Search Results for author:
Found 218 papers, 139 papers with code
AGENT-CQ: Automatic Generation and Evaluation of Clarifying Questions for Conversational Search with LLMs
Human evaluation and CrowdLLM show that the AGENT-CQ - generation stage, consistently outperforms baselines in various aspects of question and answer quality.
Evaluation of Attribution Bias in Retrieval-Augmented Large Language Models
Our results show that adding authorship information to source documents can significantly change the attribution quality of LLMs by 3% to 18%.
MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization
As large language models (LLMs) are rapidly advancing and achieving near-human capabilities, aligning them with human values is becoming more urgent.
Information Discovery in e-Commerce
Methods for information discovery in e-commerce largely focus on improving the effectiveness of e-commerce search and recommender systems, on enriching and using knowledge graphs to support e-commerce, and on developing innovative question answering and bot-based solutions that help to connect people to goods and services.
Table Question Answering for Low-resourced Indic Languages
TableQA models trained on our large-scale datasets outperform state-of-the-art LLMs.
Cognitive Biases in Large Language Models for News Recommendation
Despite large language models (LLMs) increasingly becoming important components of news recommender systems, employing LLMs in such systems introduces new risks, such as the influence of cognitive biases in LLMs.
Generative Retrieval Meets Multi-Graded Relevance
GR$^2$ focuses on two key components: ensuring relevant and distinct identifiers, and implementing multi-graded constrained contrastive training.
Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Method
We have developed a Chinese-language benchmark, PatentMIA, to assess the performance of detection approaches for LLMs on Chinese text.
AQA: Adaptive Question Answering in a Society of LLMs via Contextual Multi-Armed Bandit
In question answering (QA), different questions can be effectively addressed with different answering strategies.
Proximal Ranking Policy Optimization for Practical Safety in Counterfactual Learning to Rank
We propose a novel approach, proximal ranking policy optimization (PRPO), that provides safety in deployment without assumptions about user behavior.
Real World Conversational Entity Linking Requires More Than Zeroshots
Entity linking (EL) in conversations faces notable challenges in practical applications, primarily due to the scarcity of entity-annotated conversational datasets and sparse knowledge bases (KB) containing domain-specific, long-tail entities.
Towards Empathetic Conversational Recommender Systems
With empathy we refer to a system's ability to capture and express emotions.
Practical and Robust Safety Guarantees for Advanced Counterfactual Learning to Rank
Our experiments show that both our novel safe doubly robust method and PRPO provide higher performance than the existing safe inverse propensity scoring approach.
Assessing Brittleness of Image-Text Retrieval Benchmarks from Vision-Language Models Perspective
We examine the brittleness of the image-text retrieval (ITR) evaluation pipeline with a focus on concept granularity.
Bootstrapped Pre-training with Dynamic Identifier Prediction for Generative Retrieval
Generative retrieval uses differentiable search indexes to directly generate relevant document identifiers in response to a query.
Robust Neural Information Retrieval: An Adversarial and Out-of-distribution Perspective
Recent advances in neural information retrieval (IR) models have significantly enhanced their effectiveness over various IR tasks.
The SIFo Benchmark: Investigating the Sequential Instruction Following Ability of Large Language Models
Following multiple instructions is a crucial ability for large language models (LLMs).
Robust Information Retrieval
Beyond effectiveness, the robustness of an information retrieval (IR) system is increasingly attracting attention.
Let Me Do It For You: Towards LLM Empowered Recommendation via Tool Learning
Through the integration of LLMs, ToolRec enables conventional recommender systems to become external tools with a natural language interface.
Optimal Baseline Corrections for Off-Policy Contextual Bandits
The foundation of our framework is the derivation of an equivalent baseline correction for all of the existing control variates.
QFMTS: Generating Query-Focused Summaries over Multi-Table Inputs
Our approach, which comprises a table serialization module, a summarization controller, and a large language model (LLM), utilizes textual queries and multiple tables to generate query-dependent table summaries tailored to users' information needs.
Are We Really Achieving Better Beyond-Accuracy Performance in Next Basket Recommendation?
So far, most NBR studies have focused on optimizing the accuracy of the recommendation, whereas optimizing for beyond-accuracy metrics, e. g., item fairness and diversity remains largely unexplored.
A First Look at Selection Bias in Preference Elicitation for Recommendation
Despite the fact that the extreme sparsity of preference elicitation interactions make them severely more prone to selection bias than natural interactions, the effect of selection bias in preference elicitation on the resulting recommendations has not been studied yet.
Going Beyond Popularity and Positivity Bias: Correcting for Multifactorial Bias in Recommender Systems
Debiasing methods aim to mitigate the effect of selection bias on the evaluation and optimization of RSs.
Ranked List Truncation for Large Language Model-based Re-Ranking
RLT is crucial for re-ranking as it can improve re-ranking efficiency by sending variable-length candidate lists to a re-ranker on a per-query basis.
ExcluIR: Exclusionary Neural Information Retrieval
However, in information retrieval community, there is little research on exclusionary retrieval, where users express what they do not want in their queries.
Large Language Models for Next Point-of-Interest Recommendation
Our results show that the proposed framework outperforms the state-of-the-art models in all three datasets.
Rethinking the Evaluation of Dialogue Systems: Effects of User Feedback on Crowdworkers and LLMs
Workers are more susceptible to user feedback on usefulness and interestingness compared to LLMs on interestingness and relevance.
Estimating the Hessian Matrix of Ranking Objectives for Stochastic Learning to Rank with Gradient Boosted Trees
Stochastic learning to rank (LTR) is a recent branch in the LTR field that concerns the optimization of probabilistic ranking models.
Context Does Matter: Implications for Crowdsourced Evaluation Labels in Task-Oriented Dialogue Systems
Using the first user utterance as context leads to consistent ratings, akin to those obtained using the entire dialogue, with significantly reduced annotation effort.
Unbiased Learning to Rank Meets Reality: Lessons from Baidu's Large-Scale Search Dataset
Our experiments reveal that gains in click prediction do not necessarily translate to enhanced ranking performance on expert relevance annotations, implying that conclusions strongly depend on how success is measured in this benchmark.
Multi-granular Adversarial Attacks against Black-box Neural Ranking Models
However, limiting perturbations to a single level of granularity may reduce the flexibility of adversarial examples, thereby diminishing the potential threat of the attack.
Query Performance Prediction using Relevance Judgments Generated by Large Language Models
To solve the challenges, we devise an approximation strategy to predict an IR measure considering recall and propose to fine-tune open-source LLMs using human-labeled relevance judgments.
Generative Retrieval as Multi-Vector Dense Retrieval
Both methods compute relevance as a sum of products of query and document vectors and an alignment matrix.
Are Large Language Models Good at Utility Judgments?
Retrieval-augmented generation (RAG) is considered to be a promising approach to alleviate the hallucination issue of large language models (LLMs), and it has received widespread attention from researchers recently.
CAUSE: Counterfactual Assessment of User Satisfaction Estimation in Task-Oriented Dialogue Systems
In this work, we leverage large language models (LLMs) and unlock their ability to generate satisfaction-aware counterfactual dialogues to augment the set of original dialogues of a test collection.
RankingSHAP -- Listwise Feature Attribution Explanations for Ranking Models
We evaluate RankingSHAP for commonly used learning-to-rank datasets to showcase the more nuanced use of an attribution method while highlighting the limitations of selection-based explanations.
Listwise Generative Retrieval Models via a Sequential Learning Process
Specifically, we view the generation of a ranked docid list as a sequence learning process: at each step we learn a subset of parameters that maximizes the corresponding generation likelihood of the $i$-th docid given the (preceding) top $i-1$ docids.
Measuring Bias in a Ranked List using Term-based Representations
With TExFAIR, we extend the AWRF framework to allow for the evaluation of fairness in settings with term-based representations of groups in documents in a ranked list.
MELoRA: Mini-Ensemble Low-Rank Adapters for Parameter-Efficient Fine-Tuning
Parameter-efficient fine-tuning (PEFT) is a popular method for tailoring pre-trained large language models (LLMs), especially as the models' scale and the diversity of tasks increase.
Demonstrating and Reducing Shortcuts in Vision-Language Representation Learning
Hence, contrastive losses are not sufficient to learn task-optimal representations, i. e., representations that contain all task-relevant information shared between the image and associated captions.
Multimodal Learned Sparse Retrieval with Probabilistic Expansion Control
Our proposed approach efficiently transforms dense vectors from a frozen dense model into sparse lexical vectors.
CorpusBrain++: A Continual Generative Pre-Training Framework for Knowledge-Intensive Language Tasks
Very recently, a pre-trained generative retrieval model for KILTs, named CorpusBrain, was proposed and reached new state-of-the-art retrieval performance.
Query Augmentation by Decoding Semantics from Brain Signals
If the quality of the initially retrieved documents is low, then the effectiveness of query augmentation would be limited as well.
KnowTuning: Knowledge-aware Fine-tuning for Large Language Models
To address these problems, we propose a knowledge-aware fine-tuning (KnowTuning) method to improve fine-grained and coarse-grained knowledge awareness of LLMs.
Asking Multimodal Clarifying Questions in Mixed-Initiative Conversational Search
Therefore, we propose to add images to clarifying questions and formulate the novel task of asking multimodal clarifying questions in open-domain, mixed-initiative conversational search systems.
Perturbation-Invariant Adversarial Training for Neural Ranking Models: Improving the Effectiveness-Robustness Trade-Off
We decompose the robust ranking error into two components, i. e., a natural ranking error for effectiveness evaluation and a boundary ranking error for assessing adversarial robustness.
SARDINE: A Simulator for Automated Recommendation in Dynamic and Interactive Environments
Simulators can provide valuable insights for researchers and practitioners who wish to improve recommender systems, because they allow one to easily tweak the experimental setup in which recommender systems operate, and as a result lower the cost of identifying general trends and uncovering novel findings about the candidate methods.
Language Generation from Brain Recordings
Inspired by recent research that revealed associations between the brain and the large computational language models, we propose a generative language BCI that utilizes the capacity of a large language model (LLM) jointly with a semantic brain decoder to directly generate language from functional magnetic resonance imaging (fMRI) input.
Learning Robust Sequential Recommenders through Confident Soft Labels
CSRec contains a teacher module that generates high-quality and confident soft labels and a student module that acts as the target recommender and is trained on the combination of dense, soft labels and sparse, one-hot labels.
Hierarchical Forecasting at Scale
We implement our sparse hierarchical loss function within an existing forecasting model at bol, a large European e-commerce platform, resulting in an improved forecasting performance of 2% at the product level.
From Relevance to Utility: Evidence Retrieval with Feedback for Fact Verification
We argue that, rather than relevance, for FV we need to focus on the utility that a claim verifier derives from the retrieved evidence.
Generalizing Few-Shot Named Entity Recognizers to Unseen Domains with Type-Related Features
To address this limitation, recent studies enable generalization to an unseen target domain with only a few labeled examples using data augmentation techniques.
Predictive Uncertainty-based Bias Mitigation in Ranking
Prior work on bias mitigation often assumes that ranking scores, which correspond to the utility that a document holds for a user, can be accurately determined.
Continual Learning for Generative Retrieval over Dynamic Corpora
We put forward a novel Continual-LEarner for generatiVE Retrieval (CLEVER) model and make two major contributions to continual learning for GR: (i) To encode new documents into docids with low computational cost, we present Incremental Product Quantization, which updates a partial quantization codebook according to two adaptive thresholds; and (ii) To memorize new documents for querying without forgetting previous knowledge, we propose a memory-augmented learning mechanism, to form meaningful connections between old and new documents.
Black-box Adversarial Attacks against Dense Retrieval Models: A Multi-view Contrastive Learning Method
The AREA task is meant to trick DR models into retrieving a target document that is outside the initial set of candidate documents retrieved by the DR model in response to a query.
The Impact of Group Membership Bias on the Quality and Fairness of Exposure in Ranking
With group membership bias, the utility of the sensitive groups is under-estimated, hence, without correcting for this bias, a supposedly fair ranking is not truly fair.
Masked and Swapped Sequence Modeling for Next Novel Basket Recommendation in Grocery Shopping
In next basket recommendation (NBR), it is useful to distinguish between repeat items, i. e., items that a user has consumed before, and explore items, i. e., items that a user has not consumed before.
Answering Ambiguous Questions via Iterative Prompting
To provide feasible answers to an ambiguous question, one approach is to directly predict all valid answers, but this can struggle with balancing relevance and diversity.
RecFusion: A Binomial Diffusion Process for 1D Data for Recommendation
In this paper we propose RecFusion, which comprise a set of diffusion models for recommendation.
Distributional Reinforcement Learning with Dual Expectile-Quantile Regression
Motivated by the efficiency of $L_2$-based learning, we propose to jointly learn expectiles and quantiles of the return distribution in a way that allows efficient learning while keeping an estimate of the full distribution of returns.
MultiTabQA: Generating Tabular Answers for Multi-Table Question Answering
Recent advances in tabular question answering (QA) with large language models are constrained in their coverage and only answer questions over a single table.
Query Performance Prediction: From Ad-hoc to Conversational Search
The QPP task is to predict the retrieval quality of a search system for a query without relevance judgments.
Iteratively Learning Representations for Unseen Entities with Inter-Rule Correlations
Recent work on knowledge graph completion (KGC) focused on learning embeddings of entities and relations in knowledge graphs.
Improving Implicit Feedback-Based Recommendation through Multi-Behavior Alignment
Recommender systems that learn from implicit feedback often use large volumes of a single type of implicit user feedback, such as clicks, to enhance the prediction of sparse target behavior such as purchases.
On the Impact of Outlier Bias on User Clicks
We therefore propose an outlier-aware click model that accounts for both outlier and position bias, called outlier-aware position-based model ( OPBM).
A Unified Generative Retriever for Knowledge-Intensive Language Tasks via Prompt Learning
Learning task-specific retrievers that return relevant contexts at an appropriate level of semantic granularity, such as a document retriever, passage retriever, sentence retriever, and entity retriever, may help to achieve better performance on the end-to-end task.
Topic-oriented Adversarial Attacks against Black-box Neural Ranking Models
In this paper, we focus on a more general type of perturbation and introduce the topic-oriented adversarial ranking attack task against NRMs, which aims to find an imperceptible perturbation that can promote a target document in ranking for a group of queries with the same topic.
Safe Deployment for Counterfactual Learning to Rank with Exposure-Based Risk Minimization
For the CLTR field, our novel exposure-based risk minimization method enables practitioners to adopt CLTR methods in a safer manner that mitigates many of the risks attached to previous methods.
An Offline Metric for the Debiasedness of Click Models
We prove that debiasedness is a necessary condition for recovering unbiased and consistent relevance scores and for the invariance of click prediction under covariate shift.
A Self-Correcting Sequential Recommender
STEAM first corrects an input item sequence by adjusting the misclicked and/or missed items.
Generative Slate Recommendation with Reinforcement Learning
Our findings suggest that representation learning using generative models is a promising direction towards generalizable RL-based slate recommendation.
Scene-centric vs. Object-centric Image-Text Cross-modal Retrieval: A Reproducibility Study
Additionally, we select two scene-centric datasets, and three object-centric datasets, and determine the relative performance of the selected models on these datasets.
Modeling Sequential Recommendation as Missing Information Imputation
To address the limitation of sequential recommenders with side information, we define a way to fuse side information and alleviate the problem of missing side information by proposing a unified task, namely the missing information imputation (MII), which randomly masks some feature fields in a given sequence of items, including item IDs, and then forces a predictive model to recover them.
Offline Evaluation for Reinforcement Learning-based Recommendation: A Critical Issue and Some Alternatives
In this paper, we argue that the paradigm commonly adopted for offline evaluation of sequential recommender systems is unsuitable for evaluating reinforcement learning-based recommenders.
Contrastive Learning Reduces Hallucination in Conversations
MixCL effectively reduces the hallucination of LMs in conversations and achieves the highest performance among LM-based dialogue agents in terms of relevancy and factuality.
Feature-Level Debiased Natural Language Understanding
We also propose a dynamic negative sampling strategy to capture the dynamic influence of biases by employing a bias-only model to dynamically select the most similar biased negative samples.
RADio -- Rank-Aware Divergence Metrics to Measure Normative Diversity in News Recommendations
In traditional recommender system literature, diversity is often seen as the opposite of similarity, and typically defined as the distance between identified topics, categories or word models.
Certified Robustness to Word Substitution Ranking Attack for Neural Ranking Models
A ranking model is said to be Certified Top-$K$ Robust on a ranked list when it is guaranteed to keep documents that are out of the top $K$ away from the top $K$ under any attack.
Intersection of Parallels as an Early Stopping Criterion
Using this result, we propose to train two parallel instances of a linear model, initialized with different random seeds, and use their intersection as a signal to detect overfitting.
Towards the Use of Saliency Maps for Explaining Low-Quality Electrocardiograms to End Users
In this paper, we report on ongoing work regarding (i) the development of an AI system for flagging and explaining low-quality medical images in real-time, (ii) an interview study to understand the explanation needs of stakeholders using the AI system at OurCompany, and, (iii) a longitudinal user study design to examine the effect of including explanations on the workflow of the technicians in our clinics.
Debiasing Learning for Membership Inference Attacks Against Recommender Systems
To address the above limitations, we propose a Debiasing Learning for Membership Inference Attacks against recommender systems (DL-MIA) framework that has four main components: (1) a difference vector generator, (2) a disentangled encoder, (3) a weight estimator, and (4) an attack model.
A Simulation Environment and Reinforcement Learning Method for Waste Reduction
We frame inventory restocking as a new reinforcement learning task that exhibits stochastic behavior conditioned on the agent's actions, making the environment partially observable.
Distributional Reinforcement Learning
reinforcement-learning
+2
Fairness of Exposure in Light of Incomplete Exposure Estimation
In this work, we discuss how to approach fairness of exposure in cases where the policy contains rankings of which, due to inter-item dependencies, we cannot reliably estimate the exposure distribution.
State Encoders in Reinforcement Learning for Recommendation: A Reproducibility Study
In response to these shortcomings, we reproduce and expand on the existing comparison of attention-based state encoders (1) in the publicly available debiased RL4Rec SOFA simulator with (2) a different RL method, (3) more state encoders, and (4) a different dataset.
A Simple Contrastive Learning Objective for Alleviating Neural Text Degeneration
The cross-entropy objective has proved to be an all-purpose training objective for autoregressive language models (LMs).
Reducing Predictive Feature Suppression in Resource-Constrained Contrastive Image-Caption Retrieval
We add an additional decoder to the contrastive ICR framework, to reconstruct the input caption in a latent space of a general-purpose sentence encoder, which prevents the image and caption encoder from suppressing predictive features.
Probabilistic Permutation Graph Search: Black-Box Optimization for Fairness in Ranking
Different from PL, where pointwise logits are used as the distribution parameters, in PPG pairwise inversion probabilities together with a reference permutation construct the distribution.
Understanding User Satisfaction with Task-oriented Dialogue Systems
What is the influence of user experience on the user satisfaction rating of TDS as opposed to, or in addition to, utility?
Conversational Recommendation
Task-Oriented Dialogue Systems
Summarization with Graphical Elements
Motivated from these two angles, we propose a new task: summarization with graphical elements, and we verify that these summaries are helpful for a critical mass of people.
Parameter-Efficient Abstractive Question Answering over Tables or Text
In this work, we study parameter-efficient abstractive QA in encoder-decoder models over structured tabular data and unstructured textual data using only 1. 5% additional parameters for each modality.
PRADA: Practical Black-Box Adversarial Attacks against Neural Ranking Models
We focus on the decision-based black-box attack setting, where the attackers cannot directly get access to the model information, but can only query the target model to obtain the rank positions of the partial retrieved list.
Metaphorical User Simulators for Evaluating Task-oriented Dialogue Systems
Employing existing user simulators to evaluate TDSs is challenging as user simulators are primarily designed to optimize dialogue policies for TDSs and have limited evaluation capabilities.
Conversational Recommendation
Task-Oriented Dialogue Systems
Do Lessons from Metric Learning Generalize to Image-Caption Retrieval?
Recent progress in metric learning has given rise to new loss functions that outperform the triplet loss on tasks such as image retrieval and representation learning.
Extending CLIP for Category-to-image Retrieval in E-commerce
One aspect of this data is a category tree that is being used in search and recommendation.
Understanding and Mitigating the Effect of Outliers in Fair Ranking
We formalize outlierness in a ranking, show that outliers are present in realistic datasets, and present the results of an eye-tracking study, showing that users scanning order and the exposure of items are influenced by the presence of outliers.
Parameter Efficient Deep Probabilistic Forecasting
However, these methods require a large number of parameters to be learned, which imposes high memory requirements on the computational resources for training such models.
It Is Different When Items Are Older: Debiasing Recommendations When Selection Bias and User Preferences Are Dynamic
We theoretically show that in a dynamic scenario in which both the selection bias and user preferences are dynamic, existing debiasing methods are no longer unbiased.
Reproducibility as a Mechanism for Teaching Fairness, Accountability, Confidentiality, and Transparency in Artificial Intelligence
In this work, we explain the setup for a technical, graduate-level course on Fairness, Accountability, Confidentiality, and Transparency in Artificial Intelligence (FACT-AI) at the University of Amsterdam, which teaches FACT-AI concepts through the lens of reproducibility.
A Next Basket Recommendation Reality Check
We propose a set of metrics that measure the repeat/explore ratio and performance of NBR models.
ReMeDi: Resources for Multi-domain, Multi-service, Medical Dialogues
(1) there is no dataset with large-scale medical dialogues that covers multiple medical services and contains fine-grained medical labels (i. e., intents, actions, slots, values), and (2) there is no set of established benchmarks for MDSs for multi-domain, multi-service medical dialogues.
sigmoidF1: A Smooth F1 Score Surrogate Loss for Multilabel Classification
We propose a loss function, sigmoidF1, which is an approximation of the F1 score that (1) is smooth and tractable for stochastic gradient descent, (2) naturally approximates a multilabel metric, and (3) estimates label propensities and label counts.
Mixture-Based Correction for Position and Trust Bias in Counterfactual Learning to Rank
Affine correction (AC) is a generalization of IPS that corrects for position bias and trust bias.
A Human-machine Collaborative Framework for Evaluating Malevolence in Dialogues
HMCEval casts dialogue evaluation as a sample assignment problem, where we need to decide to assign a sample to a human or a machine for evaluation.
Learning to Ask Conversational Questions by Optimizing Levenshtein Distance
Conversational Question Simplification (CQS) aims to simplify self-contained questions into conversational ones by incorporating some conversational characteristics, e. g., anaphora and ellipsis.
News Article Retrieval in Context for Event-centric Narrative Creation
Given an incomplete narrative that specifies a main event and a context, we aim to retrieve news articles that discuss relevant events that would enable the continuation of the narrative.
Few-Shot Electronic Health Record Coding through Graph Contrastive Learning
We seek to improve the performance for both frequent and rare ICD codes by using a contrastive graph-based EHR coding framework, CoGraph, which re-casts EHR coding as a few-shot learning task.
Improving Transformer-based Sequential Recommenders through Preference Editing
By doing so, the SR model is able to learn how to identify common and unique user preferences, and thereby do better user preference extraction and representation.
Probabilistic Gradient Boosting Machines for Large-Scale Probabilistic Regression
We propose Probabilistic Gradient Boosting Machines (PGBM), a method to create probabilistic predictions with a single ensemble of decision trees in a computationally efficient manner.
Wizard of Search Engine: Access to Information Through Conversations with Search Engines
(2) We release a benchmark dataset, called wizard of search engine (WISE), which allows for comprehensive and in-depth research on all aspects of CIS.
Cross-Domain Contract Element Extraction with a Bi-directional Feedback Clause-Element Relation Network
First, contract elements are far more fine-grained than named entities, which hinders the transfer of extractors.
Cross-Domain Named Entity Recognition
Graph Neural Network
+5
Semi-Supervised Variational Reasoning for Medical Dialogue Generation
We propose an end-to-end variational reasoning approach to medical dialogue generation.
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.
Improving Response Quality with Backward Reasoning in Open-domain Dialogue Systems
The proposed backward reasoning step pushes the model to produce more informative and coherent content because the forward generation step's output is used to infer the dialogue context in the backward direction.
A Large-Scale Analysis of Mixed Initiative in Information-Seeking Dialogues for Conversational Search
These datasets were collected to inform different dialogue-based tasks including conversational search.
A Cooperative Memory Network for Personalized Task-oriented Dialogue Systems with Incomplete User Profiles
We find that CoMemNN is able to enrich user profiles effectively, which results in an improvement of 3. 06% in terms of response selection accuracy compared to state-of-the-art methods.
Robust Generalization and Safe Query-Specialization in Counterfactual Learning to Rank
We introduce the Generalization and Specialization (GENSPEC) algorithm, a robust feature-based counterfactual LTR method that pursues per-query memorization when it is safe to do so.
CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks
In this work, we propose a method for generating CF explanations for GNNs: the minimal perturbation to the input (graph) data such that the prediction changes.
Advances and Challenges in Conversational Recommender Systems: A Survey
In this paper, we provide a systematic review of the techniques used in current CRSs.
Abstractive Opinion Tagging
In this paper, we propose the abstractive opinion tagging task, where systems have to automatically generate a ranked list of opinion tags that are based on, but need not occur in, a given set of user-generated reviews.
Analyzing and Predicting Purchase Intent in E-commerce: Anonymous vs. Identified Customers
In this paper, we focus on purchase prediction for both anonymous and identified sessions on an e-commerce platform.
What Makes a Good and Useful Summary? Incorporating Users in Automatic Summarization Research
Motivated by our findings, we present ways to mitigate this mismatch in future research on automatic summarization: we propose research directions that impact the design, the development and the evaluation of automatically generated summaries.
Unifying Online and Counterfactual Learning to Rank
With the introduction of the intervention-aware estimator, we aim to bridge the online/counterfactual LTR division as it is shown to be highly effective in both online and counterfactual scenarios.
Conversational Browsing
How can we better understand the mechanisms behind multi-turn information seeking dialogues?
Mixed Information Flow for Cross-domain Sequential Recommendations
One of the key challenges in cross-domain sequential recommendation is to grasp and transfer the flow of information from multiple domains so as to promote recommendations in all domains.
Guided Dialogue Policy Learning without Adversarial Learning in the Loop
Reinforcement learning methods have emerged as a popular choice for training an efficient and effective dialogue policy.
Star Graph Neural Networks for Session-based Recommendation
The proposed SGNN-HN applies a star graph neural network (SGNN) to model the complex transition relationship between items in an ongoing session.
Ranked #1 on
Session-Based Recommendations
on yoochoose1/64
Rethinking Supervised Learning and Reinforcement Learning in Task-Oriented Dialogue Systems
Then, the traditional multi-label classification solution for dialogue policy learning is extended by adding dense layers to improve the dialogue agent performance.
When Inverse Propensity Scoring does not Work: Affine Corrections for Unbiased Learning to Rank
Our main contribution is a new estimator based on affine corrections: it both reweights clicks and penalizes items displayed on ranks with high trust bias.
Detecting and Classifying Malevolent Dialogue Responses: Taxonomy, Data and Methodology
In this paper, we define the task of Malevolent Dialogue Response Detection and Classification (MDRDC).
Diversifying Task-oriented Dialogue Response Generation with Prototype Guided Paraphrasing
Instead of generating a response from scratch, P2-Net generates system responses by paraphrasing template-based responses.
Attribute-aware Diversification for Sequential Recommendations
Users prefer diverse recommendations over homogeneous ones.
Taking the Counterfactual Online: Efficient and Unbiased Online Evaluation for Ranking
LogOpt turns the counterfactual approach - which is indifferent to the logging policy - into an online approach, where the algorithm decides what rankings to display.
Pre-Trained Models for Heterogeneous Information Networks
We propose a self-supervised pre-training and fine-tuning framework, PF-HIN, to capture the features of a heterogeneous information network.
Optimizing Interactive Systems via Data-Driven Objectives
Effective optimization is essential for real-world interactive systems to provide a satisfactory user experience in response to changing user behavior.
Cascade Model-based Propensity Estimation for Counterfactual Learning to Rank
Unbiased CLTR requires click propensities to compensate for the difference between user clicks and true relevance of search results via IPS.
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.
Query Resolution for Conversational Search with Limited Supervision
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.
Accelerated Convergence for Counterfactual Learning to Rank
Counterfactual Learning to Rank (LTR) algorithms learn a ranking model from logged user interactions, often collected using a production system.
Policy-Aware Unbiased Learning to Rank for Top-k Rankings
We prove that the policy-aware estimator is unbiased if every relevant item has a non-zero probability to appear in the top-k ranking.
Rethinking Item Importance in Session-based Recommendation
We employ a modified self-attention mechanism to estimate item importance in a session, which is then used to predict user's long-term preference.
WN-Salience: A Corpus of News Articles with Entity Salience Annotations
To support research on entity salience, we present a new dataset, the WikiNews Salience dataset (WN-Salience), which can be used to benchmark tasks such as entity salience detection and salient entity linking.
Conversations with Search Engines: SERP-based Conversational Response Generation
In this paper, we address the problem of answering complex information needs by conversing conversations with search engines, in the sense that users can express their queries in natural language, and directly receivethe information they need from a short system response in a conversational manner.
Guided Dialog Policy Learning without Adversarial Learning in the Loop
Reinforcement Learning (RL) methods have emerged as a popular choice for training an efficient and effective dialogue policy.