Papers by Lane Schwartz

7 papers
Morphology Matters: A Multilingual Language Modeling Analysis (2021.tacl-1)

Copied to clipboard

Challenge: Existing studies on inflectional morphology disagree on whether or not it makes languages harder to model.
Approach: They propose to use a corpus of 145 Bible translations in 92 languages to investigate whether inflectional morphology makes languages harder to model.
Outcome: The proposed model trains with linguistically motivated subword segmentation strategies and reduces the impact of morphology on language modeling.
Primum Non Nocere: Before working with Indigenous data, the ACL must confront ongoing colonialism (2022.acl-short)

Copied to clipboard

Challenge: aCL researchers must acknowledge that Indigenous languages are not merely low resource languages . authors propose that the ACL draft and adopt an ethical framework for NLP research involving Indigenous languages based on the legacy of colonialism .
Approach: They propose that the ACL draft and adopt an ethical framework for NLP researchers . they propose to draw on best practices drawn from the Indigenous studies literature .
Outcome: The proposed ethical framework is drawn from the Indigenous studies literature . it would be ethical for researchers to engage with Indigenous languages .
Community lexical access for an endangered polysynthetic language: An electronic dictionary for St. Lawrence Island Yupik (N19-4)

Copied to clipboard

Challenge: a new electronic dictionary for St. Lawrence Island Yupik is developed to facilitate language-learning on the island . the endangered language is spoken primarily on St. lisa's St.liss island, Alaska .
Approach: They propose a morphologically-aware electronic dictionary for St. Lawrence Island Yupik . the dictionary is set in an uncluttered interface and uses HTML, Javascript, and CSS .
Outcome: The proposed dictionary is set in an uncluttered interface and is available in English and in Yupik . it is based on the morphologically-aware version of the Badten et al. paper dictionary .
Depth-bounding is effective: Improvements and evaluation of unsupervised PCFG induction (D18-1)

Copied to clipboard

Challenge: Recent attempts to improve grammar induction systems by bounding complexity of the model have not been compared against unbounded induction models.
Approach: They propose to use a Bayesian induction inducer to limit the search space of the model and then sample trees with or without bounding.
Outcome: The proposed model produces trees more accurately than or competitively with state-of-the-art constituency grammar induction models.
A Morphological Analyzer for St. Lawrence Island / Central Siberian Yupik (L18-1)

Copied to clipboard

Challenge: St. Lawrence Island / Central Siberian Yupik is an endangered language . it exhibits pervasive agglutinative and polysynthetic properties .
Approach: They propose to implement a finite-state morphological analyzer for the endangered language . it cyclically interweaves morphology and phonology to account for the language's intricate morphophonological system.
Outcome: The proposed method cyclically interweaves morphology and phonology to account for the language's intricate morphophonological system.
Improved Finite-State Morphological Analysis for St. Lawrence Island Yupik Using Paradigm Function Morphology (2020.lrec-1)

Copied to clipboard

Challenge: St. Lawrence Island Yupik is an endangered polysynthetic language of the Bering Strait region . linguistic fieldwork observed substantial support within the Yupis for language revitalization .
Approach: They propose a finite-state morphological analyzer for the endangered Yupik language . they use the Paradigm Function Morphology theory of morphology to evaluate the results .
Outcome: The proposed morphological analyzer outperforms existing analyzers in accuracy and coverage rates across multiple datasets.
Unsupervised Learning of PCFGs with Normalizing Flow (P19-1)

Copied to clipboard

Challenge: Existing induction models unable to incorporate semantics and morphology into induction . current models lack a robust model for generating morphologically rich sentences .
Approach: They propose a PCFG inducer which uses context embeddings to generalize over rare, morphologically rich forms.
Outcome: The proposed model produces grammars with state-of-the-art accuracy on a variety of languages.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations