Papers by Alexis Palmer
Predicting the Focus of Negation: Model and Error Analysis (2020.acl-main)
Copied to clipboard
| Challenge: | Experimental results show that a scope detector can predict the focus of negation . negation is a complex phenomenon present in all human languages . |
| Approach: | They propose to leverage a scope detector to introduce the scope of negation as an additional input to the neural network. |
| Outcome: | The proposed model obtains the best results to date, and analyzes errors depending on scope and context information. |
From Priest to Doctor: Domain Adaptation for Low-Resource Neural Machine Translation (2025.coling-main)
Copied to clipboard
| Challenge: | Existing data for low-resource languages are limited; the languages that could most benefit from domain adaptation (DA) are the ones left behind. |
| Approach: | They propose a realistic setting in which they aim to translate between a high-resource and a low-resourced language with limited parallel data, a bilingual dictionary, and c) a monolingual target-domain corpus in the high-rsource language. |
| Outcome: | The proposed methods are compared with a human evaluation of DALI and show that the most effective is the simplest. |
A Kind Introduction to Lexical and Grammatical Aspect, with a Survey of Computational Approaches (2023.eacl-main)
Copied to clipboard
| Challenge: | Lexical and grammatical aspect plays essential roles in semantic interpretation, but many systems do not address it systematically. |
| Approach: | They propose to model lexical and grammatical aspect using computational approaches . they argue that a good computational understanding of lexic and grammmatical aspects is needed . |
| Outcome: | The proposed models are based on the lexical and grammatical aspect of a situation, the authors argue . they argue that the models need to be able to handle and evaluate the aspect systematically . |
Neural Induction of Finite-State Transducers (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to construct finite-state transducers by hand are difficult and require domain knowledge and significant human effort. |
| Approach: | They propose a method for automatically constructing unweighted FSTs following the hidden state geometry learned by a recurrent neural network. |
| Outcome: | The proposed method outperforms classical transducer learning algorithms by up to 87% accuracy on held-out test sets. |
Boosting the Capabilities of Compact Models in Low-Data Contexts with Large Language Models and Retrieval-Augmented Generation (2025.coling-main)
Copied to clipboard
| Challenge: | Existing language models lack data and computation power, but they are extremely parameter-heavy and difficult to train. |
| Approach: | They propose a retrieval augmented generation framework backed by a large language model to correct the output of a smaller model for morphological glossing. |
| Outcome: | The proposed model is highly effective in data-scarce settings and offers a state-of-the-art for morphological glossing. |
Massively Multilingual Joint Segmentation and Glossing (2026.acl-long)
Copied to clipboard
Michael Ginn, Lindia Tjuatja, Enora Rice, Ali Marashian, Maria Valentini, Jasmine Xu, Graham Neubig, Alexis Palmer
| Challenge: | Existing models generate morpheme-level glosses but assign them to whole words without predicting the actual morphological boundaries, making them less interpretable and therefore untrustworthy to human annotators. |
| Approach: | They propose to use neural networks to predict interlinear glosses and morphological segmentation from raw text. |
| Outcome: | The proposed model outperforms GlossLM on glossing and beats open-source models on segmentation, glossing, and alignment. |
Building a Broad Infrastructure for Uniform Meaning Representations (2024.lrec-main)
Copied to clipboard
Julia Bonn, Matthew J. Buchholz, Jayeol Chun, Andrew Cowell, William Croft, Lukas Denk, Sijia Ge, Jan Hajič, Kenneth Lai, James H. Martin, Skatje Myers, Alexis Palmer, Martha Palmer, Claire Benet Post, James Pustejovsky, Kristine Stenzel, Haibo Sun, Zdeňka Urešová, Rosa Vallejos, Jens E. L. Van Gysel, Meagan Vigus, Nianwen Xue, Jin Zhao
| Challenge: | This paper reports the first release of the UMR data set for six languages . it includes annotations for six different languages that vary greatly in terms of their linguistic properties and resource availability. |
| Approach: | They report the first release of the UMR data set for six languages . they describe on-going efforts to enlarge the data set and extend it to other languages - including Navajo, Navájo, and Sanapaná . |
| Outcome: | The first release of the UMR data set includes annotations for six languages . the language dataset is available for free and can be extended to other languages if needed . |
It’s not a Non-Issue: Negation as a Source of Error in Machine Translation (2020.findings-emnlp)
Copied to clipboard
| Challenge: | In this study, we focus on negation, a universal, core property of human language that affects the semantics of an utterance. |
| Approach: | They focus on negation, a universal, core property of human language that affects semantics of an utterance. |
| Outcome: | The proposed method improves translation quality by 60% in some cases . the authors also provide a linguistically motivated analysis that directly explains the majority of the results. |
Can we teach language models to gloss endangered languages? (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Prior research has explored statistical and neural methods for automatically producing IGT. |
| Approach: | They propose to use in-context learning to generate interlinear glossed text . they propose to employ supervised learning to select examples to provide in-text . |
| Outcome: | The proposed methods beat standard transformer baselines, despite requiring no training at all. |
AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages (2022.acl-long)
Copied to clipboard
Abteen Ebrahimi, Manuel Mager, Arturo Oncevay, Vishrav Chaudhary, Luis Chiruzzo, Angela Fan, John Ortega, Ricardo Ramos, Annette Rios, Ivan Vladimir Meza Ruiz, Gustavo Giménez-Lugo, Elisabeth Mager, Graham Neubig, Alexis Palmer, Rolando Coto-Solano, Thang Vu, Katharina Kann
| Challenge: | Pretrained multilingual models can perform cross-lingual transfer in a zero-shot setting, even for unseen languages. |
| Approach: | They propose to extend XNLI to 10 indigenous languages of the Americas and test multiple zero-shot and translation-based approaches. |
| Outcome: | The proposed model can perform cross-lingual transfer in a zero-shot setting even for languages unseen during pretraining. |
OLEA: Tool and Infrastructure for Offensive Language Error Analysis in English (2023.eacl-demo)
Copied to clipboard
| Challenge: | State-of-the-art models for identifying offensive language fail to generalize over nuanced or implicit cases of offensive and hateful language. |
| Approach: | They propose an open-source Python library for error analysis in the context of offensive language detection. |
| Outcome: | OLEA provides tools for error analysis in the context of detecting offensive language in English. |
Interdisciplinary Research in Conversation: A Case Study in Computational Morphology for Language Documentation (2025.emnlp-main)
Copied to clipboard
| Challenge: | despite interest in language documentation, we still lack broadly usable tools that support workflows. |
| Approach: | They propose to integrate user-centered design principles into NLP to reshape the field. |
| Outcome: | The proposed model fails to meet core usability needs in real-world language documentation contexts. |
GlossLM: A Massively Multilingual Corpus and Pretrained Model for Interlinear Glossed Text (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing resources for standardized, easily accessible IGT data limit their applicability to linguistic research. |
| Approach: | They compile the largest existing corpus of interlinear glossed text data from a variety of sources and use it to generate annotated text. |
| Outcome: | The proposed model outperforms SOTA models on monolingual corpora by 6.6%. |
Contrast Sets for Stativity of English Verbs in Context (2022.coling-1)
Copied to clipboard
| Challenge: | Current methods for classifying verbs in context as dynamic or stative are limited to particular data sets. |
| Approach: | They apply contrast set methodology to classify verbs in context as dynamic or stative . they create nearly 300 contrastive pairs by perturbing test set instances just enough to change their labels . |
| Outcome: | The contrast set method is used to evaluate the performance of a model on a classifying task . the model performs worse on transformed examples than on human examples . |
Determining Event Durations: Models and Error Analysis (N18-2)
Copied to clipboard
| Challenge: | a crucial piece of information regarding events is their duration, a rarely mentioned attribute . core tasks such as temporal understanding and reasoning would benefit from knowing the expected duration of events. |
| Approach: | They introduce aspectual features that capture deeper linguistic information . they also experiment with neural networks to predict event durations . |
| Outcome: | The proposed models capture deeper linguistic information than previous work and provide useful clues. |
WikiPossessions: Possession Timeline Generation as an Evaluation Benchmark for Machine Reading Comprehension of Long Texts (2020.lrec-1)
Copied to clipboard
| Challenge: | a new corpus of articles is created for the task of temporally-oriented possession . the task is open-domain and can be used to track possession in other texts . |
| Approach: | They propose a new corpus for the task of temporally-oriented possession . they annotate Wikipedia articles for 90 different well-known artifacts . |
| Outcome: | The proposed task is based on annotated Wikipedia articles for 90 artifacts, including paintings, diamonds, and archaeological artifos. |
TAMS: Translation-Assisted Morphological Segmentation (2024.acl-long)
Copied to clipboard
| Challenge: | Canonical morphological segmentation is a key task in endangered language documentation . training data for canonical segmentation can be difficult, making it difficult to train high quality models. |
| Approach: | They propose a model that leverages translation data to speed up canonical segmentation . they propose to use translation data as an additional signal to leverage the data . |
| Outcome: | The proposed model outperforms baseline models in a super-low resource setting but yields mixed results on training splits with more data. |
Is linguistically-motivated data augmentation worth it? (2025.acl-long)
Copied to clipboard
| Challenge: | Data augmentation is a widely-used technique for addressing data scarcity. |
| Approach: | They compare linguistically-motivated and linguisticly-naive data augmentation strategies for two low-resource languages with different morphological properties. |
| Outcome: | The proposed methods produce synthetic data that follows all linguistic constraints, but they require linguistic expertise and are more difficult to implement. |
Understanding the Gap: an Analysis of Research Collaborations in NLP and Language Documentation (2025.findings-acl)
Copied to clipboard
| Challenge: | despite 20 years of NLP work, practical use of this work remains vanishingly scarce. |
| Approach: | They propose to use interviews and surveys to examine the lack of NLP adoption in LD . they find that linguists and language communities have little or no use of Nlp in their work . |
| Outcome: | a new study shows that linguists and language researchers are not using NLP in LD . the findings highlight the importance of misaligned professional incentives and LD software . |
Bootstrapping UMR Annotations for Arapaho from Language Documentation Resources (2024.lrec-main)
Copied to clipboard
| Challenge: | Uniform Meaning Representation (UMR) is a graph-based semantic labeling system . it is based on the AMR family and is designed to be uniformly applicable to typologically diverse languages. |
| Approach: | They propose methods for bootstrapping UMR annotations for a given language from existing resources and typical language documentation products. |
| Outcome: | The proposed method generates enough basic structure in UMR graphs to automate labeling to a significant extent. |