18 citations · 97 across the 27 of their papers we have counts for
11 papers · 1 filter
Evaluation Metrics of Language Generation Models for Synthetic Traffic Generation Tasks
Simone Filice, Jason Ingyu Choi, Giuseppe Castellucci +2
Many Natural Language Generation (NLG) tasks aim to generate a single output text given an input prompt. Other settings require the generation of multiple texts, e.g., for Syntheti…
Ericson: An Interactive Open-Domain Conversational Search Agent
Zihao Wang, Ali Ahmadvand, Jason Choi +2
Open-domain conversational search (ODCS) aims to provide valuable, up-to-date information, while maintaining natural conversations to help users refine and ultimately answer inform…
FCC: Fusing Conversation History and Candidate Provenance for Contextual Response Ranking in Dialogue Systems
Zihao Wang, Eugene Agichtein, Jinho Choi
Response ranking in dialogues plays a crucial role in retrieval-based conversational systems. In a multi-turn dialogue, to capture the gist of a conversation, contextual informatio…
Alexa, Let's Work Together: Introducing the First Alexa Prize TaskBot Challenge on Conversational Task Assistance
Anna Gottardi, Osman Ipek, Giuseppe Castellucci +27
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…
Identifying Helpful Sentences in Product Reviews
Iftah Gamzu, Hila Gonen, Gilad Kutiel +2
In recent years online shopping has gained momentum and became an important venue for customers wishing to save time and simplify their shopping process. A key advantage of shoppin…
Contextual Dialogue Act Classification for Open-Domain Conversational Agents
Ali Ahmadvand, Jason Ingyu Choi, Eugene Agichtein
Classifying the general intent of the user utterance in a conversation, also known as Dialogue Act (DA), e.g., open-ended question, statement of opinion, or request for an opinion,…
Would you Like to Talk about Sports Now? Towards Contextual Topic Suggestion for Open-Domain Conversational Agents
Ali Ahmadvand, Harshita Sahijwani, Eugene Agichtein
To hold a true conversation, an intelligent agent should be able to occasionally take initiative and recommend the next natural conversation topic. This is a challenging task. A to…
ConCET: Entity-Aware Topic Classification for Open-Domain Conversational Agents
Ali Ahmadvand, Harshita Sahijwani, Jason Ingyu Choi +1
Identifying the topic (domain) of each user's utterance in open-domain conversational systems is a crucial step for all subsequent language understanding and response tasks. In par…
Domain-Guided Task Decomposition with Self-Training for Detecting Personal Events in Social Media
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. To reduce…
Learning to Focus when Ranking Answers
Dana Sagi, Tzoof Avny, Kira Radinsky +1
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. To achieve this r…
Did You Really Just Have a Heart Attack? Towards Robust Detection of Personal Health Mentions in Social Media
Payam Karisani, Eugene Agichtein
Millions of users share their experiences on social media sites, such as Twitter, which in turn generate valuable data for public health monitoring, digital epidemiology, and other…