Search Results for author:
Found 34 papers, 6 papers with code
Wizard of Tasks: A Novel Conversational Dataset for Solving Real-World Tasks in Conversational Settings
Conversational Task Assistants (CTAs) are conversational agents whose goal is to help humans perform real-world tasks.
Evaluation Metrics of Language Generation Models for Synthetic Traffic Generation Tasks
Experiments on three tasks, i. e., Shopping Utterance Generation, Product Question Generation and Query Auto Completion, demonstrate that our metrics are effective for evaluating STG tasks, and improve the agreement with human judgement up to 20% with respect to common NLG metrics.
An Interactive Query Generation Assistant using LLM-based Prompt Modification and User Feedback
While search is the predominant method of accessing information, formulating effective queries remains a challenging task, especially for situations where the users are not familiar with a domain, or searching for documents in other languages, or looking for complex information such as events, which are not easily expressible as queries.
A Deep Reinforcement Learning Approach for Interactive Search with Sentence-level Feedback
Interactive search can provide a better experience by incorporating interaction feedback from the users.
Contextual Response Interpretation for Automated Structured Interviews: A Case Study in Market Research
Structured interviews are used in many settings, importantly in market research on topics such as brand perception, customer habits, or preferences, which are critical to product development, marketing, and e-commerce at large.
Ericson: An Interactive Open-Domain Conversational Search Agent
Open-domain conversational search (ODCS) aims to provide valuable, up-to-date information, while maintaining natural conversations to help users refine and ultimately answer information needs.
FCC: Fusing Conversation History and Candidate Provenance for Contextual Response Ranking in Dialogue Systems
In a multi-turn dialogue, to capture the gist of a conversation, contextual information serves as essential knowledge to achieve this goal.
Detecting Elevated Air Pollution Levels by Monitoring Web Search Queries: Deep Learning-Based Time Series Forecasting
Most of the prior work relied on modeling pollutant concentrations collected from ground-based monitors and meteorological data for long-term forecasting of outdoor ozone, oxides of nitrogen, and PM2. 5.
Alexa, Let's Work Together: Introducing the First Alexa Prize TaskBot Challenge on Conversational Task Assistance
Since its inception in 2016, the Alexa Prize program has enabled hundreds of university students to explore and compete to develop conversational agents through the SocialBot Grand Challenge.
Making Large Language Models Interactive: A Pioneer Study on Supporting Complex Information-Seeking Tasks with Implicit Constraints
Current interactive systems with natural language interfaces lack the ability to understand a complex information-seeking request which expresses several implicit constraints at once, and there is no prior information about user preferences e. g.,"find hiking trails around San Francisco which are accessible with toddlers and have beautiful scenery in summer", where output is a list of possible suggestions for users to start their exploration.
You Sound Like Someone Who Watches Drama Movies: Towards Predicting Movie Preferences from Conversational Interactions
We call our proposed method ConvExtr (Conversational Collaborative Filtering using External Data), which 1) infers a user{'}s sentiment towards an entity from the conversation context, and 2) transforms the ratings of {``}similar{''} external reviewers to predict the current user{'}s preferences.
RLIRank: Learning to Rank with Reinforcement Learning for Dynamic Search
To support this dynamic ranking paradigm effectively, search result ranking must incorporate both the user feedback received, and the information displayed so far.
De-Biased Modelling of Search Click Behavior with Reinforcement Learning
Our experiments demonstrate the effectiveness of the DRLC model in learning to reduce bias in click logs, leading to improved modeling performance and showing the potential for using DRLC for improving Web search quality.
Diversifying Multi-aspect Search Results Using Simpson's Diversity Index
In search and recommendation, diversifying the multi-aspect search results could help with reducing redundancy, and promoting results that might not be shown otherwise.
APRF-Net: Attentive Pseudo-Relevance Feedback Network for Query Categorization
Query categorization is an essential part of query intent understanding in e-commerce search.
DeepCAT: Deep Category Representation for Query Understanding in E-commerce Search
Mapping a search query to a set of relevant categories in the product taxonomy is a significant challenge in e-commerce search for two reasons: 1) Training data exhibits severe class imbalance problem due to biased click behavior, and 2) queries with little customer feedback (e. g., tail queries) are not well-represented in the training set, and cause difficulties for query understanding.
Identifying Helpful Sentences in Product Reviews
This task is closely related to the task of Multi Document Summarization in the product reviews domain but differs in its objective and its level of conciseness.
VoiSeR: A New Benchmark for Voice-Based Search Refinement
This common user intent is usually available through a {``}filter-by{''} interface on online shopping websites, but is challenging to support naturally via voice, as the intent of refinements must be interpreted in the context of the original search, the initial results, and the available product catalogue facets.
Semantic Product Search for Matching Structured Product Catalogs in E-Commerce
Retrieving all semantically relevant products from the product catalog is an important problem in E-commerce.
Would You Like to Hear the News? Investigating Voice-BasedSuggestions for Conversational News Recommendation
One of the key benefits of voice-based personal assistants is the potential to proactively recommend relevant and interesting information.
Quantifying the Effects of Prosody Modulation on User Engagement and Satisfaction in Conversational Systems
To accomplish this, we report results obtained from a large-scale empirical study that measures the effects of prosodic modulation on user behavior and engagement across multiple conversation domains, both immediately after each turn, and at the overall conversation level.
Offline and Online Satisfaction Prediction in Open-Domain Conversational Systems
The insights from our study can enable more intelligent conversational systems, which could adapt in real-time to the inferred user satisfaction and engagement.
Would you Like to Talk about Sports Now? Towards Contextual Topic Suggestion for Open-Domain Conversational Agents
A topic suggested by the agent should be relevant to the person, appropriate for the conversation context, and the agent should have something interesting to say about it.
Contextual Dialogue Act Classification for Open-Domain Conversational Agents
Furthermore, our results show that fine-tuning the CDAC model on a small sample of manually labeled human-machine conversations allows CDAC to more accurately predict dialogue acts in real users' conversations, suggesting a promising direction for future improvements.
ConCET: Entity-Aware Topic Classification for Open-Domain Conversational Agents
Our results show that ConCET significantly improves topic classification performance on both datasets, including 8-10% improvements over state-of-the-art deep learning methods.
JointMap: Joint Query Intent Understanding For Modeling Intent Hierarchies in E-commerce Search
In this paper, we introduce Joint Query Intent Understanding (JointMap), a deep learning model to simultaneously learn two different high-level user intent tasks: 1) identifying a query's commercial vs. non-commercial intent, and 2) associating a set of relevant product categories in taxonomy to a product query.
Domain-Guided Task Decomposition with Self-Training for Detecting Personal Events in Social Media
Mining social media content for tasks such as detecting personal experiences or events, suffer from lexical sparsity, insufficient training data, and inventive lexicons.
General Classification
Semi-Supervised Text Classification
+1
Learning to Focus when Ranking Answers
One of the main challenges in ranking is embedding the query and document pairs into a joint feature space, which can then be fed to a learning-to-rank algorithm.
Did You Really Just Have a Heart Attack? Towards Robust Detection of Personal Health Mentions in Social Media
The first, critical, task for these applications is classifying whether a personal health event was mentioned, which we call the (PHM) problem.
EviNets: Neural Networks for Combining Evidence Signals for Factoid Question Answering
A critical task for question answering is the final answer selection stage, which has to combine multiple signals available about each answer candidate.
