---
title: "Yoav Goldberg — papers and cards"
description: "Yoav Goldberg: 19 paper cards in the Research library (2006–2023), with what each paper is about, the ideas Mova took from it, and the co-authors."
canonical: "https://research.elamur.ai/free/en/authors/yoav-goldberg/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/yoav-goldberg/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Yoav Goldberg

# Yoav Goldberg

19 paper cards in the Research library · 2006–2023

Yoav Goldberg wrote 19 of the papers Mova reads, in 2006–2023, most of them on [Dependency parsing](https://md.research.elamur.ai/free/en/topics/dependency-parsing/), [Part-of-speech tagging](https://md.research.elamur.ai/free/en/topics/part-of-speech-tagging/), [Treebanks](https://md.research.elamur.ai/free/en/topics/treebanks/); often with [Michael Elhadad](https://md.research.elamur.ai/free/en/authors/michael-elhadad/), [Reut Tsarfaty](https://md.research.elamur.ai/free/en/authors/reut-tsarfaty/), [Meni Adler](https://md.research.elamur.ai/free/en/authors/meni-adler/).

[OpenAlex](https://openalex.org/A5028476919) · [ORCID](https://orcid.org/0000-0002-6497-829X) · [**h-index 59**](https://openalex.org/authors/A5028476919) · [23282 citations](https://openalex.org/authors/A5028476919) · [401 works](https://openalex.org/works?filter=author.id:A5028476919) — openalex-snapshot, 2026-10-14

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

Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Yoav+Goldberg) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Yoav+Goldberg) · [dblp](https://dblp.org/search?q=Yoav+Goldberg) · [ACL Anthology](https://aclanthology.org/search/?q=Yoav+Goldberg) · [ORCID](https://orcid.org/orcid-search/search?searchQuery=Yoav+Goldberg)

Topics: [Dependency parsing](https://md.research.elamur.ai/free/en/topics/dependency-parsing/) 4 · [Part-of-speech tagging](https://md.research.elamur.ai/free/en/topics/part-of-speech-tagging/) 4 · [Treebanks](https://md.research.elamur.ai/free/en/topics/treebanks/) 2 · [Coreference resolution](https://md.research.elamur.ai/free/en/topics/coreference-resolution/) 1 · [Word sense disambiguation](https://md.research.elamur.ai/free/en/topics/word-sense-disambiguation/) 1 · [Universal Dependencies](https://md.research.elamur.ai/free/en/topics/universal-dependencies/) 1

## Ideas Mova took (2)

From the ideas ledger: an idea tried, kept or queued, or measured with no gain, and what it gave.

- **kept** — en/src/parse.rs feature template: add conjunct-symmetry features (lemma match, suffix match, capitalization match, UPOS match) for candidate conj attachments in the arc-standard perceptron; metric: conj Rel+Att F1 and LAS on EWT test. *([Improving a Strong Neural Parser with Conjunction-Specific…](https://md.research.elamur.ai/free/en/papers/aclbulk-2017-ficler-improving-strong-neural-parser-conjunction/) · conjunct-symmetry features, EWT dev our tags, 3 shuffles: 79.20 -> 79.37 (+0.17), gold tags 83.92 -> 84.38; commit 68f0f000b)*
- **measured, no gain** — Joint segmentation and parsing as a Mova measure: run tools/hbo in a mode where all segmentations from its tables stay as arcs, and compare its one-best pipeline with the lattice reading on a dev split of treebanks/hbo/ptnk. *([Joint Hebrew Segmentation and Parsing using a PCFGLA…](https://md.research.elamur.ai/free/en/papers/aclbulk-2011-goldberg-joint-hebrew-segmentation-parsing-pcfgla/) · one-best vs lattice reading measured on dev and Chronicles (hbo lattice/choose): no gain; unpointed dev 77.09 best 77.39 (tuned) but Chronicles -0.10 at that…)*

## Papers

1. **[LingMess: Linguistically Informed Multi Expert Scorers for Coreference Resolution](https://md.research.elamur.ai/free/en/papers/otmazgin-2023-lingmess-linguistically-informed-multi-expert/)** *(2023)* Neural coreference models score every mention pair with one shared function, although different pairs need different evidence.
2. **[HeQ: a Large and Diverse Hebrew Reading Comprehension Benchmark](https://md.research.elamur.ai/free/en/papers/findings-2023-cohen-heq-large-diverse-hebrew-reading/)** *(2023)* HeQ is an extractive question-answering benchmark in the SQuAD style for Modern Hebrew: 30,147 question–answer pairs from Hebrew Wikipedia and from the Geektime tech news site.
3. **[Large Scale Substitution-based Word Sense Induction](https://md.research.elamur.ai/free/en/papers/lex-2022-eyal-substitution-wsi/)** *(2022)* The paper induces word senses for every frequent word of a large corpus. For each corpus position a masked language model proposes the top five substitutes, and the substitute vectors are clustered per word type into senses. The result is a sense-tagged corpus in which each sense comes with indicative words. Storing…
4. **[Hebrew Psychological Lexicons](https://md.research.elamur.ai/free/en/papers/aclbulk-2021-shapira-hebrew-psychological-lexicons/)** *(2021)* The authors build a set of Hebrew psychological lexicons (2018–2021) for the analysis of psychotherapy sessions, because no validated Hebrew psycholinguistic lexicon existed.
5. **[Nakdan: Professional Hebrew Diacritizer](https://md.research.elamur.ai/free/en/papers/aclbulk-2020-shmidman-nakdan-professional-hebrew-diacritizer/)** *(2020)* Nakdan adds vowel points to undiacritized Hebrew, for modern, Rabbinic and poetic texts, through a web interface that lets an editor choose among the alternatives.
6. **[pyBART: Evidence-based Syntactic Transformations for IE](https://md.research.elamur.ai/free/en/papers/ud-2020-tiktinsky-pybart-evidence-based-syntactic-transformations/)** *(2020)* pyBART is an open-source Python library that converts English UD trees into a representation (BART) that makes event structure and many content-word relations explicit, going beyond Enhanced UD.
7. **[Breaking NLI Systems with Sentences that Require Simple Lexical Inferences](https://md.research.elamur.ai/free/en/papers/glockner-2018-breaking-nli-systems-sentences-that/)** *(2018)* SNLI-trained NLI systems look strong, but the authors show they fail on very simple lexical inferences. They take SNLI training premises and replace one word with a synonym, hypernym, co-hyponym or antonym (for example "champagne" for "wine" gives entailment, "saxophone" for "guitar" gives contradiction). The…
8. **[Improving a Strong Neural Parser with Conjunction-Specific Features](https://md.research.elamur.ai/free/en/papers/aclbulk-2017-ficler-improving-strong-neural-parser-conjunction/)** *(2017)* `1 idea kept` Parsers are accurate overall but attach the conj relation poorly, even in simple sentences. The authors add features to the BIST transition parser (arc-hybrid, with a Kiperwasser and Goldberg scorer) that measure the symmetry of the two conjuncts: whether their head words share a lemma, suffix, capitalization or…
9. **[Universal Dependencies v1: A Multilingual Treebank Collection](https://md.research.elamur.ai/free/en/papers/ud-2016-nivre-universal-dependencies-v1-multilingual-treebank/)** *(2016)* The paper is the reference for the first UD release. It sets out the design principles: dependency-based and lexicalist annotation, the recoverability principle (every syntactic word must map back to the raw text), content words as the backbone of the tree with function words as dependents, and a closed inventory of…
10. **[Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations](https://md.research.elamur.ai/free/en/papers/narrative-2016-kiperwasser-simple-accurate-dependency-parsing-bidirectional/)** *(2016)* The paper replaces hand-built feature templates with a BiLSTM over word and POS embeddings, trained jointly with the parser.
11. **[A Non-Monotonic Arc-Eager Transition System for Dependency Parsing](https://md.research.elamur.ai/free/en/papers/lingbulk-2013-honnibal-non-monotonic-arc-eager-transition/)** *(2013)* The paper relaxes the two deterministic constraints of the arc-eager transition system, which keep each step consistent with earlier head decisions.
12. **[Word Segmentation, Unknown-word Resolution, and Morphological Agreement in a Hebrew Parsing System](https://md.research.elamur.ai/free/en/papers/cl-2013-goldberg-word-segmentation-unknown-word-resolution/)** *(2013)* The paper builds a constituency parser for Modern Hebrew on the BerkeleyParser (PCFG with latent annotations) and extends it for a small treebank of 6,220 sentences.
13. **[Joint Hebrew Segmentation and Parsing using a PCFGLA Lattice Parser](https://md.research.elamur.ai/free/en/papers/aclbulk-2011-goldberg-joint-hebrew-segmentation-parsing-pcfgla/)** *(2011)* Hebrew function words are written attached to the next word, so one space-delimited token can have several segmentations, and a pipeline that segments first cannot use the syntax to choose.
14. **[Easy-First Dependency Parsing of Modern Hebrew](https://md.research.elamur.ai/free/en/papers/aclbulk-2010-goldberg-easy-first-dependency-parsing-modern/)** *(2010)* The authors apply their easy-first, non-directional dependency parser to the Hebrew dependency treebank, a small treebank of a language with rich morphology and free word order.
15. **[Hebrew Dependency Parsing: Initial Results](https://md.research.elamur.ai/free/en/papers/lingbulk-2009-goldberg-hebrew-dependency-parsing-initial-results/)** *(2009)* The authors derive a Hebrew dependency treebank (DepTB) from version 2 of the Hebrew constituency treebank.
16. **[Word-Based or Morpheme-Based? Annotation Strategies for Modern Hebrew Clitics](https://md.research.elamur.ai/free/en/papers/lingbulk-2008-tsarfaty-word-based-or-morpheme-based/)** *(2008)* The Modern Hebrew Treebank splits pronominal clitics on prepositions, accusative markers and possessive markers into separate leaves: one orthographic word becomes two or more nodes (morpheme-based, MB).
17. **[Tagging a Hebrew Corpus: the Case of Participles](https://md.research.elamur.ai/free/en/papers/lingbulk-2008-adler-tagging-hebrew-corpus-case-participles/)** *(2008)* The authors build a part-of-speech and morphology corpus of Modern Hebrew news (about 40M tokens, with a 200K-token sample tagged by hand).
18. **[SVM Model Tampering and Anchored Learning: A Case Study in Hebrew NP Chunking](https://md.research.elamur.ai/free/en/papers/aclbulk-2007-goldberg-svm-model-tampering-anchored-learning/)** *(2007)* The paper studies an SVM chunker for Hebrew Simple NPs (about 4,500 training sentences, 500 test, 27K chunks) and opens the trained model in two ways.
19. **[Noun Phrase Chunking in Hebrew: Influence of Lexical and Morphological Features](https://md.research.elamur.ai/free/en/papers/aclbulk-2006-goldberg-noun-phrase-chunking-hebrew-influence/)** *(2006)* The traditional base-NP definition (non-recursive NPs, as in English) gives tiny, one-word chunks on the Hebrew Treebank, so the authors define "Simple NPs" instead.

## Co-authors (68)

- [Michael Elhadad](https://md.research.elamur.ai/free/en/authors/michael-elhadad/) ×7
- [Reut Tsarfaty](https://md.research.elamur.ai/free/en/authors/reut-tsarfaty/) ×4
- [Meni Adler](https://md.research.elamur.ai/free/en/authors/meni-adler/) ×2
- Adam Nadaf
- Adar Paz
- Adi Singer
- Adva Maman
- [Amir DN Cohen](https://md.research.elamur.ai/free/en/authors/amir-dn-cohen/)
- Amna Baloum
- Arie Cattan
- Aryeh Tiktinsky
- [Avi Shmidman](https://md.research.elamur.ai/free/en/authors/avi-shmidman/)
- Badreya Sarsour
- Boaz Yanai
- Chen Dahbash
- [Christopher D. Manning](https://md.research.elamur.ai/free/en/authors/christopher-d-manning/)
- Coral Avigdor
- Dana Atzil-Slonim
- Dana Stolowicz-Melman
- Daniel Juravski
- [Daniel Zeman](https://md.research.elamur.ai/free/en/authors/daniel-zeman/)
- David Gabay
- Elinor Sarfati
- Eliyahu Kiperwasser
- Ephraim Mosenkis
- [Filip Ginter](https://md.research.elamur.ai/free/en/authors/filip-ginter/)
- Hilla Merhav
- Hillel Taub-Tabib
- Inbal Beka
- [Jan Hajič](https://md.research.elamur.ai/free/en/authors/jan-hajic/)
- Jany Gelfand Morgenshteyn
- Jessica Ficler
- [Joakim Nivre](https://md.research.elamur.ai/free/en/authors/joakim-nivre/)
- Liat Braun
- Lidar Gez
- Limor Dayan
- Maayan Revivo
- [Marie-Catherine de Marneffe](https://md.research.elamur.ai/free/en/authors/marie-catherine-de-marneffe/)
- [Mark Johnson](https://md.research.elamur.ai/free/en/authors/mark-johnson/)
- [Matan Eyal](https://md.research.elamur.ai/free/en/authors/matan-eyal/)
- Matan Kenigsbuch
- [Matthew Honnibal](https://md.research.elamur.ai/free/en/authors/matthew-honnibal/)
- Max Glockner
- Moran Baruch
- Moria Rubin
- [Moshe Koppel](https://md.research.elamur.ai/free/en/authors/moshe-koppel/)
- [Natalia Silveira](https://md.research.elamur.ai/free/en/authors/natalia-silveira/)
- Natalie Shapira
- Noa Bergwerk
- Noam Yosef
- Ori Shapira
- Rachel Mann
- Rahav Obercyger
- Roy Azoulay
- [Ryan McDonald](https://md.research.elamur.ai/free/en/authors/ryan-mcdonald/)
- [Sampo Pyysalo](https://md.research.elamur.ai/free/en/authors/sampo-pyysalo/)
- [Shaltiel Shmidman](https://md.research.elamur.ai/free/en/authors/shaltiel-shmidman/)
- Shon Otmazgin
- [Shoval Sadde](https://md.research.elamur.ai/free/en/authors/shoval-sadde/)
- Sivan Peled
- [Slav Petrov](https://md.research.elamur.ai/free/en/authors/slav-petrov/)
- Tal Alfi-Yogev
- Tal Naor
- Tamar Naim
- Tomer Alper
- Vered Shwartz
- Yael Netzer
- Yarden Elias

## More papers in the library (25)

Pages of the Research library: our summary, the ideas, references and who cites each.

- [Understanding Transformer Memorization Recall Through Idioms](https://md.research.elamur.ai/free/en/papers/haviv-2023-understanding-transformer-memorization-recall-through/) — Adi Haviv, Ido Cohen, Jacob Gidron, et al. · 2023
- [F-coref: Fast, Accurate and Easy to Use Coreference Resolution](https://md.research.elamur.ai/free/en/papers/otmazgin-2022-f-coref-fast-accurate-easy/) — Shon Otmazgin, Arie Cattan, Yoav Goldberg · 2022
- [Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space](https://md.research.elamur.ai/free/en/papers/geva-2022-transformer-feed-forward-layers-build/) — Mor Geva, Avi Caciularu, Kevin Ro Wang, et al. · 2022
- [Amnesic Probing: Behavioral Explanation with Amnesic Counterfactuals](https://md.research.elamur.ai/free/en/papers/elazar-2021-amnesic-probing-behavioral-explanation-amnesic/) — Yanai Elazar, Shauli Ravfogel, Alon Jacovi, et al. · 2021
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://md.research.elamur.ai/free/en/papers/ben-2021-zaken-bitfit-simple-parameter-efficient-fine/) — Elad Ben-Zaken, Shauli Ravfogel, Yoav Goldberg · 2021
- [Break It Down: A Question Understanding Benchmark](https://md.research.elamur.ai/free/en/papers/wolfson-2020-break-it-down-question-understanding/) — Tomer Wolfson, Mor Geva, Ankit Gupta, et al. · 2020
- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://md.research.elamur.ai/free/en/papers/ravfogel-2020-null-it-out-guarding-protected/) — Shauli Ravfogel, Yanai Elazar, Hila Gonen, et al. · 2020
- [Towards Faithfully Interpretable NLP Systems: How Should We Define and Evaluate Faithfulness?](https://md.research.elamur.ai/free/en/papers/jacovi-2020-faithfully-interpretable-nlp-systems-how/) — Alon Jacovi, Yoav Goldberg · 2020
- [Unsupervised Domain Clusters in Pretrained Language Models](https://md.research.elamur.ai/free/en/papers/aharoni-2020-unsupervised-domain-clusters-pretrained-language/) — Roee Aharoni, Yoav Goldberg · 2020
- [Assessing BERT's Syntactic Abilities](https://md.research.elamur.ai/free/en/papers/goldberg-2019-assessing-bert-s-syntactic-abilities/) — Yoav Goldberg · 2019
- [Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them](https://md.research.elamur.ai/free/en/papers/gonen-2019-lipstick-pig-debiasing-methods-cover/) — Hila Gonen, Yoav Goldberg · 2019
- [Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation](https://md.research.elamur.ai/free/en/papers/moryossef-2019-step-step-separating-planning-realization/) — Amit Moryossef, Yoav Goldberg, Ido Dagan · 2019
- [oLMpics -- On what Language Model Pre-training Captures](https://md.research.elamur.ai/free/en/papers/talmor-2019-olmpics-language-model-pre-training/) — Alon Talmor, Yanai Elazar, Yoav Goldberg, et al. · 2019
- [Adversarial Removal of Demographic Attributes from Text Data](https://md.research.elamur.ai/free/en/papers/elazar-2018-adversarial-removal-demographic-attributes-text/) — Yanai Elazar, Yoav Goldberg · 2018
- [Controlling Linguistic Style Aspects in Neural Language Generation](https://md.research.elamur.ai/free/en/papers/ficler-2017-controlling-linguistic-style-aspects-neural/) — Jessica Ficler, Yoav Goldberg · 2017
- [DyNet: The Dynamic Neural Network Toolkit](https://md.research.elamur.ai/free/en/papers/neubig-2017-dynet-dynamic-neural-network-toolkit/) — Graham Neubig, Chris Dyer, Yoav Goldberg, et al. · 2017
- [Morphological Inflection Generation with Hard Monotonic Attention](https://md.research.elamur.ai/free/en/papers/aharoni-2017-morphological-inflection-generation-hard-monotonic/) — Roee Aharoni, Yoav Goldberg · 2017
- [Towards String-To-Tree Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/aharoni-2017-string-tree-neural-machine-translation/) — Roee Aharoni, Yoav Goldberg · 2017
- [Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies](https://md.research.elamur.ai/free/en/papers/linzen-2016-assessing-ability-lstms-learn-syntax/) — Tal Linzen, Emmanuel Dupoux, Yoav Goldberg · 2016
- [Deep multi-task learning with low level tasks supervised at lower layers](https://md.research.elamur.ai/free/en/papers/sogaard-2016-deep-multi-task-learning-low/) — Anders Søgaard, Yoav Goldberg · 2016
- [Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks](https://md.research.elamur.ai/free/en/papers/adi-2016-fine-grained-analysis-sentence-embeddings/) — Yossi Adi, Einat Kermany, Yonatan Belinkov, et al. · 2016
- [Improving Hypernymy Detection with an Integrated Path-based and Distributional Method](https://md.research.elamur.ai/free/en/papers/shwartz-2016-improving-hypernymy-detection-integrated-path/) — Vered Shwartz, Yoav Goldberg, Ido Dagan · 2016
- [Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss](https://md.research.elamur.ai/free/en/papers/plank-2016-multilingual-part-speech-tagging-bidirectional/) — Barbara Plank, Anders Søgaard, Yoav Goldberg · 2016
- [Linguistic Regularities in Sparse and Explicit Word Representations](https://md.research.elamur.ai/free/en/papers/levy-2014-linguistic-regularities-sparse-explicit-word/) — Omer Levy, Yoav Goldberg · 2014
- [Overview of the SPMRL 2013 Shared Task: A Cross-Framework Evaluation of Parsing Morphologically Rich Languages](https://md.research.elamur.ai/free/en/papers/seddah-2013-overview-spmrl-2013-shared-task/) — Djamé Seddah, Reut Tsarfaty, Sandra Kübler, et al. · 2013