activity
20162023
most citedProposition-Level Clustering for Multi-Document Summarization

2 citations · 4 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CL20231 cited

Peek Across: Improving Multi-Document Modeling via Cross-Document Question-Answering

Avi Caciularu, Matthew E. Peters, Jacob Goldberger +2

The integration of multi-document pre-training objectives into language models has resulted in remarkable improvements in multi-document downstream tasks. In this work, we propose…

cs.CL2023

Conformal Nucleus Sampling

Shauli Ravfogel, Yoav Goldberg, Jacob Goldberger

Language models generate text based on successively sampling the next word. A decoding procedure based on nucleus (top-) sampling chooses from the smallest possible set of words…

cs.CL2021

Long Context Question Answering via Supervised Contrastive Learning

Avi Caciularu, Ido Dagan, Jacob Goldberger +1

Long-context question answering (QA) tasks require reasoning over a long document or multiple documents. Addressing these tasks often benefits from identifying a set of evidence sp…

cs.CL20212 cited

Proposition-Level Clustering for Multi-Document Summarization

Ori Ernst, Avi Caciularu, Ori Shapira +4

Text clustering methods were traditionally incorporated into multi-document summarization (MDS) as a means for coping with considerable information repetition. Particularly, cluste…

cs.CL2016

Domain Adaptation For Formant Estimation Using Deep Learning

Yehoshua Dissen, Joseph Keshet, Jacob Goldberger +1

In this paper we present a domain adaptation technique for formant estimation using a deep network. We first train a deep learning network on a small read speech dataset. We then f…

cs.CL20161 cited

PMI Matrix Approximations with Applications to Neural Language Modeling

Oren Melamud, Ido Dagan, Jacob Goldberger

The negative sampling (NEG) objective function, used in word2vec, is a simplification of the Noise Contrastive Estimation (NCE) method. NEG was found to be highly effective in lear…