Ad-hoc Document Retrieval using Weak-Supervision with BERT and GPT2

no code implementations • EMNLP 2020 • Yosi Mass, Haggai Roitman

We describe a weakly-supervised method for training deep learning models for the task of ad-hoc document retrieval.

Deep Learning Information Retrieval +1

Conversational Search with Mixed-Initiative - Asking Good Clarification Questions backed-up by Passage Retrieval

no code implementations • dialdoc (ACL) 2022 • Yosi Mass, Doron Cohen, Asaf Yehudai, David Konopnicki

We deal with the scenario of conversational search, where user queries are under-specified or ambiguous.

Conversational Search Passage Retrieval +1

Genie: Achieving Human Parity in Content-Grounded Datasets Generation

no code implementations • 25 Jan 2024 • Asaf Yehudai, Boaz Carmeli, Yosi Mass, Ofir Arviv, Nathaniel Mills, Assaf Toledo, Eyal Shnarch, Leshem Choshen

Furthermore, we compare models trained on our data with models trained on human-written data -- ELI5 and ASQA for LFQA and CNN-DailyMail for Summarization.

Long Form Question Answering

QAID: Question Answering Inspired Few-shot Intent Detection

no code implementations • 2 Mar 2023 • Asaf Yehudai, Matan Vetzler, Yosi Mass, Koren Lazar, Doron Cohen, Boaz Carmeli

Intent detection with semantically similar fine-grained intents is a challenging task.

Intent Detection Question Answering +1

Conversational Search with Mixed-Initiative -- Asking Good Clarification Questions backed-up by Passage Retrieval

no code implementations • 14 Dec 2021 • Yosi Mass, Doron Cohen, Asaf Yehudai, David Konopnicki

We deal with the scenario of conversational search, where user queries are under-specified or ambiguous.

Conversational Search Passage Retrieval +2

Conversational Document Prediction to Assist Customer Care Agents

1 code implementation • EMNLP 2020 • Jatin Ganhotra, Haggai Roitman, Doron Cohen, Nathaniel Mills, Chulaka Gunasekara, Yosi Mass, Sachindra Joshi, Luis Lastras, David Konopnicki

A frequent pattern in customer care conversations is the agents responding with appropriate webpage URLs that address users' needs.

Information Retrieval Retrieval

Agent Assist through Conversation Analysis

no code implementations • EMNLP 2020 • Kshitij Fadnis, Nathaniel Mills, Jatin Ganhotra, Haggai Roitman, Gaurav Pandey, Doron Cohen, Yosi Mass, Shai Erera, Chulaka Gunasekara, Danish Contractor, Siva Patel, Q. Vera Liao, Sachindra Joshi, Luis Lastras, David Konopnicki

Customer support agents play a crucial role as an interface between an organization and its end-users.

Information Retrieval Retrieval

Unsupervised FAQ Retrieval with Question Generation and BERT

no code implementations • ACL 2020 • Yosi Mass, Boaz Carmeli, Haggai Roitman, David Konopnicki

The two models match user queries to FAQ answers and questions, respectively.

Question Generation Question-Generation +1

A Summarization System for Scientific Documents

no code implementations • IJCNLP 2019 • Shai Erera, Michal Shmueli-Scheuer, Guy Feigenblat, Ora Peled Nakash, Odellia Boni, Haggai Roitman, Doron Cohen, Bar Weiner, Yosi Mass, Or Rivlin, Guy Lev, Achiya Jerbi, Jonathan Herzig, Yufang Hou, Charles Jochim, Martin Gleize, Francesca Bonin, David Konopnicki

We present a novel system providing summaries for Computer Science publications.

A Study of BERT for Non-Factoid Question-Answering under Passage Length Constraints

no code implementations • 19 Aug 2019 • Yosi Mass, Haggai Roitman, Shai Erera, Or Rivlin, Bar Weiner, David Konopnicki

We study the use of BERT for non-factoid question-answering, focusing on the passage re-ranking task under varying passage lengths.

Learning-To-Rank Passage Re-Ranking +2

Fast End-to-End Wikification

no code implementations • 19 Aug 2019 • Ilya Shnayderman, Liat Ein-Dor, Yosi Mass, Alon Halfon, Benjamin Sznajder, Artem Spector, Yoav Katz, Dafna Sheinwald, Ranit Aharonov, Noam Slonim

Wikification of large corpora is beneficial for various NLP applications.

Learning Thematic Similarity Metric from Article Sections Using Triplet Networks

no code implementations • ACL 2018 • Liat Ein Dor, Yosi Mass, Alon Halfon, Elad Venezian, Ilya Shnayderman, Ranit Aharonov, Noam Slonim

We train a triplet network to embed sentences from the same section closer.

Clustering Collaborative Filtering +7

Semantic Relatedness of Wikipedia Concepts -- Benchmark Data and a Working Solution

no code implementations • LREC 2018 • Liat Ein Dor, Alon Halfon, Yoav Kantor, Ran Levy, Yosi Mass, Ruty Rinott, Eyal Shnarch, Noam Slonim

Entity Linking Learning-To-Rank

What did you Mention? A Large Scale Mention Detection Benchmark for Spoken and Written Text

no code implementations • 23 Jan 2018 • Yosi Mass, Lili Kotlerman, Shachar Mirkin, Elad Venezian, Gera Witzling, Noam Slonim

We describe a large, high-quality benchmark for the evaluation of Mention Detection tools.