相关论文: LAF-Fabric: a data analysis tool for Linguistic An…

Machine translation between Arabic and Hebrew has so far been limited by a lack of parallel corpora, despite the political and cultural importance of this language pair. Previous work relied on manually-crafted grammars or pivoting via…

Large language models (LLMs) for table-based reasoning often struggle with large tables due to input length limits. We propose ATF (Adaptive Table Filtering Framework), a modular and question-aware filtering pipeline that prunes…

Current benchmarks for Hebrew Natural Language Processing (NLP) focus mainly on morpho-syntactic tasks, neglecting the semantic dimension of language understanding. To bridge this gap, we set out to deliver a Hebrew Machine Reading…

Large Language Models exhibit strong reasoning and semantic understanding capabilities but often hallucinate in domains that require expert knowledge, among which fabrications, the generation of factually incorrect yet fluent statements,…

To what extent can neural network models learn generalizations about language structure, and how do we find out what they have learned? We explore these questions by training neural models for a range of natural language processing tasks on…

We present a web-based system called ViS-\'A-ViS aiming to assist literary scholars in detecting repetitive patterns in an annotated textual corpus. Pattern detection is made possible using distant reading visualizations that highlight…

Hebrew is a Morphological rich language, making its modeling harder than simpler language. Recent developments such as Transformers in general and Bert in particular opened a path for Hebrew models that reach SOTA results, not falling short…

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. For many morphologically-rich languages (MRLs), similar…

We describe a generic framework for representing and reasoning with annotated Semantic Web data, a task becoming more important with the recent increased amount of inconsistent and non-reliable meta-data on the web. We formalise the…

The Linguistic Data Consortium (LDC) has developed hundreds of data corpora for natural language processing (NLP) research. Among these are a number of annotated treebank corpora for Arabic. Typically, these corpora consist of a single…

Technology has increasingly become an integral part of the Bible translation process. Over time, both the translation process and relevant technology have evolved greatly. More recently, the field of Natural Language Processing (NLP) has…

Large Pre-trained Language Models (PLMs) have become ubiquitous in the development of language understanding technology and lie at the heart of many artificial intelligence advances. While advances reported for English using PLMs are…

Before deploying a language model (LM) within a given domain, it is important to measure its tendency to generate factually incorrect information in that domain. Existing methods for factuality evaluation of LLM generation focus on facts…

This paper introduces the L-ReLF (Low-Resource Lexical Framework), a novel, reproducible methodology for creating high-quality, structured lexical datasets for underserved languages. The lack of standardized terminology, exemplified by…

This paper proposes a connection method \`a la Bibel for an exception-tolerant family of description logics (DLs). As for the language, we assume the DL $\mathcal{ALCH}$ extended with two typicality operators: one on (complex) concepts and…

Understanding how data moves, transforms, and persists, known as data flow, is fundamental to reasoning in procedural tasks. Despite their fluency in natural and programming languages, large language models (LLMs), although increasingly…

Evaluating the factuality of long-form generations from Large Language Models (LLMs) remains challenging due to efficiency bottlenecks and reliability concerns. Prior efforts attempt this by decomposing text into claims, searching for…

Research in Computational Linguistics is dependent on text corpora for training and testing new tools and methodologies. While there exists a plethora of annotated linguistic information, these corpora are often not interoperable without…

Graph algorithms can be expressed in terms of linear algebra. GraphBLAS is a library of low-level building blocks for such algorithms that targets algorithm developers. LAGraph builds on top of the GraphBLAS to target users of graph…

In this paper, we fill in an existing gap in resources available to the Hebrew NLP community by providing it with the largest so far pre-train dataset HeDC4, a state-of-the-art pre-trained language model HeRo for standard length inputs and…