72 citations · 289 across the 69 of their papers we have counts for
10 papers · 1 filter
Semantics-aware Attention Improves Neural Machine Translation
Aviv Slobodkin, Leshem Choshen, Omri Abend
The integration of syntactic structures into Transformer machine translation has shown positive results, but to our knowledge, no work has attempted to do so with semantic structur…
On Neurons Invariant to Sentence Structural Changes in Neural Machine Translation
Gal Patel, Leshem Choshen, Omri Abend
We present a methodology that explores how sentence structure is reflected in neural representations of machine translation systems. We demonstrate our model-agnostic approach with…
The Grammar-Learning Trajectories of Neural Language Models
Leshem Choshen, Guy Hacohen, Daphna Weinshall +1
The learning trajectories of linguistic phenomena in humans provide insight into linguistic representation, beyond what can be gleaned from inspecting the behavior of an adult spea…
ComSum: Commit Messages Summarization and Meaning Preservation
Leshem Choshen, Idan Amit
We present ComSum, a data set of 7 million commit messages for text summarization. When documenting commits, software code changes, both a message and its summary are posted. We ga…
Part of Speech and Universal Dependency effects on English Arabic Machine Translation
Ofek Rafaeli, Omri Abend, Leshem Choshen +1
In this research paper, I will elaborate on a method to evaluate machine translation models based on their performance on underlying syntactical phenomena between English and Arabi…
Mediators in Determining what Processing BERT Performs First
Aviv Slobodkin, Leshem Choshen, Omri Abend
Probing neural models for the ability to perform downstream tasks using their activation patterns is often used to localize what parts of the network specialize in performing what…
SERRANT: a syntactic classifier for English Grammatical Error Types
Leshem Choshen, Matanel Oren, Dmitry Nikolaev +1
SERRANT is a system and code for automatic classification of English grammatical errors that combines SErCl and ERRANT. SERRANT uses ERRANT's annotations when they are informative…
: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering
Or Honovich, Leshem Choshen, Roee Aharoni +3
Neural knowledge-grounded generative models for dialogue often produce content that is factually inconsistent with the knowledge they rely on, making them unreliable and limiting t…
GrASP: A Library for Extracting and Exploring Human-Interpretable Textual Patterns
Piyawat Lertvittayakumjorn, Leshem Choshen, Eyal Shnarch +1
Data exploration is an important step of every data science and machine learning project, including those involving textual data. We provide a novel language tool, in the form of a…
Enhancing the Transformer Decoder with Transition-based Syntax
Leshem Choshen, Omri Abend
Notwithstanding recent advances, syntactic generalization remains a challenge for text decoders. While some studies showed gains from incorporating source-side symbolic syntactic a…