Gina-Anne Levow

Also published as: Gina Levow


2024

pdf
TEII: Think, Explain, Interact and Iterate with Large Language Models to Solve Cross-lingual Emotion Detection
Long Cheng | Qihao Shao | Christine Zhao | Sheng Bi | Gina-Anne Levow
Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis

Cross-lingual emotion detection allows us to analyze global trends, public opinion, and social phenomena at scale. We participated in the Explainability of Cross-lingual Emotion Detection (EXALT) shared task, achieving an F1-score of 0.6046 on the evaluation set for the emotion detection sub-task. Our system outperformed the baseline by more than 0.16 F1-score absolute, and ranked second amongst competing systems. We conducted experiments using fine-tuning, zero-shot learning, and few-shot learning for Large Language Model (LLM)-based models as well as embedding-based BiLSTM and KNN for non-LLM-based techniques. Additionally, we introduced two novel methods: the Multi-Iteration Agentic Workflow and the Multi-Binary-Classifier Agentic Workflow. We found that LLM-based approaches provided good performance on multilingual emotion detection. Furthermore, ensembles combining all our experimented models yielded higher F1-scores than any single approach alone.

pdf
Effectiveness of Scalable Monolingual Data and Trigger Words Prompting on Cross-Lingual Emotion Detection Task
Yao-Fei Cheng | Jeongyeob Hong | Andrew Wang | Anita Silva | Gina-Anne Levow
Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis

This paper introduces our submitted systems for WASSA 2024 Shared Task 2: Cross-Lingual Emotion Detection. We implemented a BERT-based classifier and an in-context learning-based system. Our best-performing model, using English Chain of Thought prompts with trigger words, reached 3rd overall with an F1 score of 0.6015. Following the motivation of the shared task, we further analyzed the scalability and transferability of the monolingual English dataset on cross-lingual tasks. Our analysis demonstrates the importance of data quality over quantity. We also found that augmented multilingual data does not necessarily perform better than English monolingual data in cross-lingual tasks. We open-sourced the augmented data and source code of our system for future research.

pdf
WU_TLAXE at WASSA 2024 Explainability for Cross-Lingual Emotion in Tweets Shared Task 1: Emotion through Translation using TwHIN-BERT and GPT
Jon Davenport | Keren Ruditsky | Anna Batra | Yulha Lhawa | Gina-Anne Levow
Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis

This paper describes our task 1 submission for the WASSA 2024 shared task on Explainability for Cross-lingual Emotion in Tweets. Our task is to predict the correct emotion label (Anger, Sadness, Fear, Joy, Love, and Neutral) for a dataset of English, Dutch, French, Spanish, and Russian tweets, while training exclusively on English emotion labeled data, to reveal what kind of emotion detection information is transferable cross-language (Maladry et al., 2024). To that end, we used an ensemble of models with a GPT-4 decider. Our ensemble consisted of a few-shot GPT-4 prompt system and a TwHIN-BERT system fine-tuned on the EXALT and additional English data. We ranked 8th place under the name WU_TLAXE with an F1 Macro score of 0.573 on the test set. We also experimented with an English-only TwHIN-BERT model by translating the other languages into English for inference, which proved to be worse than the other models.

pdf
Assessing Pre-Built Speaker Recognition Models for Endangered Language Data
Gina-Anne Levow
Proceedings of the 3rd Annual Meeting of the Special Interest Group on Under-resourced Languages @ LREC-COLING 2024

Significant research has focused on speaker recognition, determining which speaker is speaking in a segment of audio. However, few experiments have investigated speaker recognition for very low-resource or endangered languages. Furthermore, speaker recognition has the potential to support language documentation and revitalization efforts, making recordings more accessible to researchers and communities. Since endangered language datasets are too small to build competitive speaker representations from scratch, we investigate the application of large-scale pre-built speaker recognition models to bridge this gap. This paper compares four speaker recognition models on six diverse endangered language data sets. Comparisons contrast three recent neural network-based x-vector models and an earlier baseline i-vector model. Experiments demonstrate significantly stronger performance for some of the studied models. Further analysis highlights differences in effectiveness tied to the lengths of test audio segments and amount of data used for speaker modeling.

pdf
Fine-Tuning ASR models for Very Low-Resource Languages: A Study on Mvskoke
Julia Mainzinger | Gina-Anne Levow
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)

Recent advancements in multilingual models for automatic speech recognition (ASR) have been able to achieve a high accuracy for languages with extremely limited resources. This study examines ASR modeling for the Mvskoke language, an indigenous language of America. The parameter efficiency of adapter training is contrasted with training entire models, and it is demonstrated how performance varies with different amounts of data. Additionally, the models are evaluated with trigram language model decoding, and the outputs are compared across different types of speech recordings. Results show that training an adapter is both parameter efficient and gives higher accuracy for a relatively small amount of data.

2023

pdf
Investigating Speaker Diarization of Endangered Language Data
Gina-Anne Levow
Proceedings of the Sixth Workshop on the Use of Computational Methods in the Study of Endangered Languages

2022

pdf
A Masked Segmental Language Model for Unsupervised Natural Language Segmentation
C.m. Downey | Fei Xia | Gina-Anne Levow | Shane Steinert-Threlkeld
Proceedings of the 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology

We introduce a Masked Segmental Language Model (MSLM) for joint language modeling and unsupervised segmentation. While near-perfect supervised methods have been developed for segmenting human-like linguistic units in resource-rich languages such as Chinese, many of the world’s languages are both morphologically complex, and have no large dataset of “gold” segmentations for supervised training. Segmental Language Models offer a unique approach by conducting unsupervised segmentation as the byproduct of a neural language modeling objective. However, current SLMs are limited in their scalability due to their recurrent architecture. We propose a new type of SLM for use in both unsupervised and lightly supervised segmentation tasks. The MSLM is built on a span-masking transformer architecture, harnessing a masked bidirectional modeling context and attention, as well as adding the potential for model scalability. In a series of experiments, our model outperforms the segmentation quality of recurrent SLMs on Chinese, and performs similarly to the recurrent model on English.

2021

pdf
Developing a Shared Task for Speech Processing on Endangered Languages
Gina-Anne Levow | Emily Ahn | Emily M. Bender
Proceedings of the 4th Workshop on the Use of Computational Methods in the Study of Endangered Languages Volume 1 (Papers)

pdf
Prosody: Models, Methods, and Applications
Nigel Ward | Gina-Anne Levow
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Tutorial Abstracts

Prosody is essential in human interaction, enabling people to show interest, establish rapport, efficiently convey nuances of attitude or intent, and so on. Some applications that exploit prosodic knowledge have recently shown superhuman performance, and in many respects our ability to effectively model prosody is rapidly advancing. This tutorial will overview the computational modeling of prosody, including recent advances and diverse actual and potential applications.

pdf bib
Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue
Haizhou Li | Gina-Anne Levow | Zhou Yu | Chitralekha Gupta | Berrak Sisman | Siqi Cai | David Vandyke | Nina Dethlefs | Yan Wu | Junyi Jessy Li
Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue

2018

pdf
Discovering Phonesthemes with Sparse Regularization
Nelson F. Liu | Gina-Anne Levow | Noah A. Smith
Proceedings of the Second Workshop on Subword/Character LEvel Models

We introduce a simple method for extracting non-arbitrary form-meaning representations from a collection of semantic vectors. We treat the problem as one of feature selection for a model trained to predict word vectors from subword features. We apply this model to the problem of automatically discovering phonesthemes, which are submorphemic sound clusters that appear in words with similar meaning. Many of our model-predicted phonesthemes overlap with those proposed in the linguistics literature, and we validate our approach with human judgments.

pdf
Automatic Identification of Basic-Level Categories
Chad Mills | Francis Bond | Gina-Anne Levow
Proceedings of the 9th Global Wordnet Conference

Basic-level categories have been shown to be both psychologically significant and useful in a wide range of practical applications. We build a rule-based system to identify basic-level categories in WordNet, achieving 77% accuracy on a test set derived from prior psychological experiments. With additional annotations we found our system also has low precision, in part due to the existence of many categories that do not fit into the three classes (superordinate, basic-level, and subordinate) relied on in basic-level category research.

2017

pdf
STREAMLInED Challenges: Aligning Research Interests with Shared Tasks
Gina-Anne Levow | Emily M. Bender | Patrick Littell | Kristen Howell | Shobhana Chelliah | Joshua Crowgey | Dan Garrette | Jeff Good | Sharon Hargus | David Inman | Michael Maxwell | Michael Tjalve | Fei Xia
Proceedings of the 2nd Workshop on the Use of Computational Methods in the Study of Endangered Languages

2015

pdf
Analysis of Dysarthric Speech using Distinctive Feature Recognition
Ka Ho Wong | Yu Ting Yeung | Patrick C. M. Wong | Gina-Anne Levow | Helen Meng
Proceedings of SLPAT 2015: 6th Workshop on Speech and Language Processing for Assistive Technologies

pdf
CMILLS: Adapting Semantic Role Labeling Features to Dependency Parsing
Chad Mills | Gina-Anne Levow
Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)

2014

pdf bib
Proceedings of the Third CIPS-SIGHAN Joint Conference on Chinese Language Processing
Le Sun | Chengqing Zong | Min Zhang | Gina-Anne Levow
Proceedings of the Third CIPS-SIGHAN Joint Conference on Chinese Language Processing

2012

pdf
Bridging Gaps for Spoken Dialog System Frameworks in Instructional Settings
Gina-Anne Levow
NAACL-HLT Workshop on Future directions and needs in the Spoken Dialog Community: Tools and Data (SDCTD 2012)

2011

pdf
Contrasting Multi-Lingual Prosodic Cues to Predict Verbal Feedback for Rapport
Siwei Wang | Gina-Anne Levow
Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies

2009

pdf
Investigating Pitch Accent Recognition in Non-native Speech
Gina-Anne Levow
Proceedings of the ACL-IJCNLP 2009 Conference Short Papers

2008

pdf
Studying Discourse and Dialogue with SIDGrid
Gina-Anne Levow
Proceedings of the Third Workshop on Issues in Teaching Computational Linguistics

pdf
Automatic Prosodic Labeling with Conditional Random Fields and Rich Acoustic Features
Gina-Anne Levow
Proceedings of the Third International Joint Conference on Natural Language Processing: Volume-I

2007

pdf
SIDGRID: A Framework for Distributed and Integrated Multimodal Annotation and Archiving and and Analysis
Gina-Anne Levow | Bennett Bertenthal | Mark Hereld | Sarah Kenny | David McNeill | Michael Papka | Sonjia Waxmonsky
Proceedings of the 8th SIGdial Workshop on Discourse and Dialogue

pdf
Hybrid Document Indexing with Spectral Embedding
Irina Matveeva | Gina-Anne Levow
Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Companion Volume, Short Papers

pdf bib
Proceedings of the Human Language Technology Conference of the NAACL, Companion Volume: Tutorial Abstracts
Marti Hearst | Gina-Anne Levow | James Allan
Proceedings of the Human Language Technology Conference of the NAACL, Companion Volume: Tutorial Abstracts

pdf
Topic Segmentation with Hybrid Document Indexing
Irina Matveeva | Gina-Anne Levow
Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)

2006

pdf
The Third International Chinese Language Processing Bakeoff: Word Segmentation and Named Entity Recognition
Gina-Anne Levow
Proceedings of the Fifth SIGHAN Workshop on Chinese Language Processing

pdf
Graph-based Generalized Latent Semantic Analysis for Document Representation
Irina Matveeva | Gina-Anne Levow
Proceedings of TextGraphs: the First Workshop on Graph Based Methods for Natural Language Processing

pdf
Unsupervised and Semi-supervised Learning of Tone and Pitch Accent
Gina-Anne Levow
Proceedings of the Human Language Technology Conference of the NAACL, Main Conference

pdf
Computing Term Translation Probabilities with Generalized Latent Semantic Analysis
Irina Matveeva | Gina-Anne Levow
Demonstrations

2005

pdf
Turn-taking in Mandarin Dialogue: Interactions of Tone and Intonation
Gina-Anne Levow
Proceedings of the Fourth SIGHAN Workshop on Chinese Language Processing

2004

pdf
Combining Prosodic and Text Features for Segmentation of Mandarin Broadcast News
Gina-Anne Levow
Proceedings of the Third SIGHAN Workshop on Chinese Language Processing

pdf
Prosodic Cues to Discourse Segment Boundaries in Human-Computer Dialogue
Gina-Anne Levow
Proceedings of the 5th SIGdial Workshop on Discourse and Dialogue at HLT-NAACL 2004

pdf
Assessing Prosodic and Text Features for Segmentation of Mandarin Broadcast News
Gina-Anne Levow
Proceedings of the Workshop on Interdisciplinary Approaches to Speech Indexing and Retrieval at HLT-NAACL 2004

pdf
Prosody-based Topic Segmentation for Mandarin Broadcast News
Gina-Anne Levow
Proceedings of HLT-NAACL 2004: Short Papers

2003

pdf
Issues in Pre- and Post-translation Document Expansion: Untranslatable Cognates and Missegmented Words
Gina-Anne Levow
Proceedings of the Sixth International Workshop on Information Retrieval with Asian Languages

pdf
Learning to Speak to a Spoken Language System: Vocabulary Convergence in Novice Users
Gina-Anne Levow
Proceedings of the Fourth SIGdial Workshop of Discourse and Dialogue

2001

pdf
Improved Cross-Language Retrieval using Backoff Translation
Philip Resnik | Douglas Oard | Gina Levow
Proceedings of the First International Conference on Human Language Technology Research

pdf
Mandarin-English Information: Investigating Translingual Speech Retrieval
Helen Meng | Berlin Chen | Sanjeev Khudanpur | Gina-Anne Levow | Wai-Kit Lo | Douglas Oard | Patrick Shone | Karen Tang | Hsin-Min Wang | Jianqiang Wang
Proceedings of the First International Conference on Human Language Technology Research

pdf
Rapidly Retargetable Interactive Translingual Retrieval
Gina-Anne Levow | Douglas W. Oard | Philip Resnik
Proceedings of the First International Conference on Human Language Technology Research

2000

pdf
Mandarin-English Information (MEI): Investigating Translingual Speech Retrieval
Helen Meng | Sanjeev Khudanpur | Gina Levow | Douglas W. Oard | Hsin-Min Wang
ANLP-NAACL 2000 Workshop: Embedded Machine Translation Systems

pdf
Chinese-English Semantic Resource Construction
Bonnie J. Dorr | Gina-Anne Levow | Dekang Lin | Scott Thomas
Proceedings of the Second International Conference on Language Resources and Evaluation (LREC’00)

pdf bib
Building a Chinese-English mapping between verb concepts for multilingual applications
Bonnie J. Dorr | Gina-Anne Levow | Dekang Lin
Proceedings of the Fourth Conference of the Association for Machine Translation in the Americas: Technical Papers

This paper addresses the problem of building conceptual resources for multilingual applications. We describe new techniques for large-scale construction of a Chinese-English lexicon for verbs, using thematic-role information to create links between Chinese and English conceptual information. We then present an approach to compensating for gaps in the existing resources. The resulting lexicon is used for multilingual applications such as machine translation and cross-language information retrieval.

1999

pdf
Modeling the language assessment process and result: Proposed architecture for automatic oral proficiency assessment
Gina-Anne Levow | Mari Broman Olsen
Computer Mediated Language Assessment and Evaluation in Natural Language Processing

1998

pdf
Characterizing and Recognizing Spoken Corrections in Human-Computer Dialogue
Gina-Anne Levow
COLING 1998 Volume 1: The 17th International Conference on Computational Linguistics

pdf
Characterizing and Recognizing Spoken Corrections in Human-Computer Dialogue
Gina-Anne Levow
36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics, Volume 1