Search Results for author:
Found 79 papers, 23 papers with code
AlephBERT: Language Model Pre-training and Evaluation from Sub-Word to Sentence Level
First, so far, Hebrew resources for training large language models are not of the same magnitude as their English counterparts.
(Un)solving Morphological Inflection: Lemma Overlap Artificially Inflates Models’ Performance
In the domain of Morphology, Inflection is a fundamental and important task that gained a lot of traction in recent years, mostly via SIGMORPHON’s shared-tasks. With average accuracy above 0. 9 over the scores of all languages, the task is considered mostly solved using relatively generic neural seq2seq models, even with little data provided. In this work, we propose to re-evaluate morphological inflection models by employing harder train-test splits that will challenge the generalization capacity of the models.
QADiscourse - Discourse Relations as QA Pairs: Representation, Crowdsourcing and Baselines
Discourse relations describe how two propositions relate to one another, and identifying them automatically is an integral part of natural language understanding.
Dyna-bAbI: unlocking bAbI’s potential with dynamic synthetic benchmarking
However, the main synthetic resource for story understanding, the bAbI benchmark, lacks such a systematic mechanism for controllable task generation.
Design Choices in Crowdsourcing Discourse Relation Annotations: The Effect of Worker Selection and Training
The current contribution studies the effect of worker selection and training on the agreement on implicit relation labels between workers and gold labels, for both the DC and the QA method.
Well-Defined Morphology is Sentence-Level Morphology
Morphological tasks have gained decent popularity within the NLP community in the recent years, with large multi-lingual datasets providing morphological analysis of words, either in or out of context.
Mitigating Hallucinations in Large Vision-Language Models (LVLMs) via Language-Contrastive Decoding (LCD)
Large Vision-Language Models (LVLMs) are an extension of Large Language Models (LLMs) that facilitate processing both image and text inputs, expanding AI capabilities.
NoviCode: Generating Programs from Natural Language Utterances by Novices
Current Text-to-Code models demonstrate impressive capabilities in generating executable code from natural language snippets.
Is It Really Long Context if All You Need Is Retrieval? Towards Genuinely Difficult Long Context NLP
By using a descriptive vocabulary and discussing the relevant properties of difficulty in long-context, we can implement more informed research in this area.
Into the Unknown: Generating Geospatial Descriptions for New Environments
However, performance substantially drops in new environments with no training data.
HeSum: a Novel Dataset for Abstractive Text Summarization in Hebrew
While large language models (LLMs) excel in various natural language tasks in English, their performance in lower-resourced languages like Hebrew, especially for generative tasks such as abstractive summarization, remains unclear.
Superlatives in Context: Modeling the Implicit Semantics of Superlatives
Semantically, superlatives perform a set comparison: something (or some things) has the min/max property out of a set.
Do Pretrained Contextual Language Models Distinguish between Hebrew Homograph Analyses?
We evaluate all existing models for contextualized Hebrew embeddings on a novel Hebrew homograph challenge sets that we deliver.
LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statements
In particular, while some models prove virtually unaffected by knowledge conflicts in affirmative and negative contexts, when faced with more semantically involved modal and conditional environments, they often fail to separate the text from their internal knowledge.
MRL Parsing Without Tears: The Case of Hebrew
Syntactic parsing remains a critical tool for relation extraction and information extraction, especially in resource-scarce languages where LLMs are lacking.
Unpacking Tokenization: Evaluating Text Compression and its Correlation with Model Performance
Despite it being the cornerstone of BPE, the most common tokenization algorithm, the importance of compression in the tokenization process is still unclear.
Breaking the Language Barrier: Can Direct Inference Outperform Pre-Translation in Multilingual LLM Applications?
Large language models hold significant promise in multilingual applications.
Where Do We Go from Here? Multi-scale Allocentric Relational Inference from Natural Spatial Descriptions
Current navigation studies concentrate on egocentric local descriptions (e. g., `it will be on your right') that require reasoning over the agent's local perception.
A Truly Joint Neural Architecture for Segmentation and Parsing
Contemporary multilingual dependency parsers can parse a diverse set of languages, but for Morphologically Rich Languages (MRLs), performance is attested to be lower than other languages.
Multilingual Instruction Tuning With Just a Pinch of Multilinguality
As instruction-tuned large language models (LLMs) gain global adoption, their ability to follow instructions in multiple languages becomes increasingly crucial.
Explicit Morphological Knowledge Improves Pre-training of Language Models for Hebrew
We investigate the hypothesis that incorporating explicit morphological knowledge in the pre-training phase can improve the performance of PLMs for MRLs.
Apollo: Zero-shot MultiModal Reasoning with Multiple Experts
On the well-known task of stylized image captioning, our experiments show that our approach outperforms semi-supervised state-of-the-art models, while being zero-shot and avoiding costly training, data collection, and prompt engineering.
CoheSentia: A Novel Benchmark of Incremental versus Holistic Assessment of Coherence in Generated Texts
Up until now, little work has been done on explicitly assessing the coherence of generated texts and analyzing the factors contributing to (in)coherence.
Is Probing All You Need? Indicator Tasks as an Alternative to Probing Embedding Spaces
The ability to identify and control different kinds of linguistic information encoded in vector representations of words has many use cases, especially for explainability and bias removal.
A Novel Computational and Modeling Foundation for Automatic Coherence Assessment
On two benchmarks for coherence scoring rated by humans, one containing 500 automatically-generated short stories and another containing 4k real-world texts, our experiments confirm that jointly training on the proposed tasks leads to better performance on each task compared with task-specific models, and to better performance on assessing coherence overall, compared with strong baselines.
Covering Uncommon Ground: Gap-Focused Question Generation for Answer Assessment
Human communication often involves information gaps between the interlocutors.
HeGeL: A Novel Dataset for Geo-Location from Hebrew Text
The task of textual geolocation - retrieving the coordinates of a place based on a free-form language description - calls for not only grounding but also natural language understanding and geospatial reasoning.
Morphological Inflection with Phonological Features
Recent years have brought great advances into solving morphological tasks, mostly due to powerful neural models applied to various tasks as (re)inflection and analysis.
Conjunct Resolution in the Face of Verbal Omissions
In this work we propose a conjunct resolution task that operates directly on the text and makes use of a split-and-rephrase paradigm in order to recover the missing elements in the coordination structure.
Simple Linguistic Inferences of Large Language Models (LLMs): Blind Spots and Blinds
We evaluate LLMs' language understanding capacities on simple inference tasks that most humans find trivial.
Design Choices for Crowdsourcing Implicit Discourse Relations: Revealing the Biases Introduced by Task Design
Disagreement in natural language annotation has mostly been studied from a perspective of biases introduced by the annotators and the annotation frameworks.
Multilingual Sequence-to-Sequence Models for Hebrew NLP
We demonstrate that by casting tasks in the Hebrew NLP pipeline as text-to-text tasks, we can leverage powerful multilingual, pretrained sequence-to-sequence models as mT5, eliminating the need for a specialized, morpheme-based, separately fine-tuned decoder.
Large Pre-Trained Models with Extra-Large Vocabularies: A Contrastive Analysis of Hebrew BERT Models and a New One to Outperform Them All
We perform a contrastive analysis of this model against all previous Hebrew PLMs (mBERT, heBERT, AlephBERT) and assess the effects of larger vocabularies on task performance.
Ranked #1 on
Named Entity Recognition (NER)
on NEMO-Corpus
Breakpoint Transformers for Modeling and Tracking Intermediate Beliefs
Can we teach natural language understanding models to track their beliefs through intermediate points in text?
UniMorph 4.0: Universal Morphology
The project comprises two major thrusts: a language-independent feature schema for rich morphological annotation and a type-level resource of annotated data in diverse languages realizing that schema.
Breaking Character: Are Subwords Good Enough for MRLs After All?
Large pretrained language models (PLMs) typically tokenize the input string into contiguous subwords before any pretraining or inference.
Neural Token Segmentation for High Token-Internal Complexity
Tokenizing raw texts into word units is an essential pre-processing step for critical tasks in the NLP pipeline such as tagging, parsing, named entity recognition, and more.
Morphological Reinflection with Multiple Arguments: An Extended Annotation schema and a Georgian Case Study
In recent years, a flurry of morphological datasets had emerged, most notably UniMorph, a multi-lingual repository of inflection tables.
Morphology Without Borders: Clause-Level Morphology
We use this dataset to derive 3 clause-level morphological tasks: inflection, reinflection and analysis.
Dyna-bAbI: unlocking bAbI's potential with dynamic synthetic benchmarking
However, the main synthetic resource for story understanding, the bAbI benchmark, lacks such a systematic mechanism for controllable task generation.
Text-based NP Enrichment
Understanding the relations between entities denoted by NPs in a text is a critical part of human-like natural language understanding.
Asking It All: Generating Contextualized Questions for any Semantic Role
We develop a two-stage model for this task, which first produces a context-independent question prototype for each role and then revises it to be contextually appropriate for the passage.
(Un)solving Morphological Inflection: Lemma Overlap Artificially Inflates Models' Performance
The effect is most significant for low-resourced languages with a drop as high as 95 points, but even high-resourced languages lose about 10 points on average.
Draw Me a Flower: Processing and Grounding Abstraction in Natural Language
Abstraction is a core tenet of human cognition and communication.
The Possible, the Plausible, and the Desirable: Event-Based Modality Detection for Language Processing
Modality is the linguistic ability to describe events with added information such as how desirable, plausible, or feasible they are.
Minimal Supervision for Morphological Inflection
Neural models for the various flavours of morphological inflection tasks have proven to be extremely accurate given ample labeled data -- data that may be slow and costly to obtain.
AlephBERT:A Hebrew Large Pre-Trained Language Model to Start-off your Hebrew NLP Application With
Second, there are no accepted tasks and benchmarks to evaluate the progress of Hebrew PLMs on.
A Pointer Network Architecture for Joint Morphological Segmentation and Tagging
Neural MD may be addressed as a simple pipeline, where segmentation is followed by sequence tagging, or as an end-to-end model, predicting morphemes from raw tokens.
The Extraordinary Failure of Complement Coercion Crowdsourcing
In this work, we follow known methodologies of collecting labeled data for the complement coercion phenomenon.
ZEST: Zero-shot Learning from Text Descriptions using Textual Similarity and Visual Summarization
Specifically, given birds' images with free-text descriptions of their species, we learn to classify images of previously-unseen species based on specie descriptions.
QADiscourse -- Discourse Relations as QA Pairs: Representation, Crowdsourcing and Baselines
Discourse relations describe how two propositions relate to one another, and identifying them automatically is an integral part of natural language understanding.
A Novel Challenge Set for Hebrew Morphological Disambiguation and Diacritics Restoration
One of the primary tasks of morphological parsers is the disambiguation of homographs.
Evaluating NLP Models via Contrast Sets
Unfortunately, when a dataset has systematic gaps (e. g., annotation artifacts), these evaluations are misleading: a model can learn simple decision rules that perform well on the test set but do not capture a dataset's intended capabilities.
Neural Modeling for Named Entities and Morphology (NEMO^2)
Named Entity Recognition (NER) is a fundamental NLP task, commonly formulated as classification over a sequence of tokens.
Getting the \#\#life out of living: How Adequate Are Word-Pieces for Modelling Complex Morphology?
Therefore, when using word-pieces in MRLs, we must consider that: (1) a linear segmentation into sub-word units might not capture the full morphological complexity of words; and (2) representations that leave morphological knowledge on sub-word units inaccessible might negatively affect performance.
pyBART: Evidence-based Syntactic Transformations for IE
We present pyBART, an easy-to-use open-source Python library for converting English UD trees either to Enhanced UD graphs or to our representation.
From SPMRL to NMRL: What Did We Learn (and Unlearn) in a Decade of Parsing Morphologically-Rich Languages (MRLs)?
It has been exactly a decade since the first establishment of SPMRL, a research initiative unifying multiple research efforts to address the peculiar challenges of Statistical Parsing for Morphologically-Rich Languages (MRLs). Here we reflect on parsing MRLs in that decade, highlight the solutions and lessons learned for the architectural, modeling and lexical challenges in the pre-neural era, and argue that similar challenges re-emerge in neural architectures for MRLs.
Evaluating Models' Local Decision Boundaries via Contrast Sets
Unfortunately, when a dataset has systematic gaps (e. g., annotation artifacts), these evaluations are misleading: a model can learn simple decision rules that perform well on the test set but do not capture a dataset's intended capabilities.
Ecological Semantics: Programming Environments for Situated Language Understanding
Large-scale natural language understanding (NLU) systems have made impressive progress: they can be applied flexibly across a variety of tasks, and employ minimal structural assumptions.
RUN through the Streets: A New Dataset and Baseline Models for Realistic Urban Navigation
Following navigation instructions in natural language requires a composition of language, action, and knowledge of the environment.
What's Wrong with Hebrew NLP? And How to Make it Right
For languages with simple morphology, such as English, automatic annotation pipelines such as spaCy or Stanford's CoreNLP successfully serve projects in academia and the industry.
Joint Transition-Based Models for Morpho-Syntactic Parsing: Parsing Strategies for MRLs and a Case Study from Modern Hebrew
In standard NLP pipelines, morphological analysis and disambiguation (MA{\&}D) precedes syntactic and semantic downstream tasks.
The Hebrew Universal Dependency Treebank: Past Present and Future
The Hebrew treebank (HTB), consisting of 6221 morpho-syntactically annotated newspaper sentences, has been the only resource for training and validating statistical parsers and taggers for Hebrew, for almost two decades now.
Universal Morpho-Syntactic Parsing and the Contribution of Lexica: Analyzing the ONLP Lab Submission to the CoNLL 2018 Shared Task
We present the contribution of the ONLP lab at the Open University of Israel to the UD shared task on multilingual parsing from raw text to Universal Dependencies.
Representations and Architectures in Neural Sentiment Analysis for Morphologically Rich Languages: A Case Study from Modern Hebrew
To empirically study these effects, we develop a new sentiment analysis benchmark for Hebrew, based on 12K social media comments, and provide two instances of these data: in token-based and morpheme-based settings.
Universal Joint Morph-Syntactic Processing: The Open University of Israel's Submission to The CoNLL 2017 Shared Task
Our parser requires a lattice as input, so we generate morphological analyses of surface tokens using a data-driven morphological analyzer that derives its lexicon from the UD training corpora, and we rely on UDPipe for sentence segmentation and surface-level tokenization.
Data-Driven Broad-Coverage Grammars for Opinionated Natural Language Generation (ONLG)
Opinionated Natural Language Generation (ONLG) is a new, challenging, task that aims to automatically generate human-like, subjective, responses to opinionated articles online.
Data-Driven Morphological Analysis and Disambiguation for Morphologically Rich Languages and Universal Dependencies
Parsing texts into universal dependencies (UD) in realistic scenarios requires infrastructure for the morphological analysis and disambiguation (MA{\&}D) of typologically different languages as a first tier.
Universal Dependencies v1: A Multilingual Treebank Collection
Cross-linguistically consistent annotation is necessary for sound comparative evaluation and cross-lingual learning experiments.
