Idan Szpektor

2 paper cards in Mova's library · 2007–2023

Idan Szpektor wrote 2 of the papers Mova reads, in 2007–2023; often with Hila Noga, Iddo Greental, Ido Dagan.

The profile is the library's match of the name; two people with one name are not always told apart.

Papers

Multilingual Sequence-to-Sequence Models for Hebrew NLP (2023)
The authors argue that Hebrew encoder-only models (AlephBERT, AlephBERT-Gimmel, HeBERT) cannot emit morphemes or labels that are not in the input, so they need extra segment-then-tag components.
Semantic Inference at the Lexical-Syntactic Level for Textual Entailment Recognition (2007)
The paper proposes a proof system for textual entailment that works directly on dependency trees. Entailment rules, manual or acquired from WordNet and from DIRT-style paraphrase data, rewrite the text tree step by step towards the hypothesis, and a cost function measures the remaining distance when no full proof is…