The 2020 Israel Seminar on Computational Linguistics

Computational Linguistics and Natural Language Processing are active research and development fields in Israel today, both in academia and industry. ISCOL is a venue for exchanging ideas, reporting on work in progress and established results, forming collaborations, and advancing connections between academia and industry. ISCOL is also a friendly stage for students for their first appearance in this community.

Program

• 9:30-10:00 Opening Remarks and short explanation of the format
• 10:00-11:00 Session 1
  • 10. Simple, Interpretable and Stable Method for Detecting Words with Usage Change across Corpora
    Hila Gonen (Bar-Ilan University)*; Ganesh Jawahar (INRIA); Djame Seddah (Inria); Yoav Goldberg ()
  • 14. Humor Detection in Product Question Answering Systems
    Yftah Ziser (Amazon); Elad Kravi (Amazon)*; David Carmel (Amazon)
  • 25. Language (Re)modelling: Towards Embodied Language Understanding
    Ronen Tamari (The Hebrew University of Jerusalem)*; Chen Shani (The Hebrew University of Jerusalem); Tom Hope ( Allen Institute for Artificial Intelligence); Miriam R. L. Petruck (International Computer Science Institute); Omri Abend (Hebrew University); Dafna Shahaf (The Hebrew University of Jerusalem)
  • 27. Multilingual Word Translation using Auxiliary Languages
    Hagai Taitelbaum (BIU / Google)*; Gal Chechik (Bar Ilan University); Jacob Goldberger (Bar-Ilan Univeristy )
  • 28. The Long-Tail of Language Models: Categorical vs. Continuous Prediction
    Shiran Dudy (OHSU)*; Steven Bedrick (OHSU)
  • 39. QADiscourse - Discourse Relations as QA Pairs: Representation, Crowdsourcing and Baselines
    Valentina Pyatkin (Bar-Ilan University)*; Ayal Klein (Bar Ilan University); Reut Tsarfaty (Bar-Ilan University); Ido Dagan (Bar-Ilan University)
  • 43. JCT at SemEval-2020 Task 1: Combined Semantic Vector Spaces Models for Unsupervised Lexical Semantic Change Detection
    Chaya Liebeskind (Jerusalem College of Technology)*; Efrat Amar (Jerusalem College of Technology)
  • 51. Generative approach to remove hypothesis-only biases
    Dimion Asael (Technion)*; Yonatan Belinkov (Technion)
  • 60. Gender Bias in the Wild
    Koren Lazar (The Hebrew University of Jerusalem)*; Gabriel Stanovsky (The Hebrew University of Jerusalem)
  • 63. Sentiment Analysis Multilingual Transfer Learning
    Dror Mughaz (lev academic center)*; Rafael Knoll (lev academic center); Yehonatan Ohayon (lev academic center)
  • 64. Discourse Parsing for Contentious, Non-Convergent Discussions
    Stepan Zakharov (Ben-Gurion University)*; Yifat Ben-David Kolikant (The Hebrew University); Oren Tsur (BGU)
  • 75. Improving Transformer Models by Reordering their Sublayers
    Ofir Press (University of Washington), Noah A. Smith (University of Washington & Allen Institute for AI), Omer Levy (Facebook AI Research)
• 11:00-12:00 Session 2
  • 1. When Bert Forgets How To POS: Amnesic Probing of Linguistic Properties and MLM Predictions
    Yanai Elazar (Bar-Ilan University)*; Shauli Ravfogel (Bar Ilan University); Alon Jacovi (Bar Ilan University); Yoav Goldberg ()
  • 2. Deep Contextualized Self-training for Low Resource Dependency Parsing
    Guy Rotman (Technion - Israel Institute of Technology)*; Roi Reichart (Technion)
  • 15. QANom: Question-Answer driven SRL for Nominalizations
    Ayal Klein (Bar Ilan University)*
  • 17. Unsupervised FAQ Retrieval with Question Generation and BERT
    Yosi Mass (IBM Research)*; Haggai Roitman (IBM Research Haifa); Boaz Carmeli (IBM Research); David Konopnicki (IBM Research - Haifa)
  • 29. WEC: Deriving a Large-scale Cross-document Event Coreference dataset from Wikipedia
    Alon Eirew (Intel AI Lab)*; Arie Cattan (Bar-Ilan University); Ido Dagan (University of Bar Ilan, Israel)
  • 30. Quantifying Cognitive Factors in Lexical Decline
    Ella Rabinovich ()*; David Francis (University of Toronto); Samir Farhan (University of Toronto); David Mortensen (Carnegie Mellon University); Suzanne Stevenson (University of Toronto)
  • 40. Unsupervised Dual-Cascade Learning with Pseudo-Feedback Distillation for Query-Focused Extractive Summarization
    Haggai Roitman (IBM Research - AI); Guy Feigenblat (IBM Research - Haifa)*; Doron Cohen (IBM Research - Haifa); Odellia Boni (IBM Research - Haifa); David Konopnicki (IBM Research - Haifa)
  • 44. Automatic Construction of Aramaic-Hebrew Translation Lexicon
    Chaya Liebeskind (Jerusalem College of Technology)*; Shmuel Liebeskind (Jerusalem College of Technology)
  • 52. Paraphrasing vs Coreferring: Two Sides of the Same Coin
    Yehudit K Meged (Bar Ilan University)*; Avi Caciularu (Bar-Ilan University); Vered Shwartz (Allen Institute of AI & University of Washington); Ido Dagan (University of Bar Ilan, Israel)
  • 53. A Novel Challenge Set for Hebrew Morphological Disambiguation and Diacritics Restoration
    Avi Shmidman (Bar Ilan University)*; Josh Guedalia (Dicta); Shaltiel Shmidman (Bar Ilan University and Dicta); Moshe Koppel (Bar Ilan University and Dicta); Reut Tsarfaty (Bar-Ilan University)
  • 65. HeMoji: Emoji Prediction System for Hebrew Text
    Daniel Juravski (BIU)*
  • 66. Document-Summary Span Alignment Dataset for Multi-Document Summarization
    Ori Ernst (Bar Ilan University)*; Ori Shapira (Bar-Ilan University); Ido Dagan (Bar-Ilan University)
• 12:00-13:00 Invited talk Omer Benjakob:

  Omer Benjakob, Haaretz.com's tech editor and Wikipedia reporter, will discuss how Wikipedia went from being the original fake news to the 'good cop' of the internet. In the talk, we will learn about how the truth went digital and how facts became political through the story of the age of information's encyclopedia.

• 13:00-14:00 Lunch break
• 14:00-15:00 Session 3
  • 3. Unsupervised Domain Clusters in Pretrained Language Models
    Roee Aharoni ()*
  • 11. It’s not Greek to mBERT: Inducing Word-Level Translations from Multilingual BERT
    Hila Gonen (Bar-Ilan University)*; Shauli Ravfogel (Bar Ilan University); Yanai Elazar (Bar-Ilan University); Yoav Goldberg ()
  • 18. pyBART: Evidence-based Syntactic Transformations for IE
    Aryeh Tiktinsky (AI2-Israel/BIU)*, Yoav Goldberg, Reut Tsarfaty
  • 19. Facts2Story: Controlling Text Generation by Key Facts
    Eyal Orbach (Bar Ilan University)*; Yoav Goldberg ()
  • 31. A Pointer Network Architecture for Joint Morphological Segmentation and Tagging
    Amit Seker (Bar Ilan University)*; Reut Tsarfaty (Bar-Ilan University)
  • 32. Automatically Extracting Challenge Sets for Non-local Phenomena in Neural Machine Translation
    Leshem Choshen (Hebrew University, Jerusalem)*; Omri Abend (Hebrew University)
  • 41. Corpus Wide Argument Mining - aWorking Solution
    Liat Ein-Dor (IBM Research AI); Eyal Shnarch (IBM Research AI)*; Lena Dankin (IBM Research AI); Alon Halfon (IBM Research AI); Benjamin Sznajder (IBM Research AI); Ariel Gera (IBM research AI); Carlos Alzate (IBM Research, Ireland); Martin Gleize (IBM Research); Leshem Choshen (IBM Research AI); Yufang Hou (IBM Research); Yonatan Bilu (Haifa Lab, IBM Research); Ranit Aharonov (Haifa Lab, IBM Research); Noam Slonim (IBM)
  • 45. Deep Learning for Period Classification of Historical Hebrew Texts
    Chaya Liebeskind (Jerusalem College of Technology)*; Shmuel Liebeskind (Jerusalem College of Technology)
  • 54. A Simple and Effective Model for Answering Multi-span Questions
    Elad Segal (Tel Aviv University)*; Avia Efrat (Tel Aviv University); Mor Shoham (Tel Aviv University); Jonathan Berant (Tel Aviv University/Allen Institute for AI); Amir Globerson (Tel Aviv University, Google)
  • 55. TAPAS: Weakly Supervised Table Parsing via Pre-training
    Jonathan Herzig (Tel-Aviv University)*
  • 67. It’s a Thin Line Between Love and Hate: Using the Echo in ModelingDynamics of Racist Online Communities
    Eyal Arviv (Ben Gurion University)*; Oren Tsur (BGU)
  • 68. Analyzing the Language and Discourse of the Babylonian Talmud
    Joshua Waxman (Stern College for Women, Yeshiva University)*, Adina Bruce (Yeshiva University)*, Lily Polonetsky (Yeshiva University)*, Noah Kalandar (Yeshiva University)*, Jonathan Crane (Yeshiva University)*, Meir Waxman()
• 15:00-16:00 Session 4
  • 5. Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection
    Shauli Ravfogel (Bar Ilan University)*; Yanai Elazar (Bar-Ilan University); Hila Gonen (Bar-Ilan University); Michael Twiton (Independent); Yoav Goldberg ()
  • 6. PERL: Pivot-based Domain Adaptation for Pre-trained Deep Contextualized Embedding Models
    Eyal Ben-David (Technion - Israel Institute of Technology)*; Roi Reichart (Technion)
  • 21. CausaLM: Causal Model Explanation Through Counterfactual Language Models
    Amir Feder (Technion)*; Nadav Oved (Technion - Israel Institute of Technology); Uri Shalit (Technion); Roi Reichart (Technion)
  • 33. A Large-Scale Dataset for Argument Quality Ranking: Construction and Analysis
    Shai Gretz (IBM Research)*; Roni Friedman (IBM Research); Edo Cohen-Karlik (IBM Research); Assaf Toledo (IBM Research); Dan Lahav (IBM Research); Ranit Aharonov (IBM Research); Noam Slonim (IBM)
  • 34. Linguistic Accommodation in Contentious Discussions
    Aviv Ben Haim (Ben Gurion University of the Negev)*; Oren Tsur (BGU)
  • 36. Neural Modeling for Named Entities and Morphology (NEMO^2)
    "Dan Bareket (Open University of Israel. Bar-Ilan University.)*; Reut Tsarfaty (Bar Ilan University
    )"
  • 46. Evaluating the Evaluation of Diversity in Natural Language Generation
    Guy Tevet (Tel Aviv University)*; Jonathan Berant (Tel Aviv University/Allen Institute for AI)
  • 56. Predicting Psychotherapy Outcome Using Machine-Learning Analysis: The MATRIX Initiative
    Mor Bar (Salvata Mental Health Center)*; Shlomo Mendlovic (Shalvata Mental Health Center)
  • 57. Towards Hate Speech Detection at Large via Deep Generative Modeling
    Tomer Wullach (University of Haifa)*; Amir Adler (MIT); Einat Minkov ()
  • 69. Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes
    Ofer Sabo (Bar-Ilan University)*; Yanai Elazar (Bar-Ilan University); Ido Dagan (Bar-Ilan University); Yoav Goldberg ()
  • 70. Exposing Shallow Heuristics of Relation Extraction Models with Challenge Data
    Shachar Rosenman (Bar-Ilan University)*, Alon Jacovi (Bar-Ilan University)*, Yoav Goldberg(Bar-Ilan University)*
• 16:00-17:00 Session 5
  • 7. Injecting Numerical Reasoning Skills into Language Models
    Mor Geva (Tel Aviv University)*; Ankit Gupta (Tel Aviv University); Jonathan Berant (Tel Aviv University/Allen Institute for AI)
  • 8. Out of the Echo Chamber: Detecting Countering Debate Speeches
    Matan Orbach (IBM Research)*; Yonatan Bilu (Haifa Lab, IBM Research); Assaf Toledo (IBM Research); Dan Lahav (IBM Research); Ranit Aharonov (Haifa Lab, IBM Research); Noam Slonim (IBM)
  • 22. A Taxonomy, Benchmark and Models for Identifying and Classifying Event-Based Modality
    "Shoval Sadde (BIU)*; Valentina Pyatkin (Bar Ilan University); Aynat Rubinstein (Hebrew University of Jerusalem); Paul Portner (Georgetown University); Reut Tsarfaty (Bar Ilan University
    )"
  • 23. CoRefi: A Crowd Sourcing Suite for Coreference Annotation
    Aaron Bornstein (Microsoft BIU NLP)*; Arie Cattan (Bar-Ilan University); Ido Dagan (Bar-Ilan University)
  • 35. Product Titles-to-Attributes As a Text-to-Text Task
    Gilad Fuchs (eBay)*, Yoni Acrich (eBay)
  • 47. GMAT: Global Memory Augmentation for Transformers
    Ankit Gupta (Tel Aviv University)*; Jonathan Berant (Tel Aviv University/Allen Institute for AI)
  • 48. Explaining Question Answering Models through Text Generation
    Veronica Latcinnik (TAU)*
  • 58. Real-Time Sign Language Detection using Human Pose Estimation
    Amit Moryossef (Bar-Ilan University, Google)*; Ioannis Tsochantaridis (Google); Roee Aharoni (Google); Sarah Ebling (University Of Zurich); Srini Narayanan (Google)
  • 71. From Arguments to Key Points: Towards Automatic Argument Summarization
    Roy Bar-Haim (IBM Research)*; Lilach Eden (IBM Research); Roni Friedman (IBM Research); Yoav Kantor (IBM Research); Dan Lahav (IBM Research); Noam Slonim (IBM)
  • 72. Politician’s short statements lying classifier based on linguistic aspects
    Ben Hagag (BIU)*; Reut Tsarfaty (Bar-Ilan University)
  • 74. Mask Please! Linguistic Landscape of COVID-19 in Israel
    Yael Netzer (Ben Gurion University | Haifa University | Dicta)*; Tal Baumel (Microsoft)
  • 76. Syntactic Search by Example
    Micah Shlain (Allen Institute for Artificial Intelligence); Hillel Taub-Tabib (Allen Institute for Artificial Intelligence)*; Shoval Sadde (Allen Institute for Artificial Intelligence); Yoav Goldberg ()
• 17:00-18:00 Session 6
  • 9. Break It Down: A Question Understanding Benchmark
    Tomer Wolfson (Tel Aviv University)*
  • 12. Pick a Fight or Bite your Tongue: Investigation of Gender Differences in Figurative Language Usage
    Ella Rabinovich ()*; Hila Gonen (Bar-Ilan University); Suzanne Stevenson (University of Toronto)
  • 20. Predicting In-game Actions from Interviews of NBA Players
    Nadav Oved (Technion - Israel Institute of Technology)*; Amir Feder (Technion); Roi Reichart (Technion)
  • 24. Web Table Retrieval using Multimodal Deep Learning
    Roee Shraga (Technion - Israel Institute of Technology)*; Haggai Roitman (IBM Research Haifa); Guy Feigenblat (IBM Research - Haifa)
  • 26. Streamlining Cross-Document Coreference Resolution: Evaluation and Modeling
    Arie Cattan (Bar-Ilan University)*; Alon Eirew (Intel AI Lab); Gabriel Stanovsky (Allen Institute for AI); Mandar Joshi (University of Washington); Ido Dagan (University of Bar Ilan, Israel)
  • 37. With Measured Words: Simple Sentence Selection for Black-Box Optimization of Sentence Compression Algorithms
    Yotam Shichel (Ben Gurion University)*; Meir Kalech (Ben Gurion University); Oren Tsur (BGU)
  • 38. Evaluating Interactive Summarization: an Expansion-Based Framework
    Ori Shapira (Bar-Ilan University)*
  • 49. Minimal Supervision for Morphological Inflection
    omer goldman (Tel Aviv University / Ber Ilan University)*; Reut Tsarfaty (Bar Ilan University
    )
  • 50. Invariant Risk Minimization for Natural Language Inference
    Yana Dranker (Technion)*; Yonatan Belinkov (Technion)
  • 61. Comparing the Attention Model with New pre/post Model
    Dror Mughaz (lev academic center)*; Ariel Eshel (lev academic center); Alon Elimelech (lev academic center)
  • 62. Improving Compositional Generalization in Semantic Parsing
    Inbar Oren (Tel Aviv University)*; Jonathan Herzig (Tel-Aviv University); Nitish Gupta (University of Pennsylvania); Matt Gardner (AI2); Jonathan Berant (Tel-Aviv University)
  • 73. Latent Compositional Representations Improve Systematic Generalization in Grounded Question Answering
    Ben Bogin (Tel-Aviv University)*; Sanjay Subramanian (Allen Institute for Artificial Intelligence); Matt Gardner (AI2); Jonathan Berant (Tel Aviv University/Allen Institute for AI)
• 18:00-18:15 Closing Remarks