Search Results for author: Eugene Agichtein

Found 34 papers, 6 papers with code

Evaluation Metrics of Language Generation Models for Synthetic Traffic Generation Tasks

no code implementations21 Nov 2023 Simone Filice, Jason Ingyu Choi, Giuseppe Castellucci, Eugene Agichtein, Oleg Rokhlenko

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.

Question Generation Question-Generation +1

An Interactive Query Generation Assistant using LLM-based Prompt Modification and User Feedback

1 code implementation19 Nov 2023 Kaustubh D. Dhole, Ramraj Chandradevan, Eugene Agichtein

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.

Contextual Response Interpretation for Automated Structured Interviews: A Case Study in Market Research

no code implementations30 Apr 2023 Harshita Sahijwani, Kaustubh Dhole, Ankur Purwar, Venugopal Vasudevan, Eugene Agichtein

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.

Marketing Multiple-choice +1

Ericson: An Interactive Open-Domain Conversational Search Agent

no code implementations5 Apr 2023 ZiHao Wang, Ali Ahmadvand, Jason Choi, Payam Karisani, Eugene Agichtein

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.

Conversational Search Dialogue Management +6

FCC: Fusing Conversation History and Candidate Provenance for Contextual Response Ranking in Dialogue Systems

no code implementations31 Mar 2023 ZiHao Wang, Eugene Agichtein, Jinho Choi

In a multi-turn dialogue, to capture the gist of a conversation, contextual information serves as essential knowledge to achieve this goal.

Miscellaneous Retrieval

Detecting Elevated Air Pollution Levels by Monitoring Web Search Queries: Deep Learning-Based Time Series Forecasting

no code implementations9 Nov 2022 Chen Lin, Safoora Yousefi, Elvis Kahoro, Payam Karisani, Donghai Liang, Jeremy Sarnat, Eugene Agichtein

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.

Time Series Time Series Forecasting

Making Large Language Models Interactive: A Pioneer Study on Supporting Complex Information-Seeking Tasks with Implicit Constraints

no code implementations2 May 2022 Ali Ahmadvand, Negar Arabzadeh, Julia Kiseleva, Patricio Figueroa Sanz, Xin Deng, Sujay Jauhar, Michael Gamon, Eugene Agichtein, Ned Friend, Aniruddha

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

1 code implementation NAACL 2021 Sergey Volokhin, Joyce Ho, Oleg Rokhlenko, Eugene Agichtein

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.

Collaborative Filtering Domain Adaptation +1

RLIRank: Learning to Rank with Reinforcement Learning for Dynamic Search

no code implementations21 May 2021 Jianghong Zhou, Eugene Agichtein

To support this dynamic ranking paradigm effectively, search result ranking must incorporate both the user feedback received, and the information displayed so far.

Learning-To-Rank reinforcement-learning +1

De-Biased Modelling of Search Click Behavior with Reinforcement Learning

no code implementations21 May 2021 Jianghong Zhou, Sayyed M. Zahiri, Simon Hughes, Khalifeh Al Jadda, Surya Kallumadi, Eugene Agichtein

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.

Learning-To-Rank reinforcement-learning +1

Diversifying Multi-aspect Search Results Using Simpson's Diversity Index

no code implementations21 May 2021 Jianghong Zhou, Eugene Agichtein, Surya Kallumadi

In search and recommendation, diversifying the multi-aspect search results could help with reducing redundancy, and promoting results that might not be shown otherwise.

DeepCAT: Deep Category Representation for Query Understanding in E-commerce Search

no code implementations23 Apr 2021 Ali Ahmadvand, Surya Kallumadi, Faizan Javed, Eugene Agichtein

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

no code implementations NAACL 2021 Iftah Gamzu, Hila Gonen, Gilad Kutiel, Ran Levy, Eugene Agichtein

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.

Document Summarization Multi-Document Summarization

VoiSeR: A New Benchmark for Voice-Based Search Refinement

no code implementations EACL 2021 Simone Filice, Giuseppe Castellucci, Marcus Collins, Eugene Agichtein, Oleg Rokhlenko

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.

Conversational Search

Semantic Product Search for Matching Structured Product Catalogs in E-Commerce

no code implementations18 Aug 2020 Jason Ingyu Choi, Surya Kallumadi, Bhaskar Mitra, Eugene Agichtein, Faizan Javed

Retrieving all semantically relevant products from the product catalog is an important problem in E-commerce.

Quantifying the Effects of Prosody Modulation on User Engagement and Satisfaction in Conversational Systems

no code implementations2 Jun 2020 Jason Ingyu Choi, Eugene Agichtein

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

1 code implementation2 Jun 2020 Jason Ingyu Choi, Ali Ahmadvand, Eugene Agichtein

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

no code implementations28 May 2020 Ali Ahmadvand, Harshita Sahijwani, Eugene Agichtein

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.

Collaborative Filtering

Contextual Dialogue Act Classification for Open-Domain Conversational Agents

1 code implementation28 May 2020 Ali Ahmadvand, Jason Ingyu Choi, Eugene Agichtein

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.

Classification Dialogue Act Classification +3

ConCET: Entity-Aware Topic Classification for Open-Domain Conversational Agents

1 code implementation28 May 2020 Ali Ahmadvand, Harshita Sahijwani, Jason Ingyu Choi, Eugene Agichtein

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.

Classification General Classification +1

JointMap: Joint Query Intent Understanding For Modeling Intent Hierarchies in E-commerce Search

no code implementations28 May 2020 Ali Ahmadvand, Surya Kallumadi, Faizan Javed, Eugene Agichtein

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.

Active Learning

Domain-Guided Task Decomposition with Self-Training for Detecting Personal Events in Social Media

no code implementations21 Apr 2020 Payam Karisani, Joyce C. Ho, Eugene Agichtein

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

no code implementations8 Aug 2018 Dana Sagi, Tzoof Avny, Kira Radinsky, Eugene Agichtein

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.

Feature Engineering Learning-To-Rank +1

Did You Really Just Have a Heart Attack? Towards Robust Detection of Personal Health Mentions in Social Media

2 code implementations26 Feb 2018 Payam Karisani, Eugene Agichtein

The first, critical, task for these applications is classifying whether a personal health event was mentioned, which we call the (PHM) problem.

Epidemiology Semi-Supervised Text Classification

EviNets: Neural Networks for Combining Evidence Signals for Factoid Question Answering

no code implementations ACL 2017 Denis Savenkov, Eugene Agichtein

A critical task for question answering is the final answer selection stage, which has to combine multiple signals available about each answer candidate.

Answer Selection Feature Engineering +4

Cannot find the paper you are looking for? You can Submit a new open access paper.