuring soft attribute ranking. We propose a more natural representation as personalized relative statements, rather than as absolute item properties. We present novel data collection techniques and evaluation approaches, and a new public dataset. We also propose a set of scoring approaches, from unsupervised to weakly supervised to fully supervised, as a step towards interpreting and acting upon soft attribute based critiques.

cs.IR↗

arXiv2021

POINTREC: A Test Collection for Narrative-driven Point of Interest Recommendation

This paper presents a test collection for contextual point of interest (POI) recommendation in a narrative-driven scenario. There, user history is not available, instead, user requests are described in natural language. The requests in our collection are manually collected from social sharing websites, and are annotated with various types of metadata, including location, categories, constraints, and example POIs. These requests are to be resolved from a dataset of POIs, which are collected from a popular online directory, and are further linked to a geographical knowledge base and enriched with relevant web snippets. Graded relevance assessments are collected using crowdsourcing, by pooling both manual and automatic recommendations, where the latter serve as baselines for future performance comparison. This resource supports the development of novel approaches for end-to-end POI recommendation as well as for specific semantic annotation tasks on natural language requests.

cs.IR↗

arXiv2021

Semantic Table Retrieval using Keyword and Table Queries

Tables on the Web contain a vast amount of knowledge in a structured form. To tap into this valuable resource, we address the problem of table retrieval: answering an information need with a ranked list of tables. We investigate this problem in two different variants, based on how the information need is expressed: as a keyword query or as an existing table ("query-by-table"). The main novel contribution of this work is a semantic table retrieval framework for matching information needs (keyword or table queries) against tables. Specifically, we (i) represent queries and tables in multiple semantic spaces (both discrete sparse and continuous dense vector representations) and (ii) introduce various similarity measures for matching those semantic representations. We consider all possible combinations of semantic representations and similarity measures and use these as features in a supervised learning model. Using two purpose-built test collections based on Wikipedia tables, we demonstrate significant and substantial improvements over state-of-the-art baselines.

cs.IR↗

arXiv2021

Conversational Entity Linking: Problem Definition and Datasets

Machine understanding of user utterances in conversational systems is of utmost importance for enabling engaging and meaningful conversations with users. Entity Linking (EL) is one of the means of text understanding, with proven efficacy for various downstream tasks in information retrieval. In this paper, we study entity linking for conversational systems. To develop a better understanding of what EL in a conversational setting entails, we analyze a large number of dialogues from existing conversational datasets and annotate references to concepts, named entities, and personal entities using crowdsourcing. Based on the annotated dialogues, we identify the main characteristics of conversational entity linking. Further, we report on the performance of traditional EL systems on our Conversational Entity Linking dataset, ConEL, and present an extension to these methods to better fit the conversational setting. The resources released with this paper include annotated datasets, detailed descriptions of crowdsourcing setups, as well as the annotations produced by various EL systems. These new resources allow for an investigation of how the role of entities in conversations is different from that in documents or isolated short text utterances like queries and tweets, and complement existing conversational datasets.

cs.CL↗

arXiv2021

Simulating User Satisfaction for the Evaluation of Task-oriented Dialogue Systems

Evaluation is crucial in the development process of task-oriented dialogue systems. As an evaluation method, user simulation allows us to tackle issues such as scalability and cost-efficiency, making it a viable choice for large-scale automatic evaluation. To help build a human-like user simulator that can measure the quality of a dialogue, we propose the following task: simulating user satisfaction for the evaluation of task-oriented dialogue systems. The purpose of the task is to increase the evaluation power of user simulations and to make the simulation more human-like. To overcome a lack of annotated data, we propose a user satisfaction annotation dataset, USS, that includes 6,800 dialogues sampled from multiple domains, spanning real-world e-commerce dialogues, task-oriented dialogues constructed through Wizard-of-Oz experiments, and movie recommendation dialogues. All user utterances in those dialogues, as well as the dialogues themselves, have been labeled based on a 5-level satisfaction scale. We also share three baseline methods for user satisfaction prediction and action prediction tasks. Experiments conducted on the USS dataset suggest that distributed representations outperform feature-based methods. A model based on hierarchical GRUs achieves the best performance in in-domain user satisfaction prediction, while a BERT-based model has better cross-domain generalization ability.

cs.IR↗