Damir Ćavar

Also published as: Damir Cavar


2024

pdf bib
The Typology of Ellipsis: A Corpus for Linguistic Analysis and Machine Learning Applications
Damir Cavar | Ludovic Mompelat | Muhammad Abdo
Proceedings of the 6th Workshop on Research in Computational Linguistic Typology and Multilingual NLP

State-of-the-art (SotA) Natural Language Processing (NLP) technology faces significant challenges with constructions that contain ellipses. Although theoretically well-documented and understood, there needs to be more sufficient cross-linguistic language resources to document, study, and ultimately engineer NLP solutions that can adequately provide analyses for ellipsis constructions. This article describes the typological data set on ellipsis that we created for currently seventeen languages. We demonstrate how SotA parsers based on a variety of syntactic frameworks fail to parse sentences with ellipsis, and in fact, probabilistic, neural, and Large Language Models (LLM) do so, too. We demonstrate experiments that focus on detecting sentences with ellipsis, predicting the position of elided elements, and predicting elided surface forms in the appropriate positions. We show that cross-linguistic variation of ellipsis-related phenomena has different consequences for the architecture of NLP systems.

2022

pdf bib
Event Sequencing Annotation with TIE-ML
Damir Cavar | Ali Aljubailan | Ludovic Mompelat | Yuna Won | Billy Dickson | Matthew Fort | Andrew Davis | Soyoung Kim
Proceedings of the 18th Joint ACL - ISO Workshop on Interoperable Semantic Annotation within LREC2022

TIE-ML (Temporal Information Event Markup Language) first proposed by Cavar et al. (2021) provides a radically simplified temporal annotation schema for event sequencing and clause level temporal properties even in complex sentences. TIE-ML facilitates rapid annotation of essential tense features at the clause level by labeling simple or periphrastic tense properties, as well as scope relations between clauses, and temporal interpretation at the sentence level. This paper presents the first annotation samples and empirical results. The application of the TIE-ML strategy on the sentences in the Penn Treebank (Marcus et al., 1993) and other non-English language data is discussed in detail. The motivation, insights, and future directions for TIE-ML are discussed, too. The aim is to develop a more efficient annotation strategy and a formalism for clause-level tense and aspect labeling, event sequencing, and tense scope relations that boosts the productivity of tense and event-level corpus annotation. The central goal is to facilitate the production of large data sets for machine learning and quantitative linguistic studies of intra- and cross-linguistic semantic properties of temporal and event logic.

2016

pdf bib
Endangered Language Documentation: Bootstrapping a Chatino Speech Corpus, Forced Aligner, ASR
Malgorzata Ćavar | Damir Ćavar | Hilaria Cruz
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)

This project approaches the problem of language documentation and revitalization from a rather untraditional angle. To improve and facilitate language documentation of endangered languages, we attempt to use corpus linguistic methods and speech and language technologies to reduce the time needed for transcription and annotation of audio and video language recordings. The paper demonstrates this approach on the example of the endangered and seriously under-resourced variety of Eastern Chatino (CTP). We show how initial speech corpora can be created that can facilitate the development of speech and language technologies for under-resourced languages by utilizing Forced Alignment tools to time align transcriptions. Time-aligned transcriptions can be used to train speech corpora and utilize automatic speech recognition tools for the transcription and annotation of untranscribed data. Speech technologies can be used to reduce the time and effort necessary for transcription and annotation of large collections of audio and video recordings in digital language archives, addressing the transcription bottleneck problem that most language archives and many under-documented languages are confronted with. This approach can increase the availability of language resources from low-resourced and endangered languages to speech and language technology research and development.

pdf bib
Global Open Resources and Information for Language and Linguistic Analysis (GORILLA)
Damir Cavar | Malgorzata Cavar | Lwin Moe
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)

The infrastructure Global Open Resources and Information for Language and Linguistic Analysis (GORILLA) was created as a resource that provides a bridge between disciplines such as documentary, theoretical, and corpus linguistics, speech and language technologies, and digital language archiving services. GORILLA is designed as an interface between digital language archive services and language data producers. It addresses various problems of common digital language archive infrastructures. At the same time it serves the speech and language technology communities by providing a platform to create and share speech and language data from low-resourced and endangered languages. It hosts an initial collection of language models for speech and natural language processing (NLP), and technologies or software tools for corpus creation and annotation. GORILLA is designed to address the Transcription Bottleneck in language documentation, and, at the same time to provide solutions to the general Language Resource Bottleneck in speech and language technologies. It does so by facilitating the cooperation between documentary and theoretical linguistics, and speech and language technologies research and development, in particular for low-resourced and endangered languages.

pdf bib
Generating a Yiddish Speech Corpus, Forced Aligner and Basic ASR System for the AHEYM Project
Malgorzata Ćavar | Damir Ćavar | Dov-Ber Kerler | Anya Quilitzsch
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)

To create automatic transcription and annotation tools for the AHEYM corpus of recorded interviews with Yiddish speakers in Eastern Europe we develop initial Yiddish language resources that are used for adaptations of speech and language technologies. Our project aims at the development of resources and technologies that can make the entire AHEYM corpus and other Yiddish resources more accessible to not only the community of Yiddish speakers or linguists with language expertise, but also historians and experts from other disciplines or the general public. In this paper we describe the rationale behind our approach, the procedures and methods, and challenges that are not specific to the AHEYM corpus, but apply to all documentary language data that is collected in the field. To the best of our knowledge, this is the first attempt to create a speech corpus and speech technologies for Yiddish. This is also the first attempt to work out speech and language technologies to transcribe and translate a large collection of Yiddish spoken language resources.

2014

pdf bib
Visualization of Language Relations and Families: MultiTree
Damir Cavar | Malgorzata Cavar
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)

MultiTree is an NFS-funded project collecting scholarly hypotheses about language relationships, and visualizing them on a web site in the form of trees or graphs. Two open online interfaces allow scholars, students, and the general public an easy access to search for language information or comparisons of competing hypotheses. One objective of the project was to facilitate research in historical linguistics. MultiTree has evolved to a much more powerful tool, it is not just a simple repository of scholarly information. In this paper we present the MultiTree interfaces and the impact of the project beyond the field of historical linguistics, including, among others, the use of standardized ISO language codes, and creating an interconnected database of language and dialect names, codes, publications, and authors. Further, we offer the dissemination of linguistic findings world-wide to both scholars and the general public, thus boosting the collaboration and accelerating the scientific exchange. We discuss also the ways MultiTree will develop beyond the time of the duration of the funding.

2009

pdf bib
On Bootstrapping of Linguistic Features for Bootstrapping Grammars
Damir Ćavar
Proceedings of the EACL 2009 Workshop on Computational Linguistic Aspects of Grammatical Inference

2004

pdf bib
On Statistical Parameter Setting
Damir Ćavar | Joshua Herring | Toshikazu Ikuta | Paul Rodrigues | Giancarlo Schrementi
Proceedings of the Workshop on Psycho-Computational Models of Human Language Acquisition