Publications (13)
Supersense and Sensibility: Proxy Tasks for Semantic Annotation of Prepositions
Luke Gessler, Shira Wein, Nathan Schneider
Prepositional supersense annotation is time-consuming and requires expert training. Here, we present two sensible methods for obtaining prepositional supersense annotations by elic…
TAMS: Translation-Assisted Morphological Segmentation
Enora Rice, Ali Marashian, Luke Gessler +2
Canonical morphological segmentation is the process of analyzing words into the standard (aka underlying) forms of their constituent morphemes. This is a core task in language docu…
Syntactic Inductive Bias in Transformer Language Models: Especially Helpful for Low-Resource Languages?
Luke Gessler, Nathan Schneider
A line of work on Transformer-based language models such as BERT has attempted to use syntactic inductive bias to enhance the pretraining process, on the theory that building synta…
BERT Has Uncommon Sense: Similarity Ranking for Word Sense BERTology
Luke Gessler, Nathan Schneider
An important question concerning contextualized word embedding (CWE) models like BERT is how well they can represent different word senses, especially those in the long tail of unc…
A Summary of the First Workshop on Language Technology for Language Documentation and Revitalization
Graham Neubig, Shruti Rijhwani, Alexis Palmer +21
Despite recent advances in natural language processing and other language technology, the application of such technology to language documentation and conservation has been limited…
Supervised Grapheme-to-Phoneme Conversion of Orthographic Schwas in Hindi and Punjabi
Aryaman Arora, Luke Gessler, Nathan Schneider
Hindi grapheme-to-phoneme (G2P) conversion is mostly trivial, with one exception: whether a schwa represented in the orthography is pronounced or unpronounced (deleted). Previous w…
AMALGUM -- A Free, Balanced, Multilayer English Web Corpus
Luke Gessler, Siyao Peng, Yang Liu +3
We present a freely available, genre-balanced English web corpus totaling 4M tokens and featuring a large number of high-quality automatic annotation layers, including dependency t…
From Priest to Doctor: Domain Adaptation for Low-Resource Neural Machine Translation
Ali Marashian, Enora Rice, Luke Gessler +2
Many of the world's languages have insufficient data to train high-performing general neural machine translation (NMT) models, let alone domain-specific models, and often the only…
DisCoDisCo at the DISRPT2021 Shared Task: A System for Discourse Segmentation, Classification, and Connective Detection
Luke Gessler, Shabnam Behzad, Yang Janet Liu +3
This paper describes our submission to the DISRPT2021 Shared Task on Discourse Unit Segmentation, Connective Detection, and Relation Classification. Our system, called DisCoDisCo,…
PrOnto: Language Model Evaluations for 859 Languages
Luke Gessler
Evaluation datasets are critical resources for measuring the quality of pretrained language models. However, due to the high cost of dataset annotation, these resources are scarce…
MicroBERT: Effective Training of Low-resource Monolingual BERTs through Parameter Reduction and Multitask Learning
Luke Gessler, Amir Zeldes
Transformer language models (TLMs) are critical for most NLP tasks, but they are difficult to create for low-resource languages because of how much pretraining data they require. I…
eRST: A Signaled Graph Theory of Discourse Relations and Organization
Amir Zeldes, Tatsuya Aoyama, Yang Janet Liu +3
In this article we present Enhanced Rhetorical Structure Theory (eRST), a new theoretical framework for computational discourse analysis, based on an expansion of Rhetorical Struct…
GENTLE: A Genre-Diverse Multilayer Challenge Set for English NLP and Linguistic Evaluation
Tatsuya Aoyama, Shabnam Behzad, Luke Gessler +6
We present GENTLE, a new mixed-genre English challenge corpus totaling 17K tokens and consisting of 8 unusual text types for out-of domain evaluation: dictionary entries, esports c…