Matt Mulholland

About me 👋

I’m a staff software engineer at Lattice @ AI. From 2011 to 2024 I worked at Educational Testing Service as an engineer. I also have taught courses on applied NLP engineering and linguistic annotation at Montclair State University. My research interests include natural language and speech processing and machine learning, especially in relation to applications to automated scoring technology. My engineering interests include Python, generative AI, TypeScript, scikit-learn, transformers, MLOps generally, aws-cdk-lib, terraform, Docker, Conda, Python packaging, AWS (Bedrock, SageMaker, ECS, Lambda, S3), FastAPI, Java, Bash, Rust, etc.

I obtained a master’s degree in Applied Linguistics (with a certificate in Computational Linguistics) from Montclair State University in 2016 and a bachelor’s degree (double major in English and Linguistics) from University of Pennsylvania in 2008.

Aside from publishing in NLP/speech conferences (listed below), I also have served as a reviewer for NLP conferences such as ACL, NAACL, EMNLP, and COLING.

Courses Taught at Montclair State University

• APLN 590/LNGN 450: Special Topics in Applied Linguistics: Applied Natural Language Processing, Summer 2023
• APLN 581/LNGN 340: Linguistic Annotation, Spring 2022

GitHub Repositories I Contribute to As Core Developer

• skll: Wrapper around scikit-learn for running experiments via configuration files, etc.
• gridmap: Run Python functions on a grid engine cluster
• RSMTool: Rater Scoring Modeling Tool

Blog Posts

• Backyard Ice Rink - Building a backyard ice rink
• Fence Construction - Replacing the fence around the house

Research Collaborations

• Automated scoring of spontaneous speech from young learners of English using transformers. To be published in the proceedings of the 2021 SLT conference.
• Do face masks introduce bias in speech technologies? The case of automated scoring of speaking proficiency. To be published in the proceedings of the 2020 INTERSPEECH conference.
• Scoring Interactional Aspects of Human-Machine Dialog for Language Learning and Assessment using Text Features. Published in 2019 in the proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue.
• Application of an Automatic Plagiarism Detection System in a Large-scale Assessment of English Speaking Proficiency. Published in 2019 in the proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications.
• Neural Approaches to Automated Speech Scoring of Monologue and Dialogue Responses. Published in the proceedings of 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
• Toward Automated Content Feedback Generation for Non-native Spontaneous Speech. Published in 2019 in the proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications.
• Automated text scoring and real-time adjustable feedback: Supporting revision of scientific arguments involving uncertainty. Published in Science Education in 2019.
• Validation of Automated Scoring for a Formative Assessment that Employs Scientific Argumentation. Published in Educational Assessment in 2018.
• A Prompt-Aware Neural Network Approach to Content-Based Scoring of Non-Native Spontaneous Speech. Published in 2018 IEEE Spoken Language Technology Workshop (SLT).
• Word-Embedding based Content Features for Automated Oral Profiency Scoring. Published in the proceedings of the Third Workshop on Semantic Deep Learning in 2018.
• Improvements to an Automated Content Scoring System for Spoken CALL Responses: The ETS Submission to the Second Spoken CALL Shared Task. Published in the proceedings of the 2018 INTERSPEECH conference as part of the Spoken CALL shared task at the 2018 ISCA International Workshop on Speech and Language Technology in Education (SLaTE).
• Validation of Automated Scoring for a Formative Assessment that Employs Scientific Argumentation. Published in ETS Research Report Series in 2017.
• Using an Automated Content Scoring System for Spoken CALL Responses: The ETS submission for the Spoken CALL Challenge. Published in the proceedings of the 2017 INTERSPEECH as part of the Spoken CALL shared task at the 2017 ISCA International Workshop on Speech and Language Technology in Education (SLaTE).
• Performance of Automated Speech Scoring on Different Low-to-Medium-Entropy Item Types for Low-Proficiency English Learners. Published in ETS Research Report Series (Wiley Periodicals, Inc.) in 2017.
• Modeling Discourse Coherence for the Automated Scoring of Spontaneous Spoken Responses. Published in the proceedings of 2017 ISCA International Workshop on Speech and Language Technology in Education (SLaTE) and won the best paper award.
• Off-Topic Spoken Response Detection with Word Embeddings. Published in the proceedings of the 2017 INTERSPEECH conference.
• Off-Topic Spoken Response Detection Using Siamese Convolutional Neural Networks. Published in the proceedings of the 2017 INTERSPEECH conference.
• Bidirectional LSTM-RNN for Improving Automated Assessment of Non-Native Children’s Speech. Published in the proceedings of the 2017 INTERSPEECH conference.
• Reflective writing as a tool for increasing STEM motivation and retention – can AI help scale it up?. Published in the International Journal of Artificial Intelligence in Education in 2017.
• Automatic plagiarism detection for spoken responses in an assessment of English language proficiency. Published in the proceedings of 2016 IEEE Spoken Language Technology Workshop (SLT).
• Use of automated scoring to generate hypotheses regarding language-based DIF. Presented at AERA/NMCE in 2016 and published in the 2017 International Journal of Testing.
• A comparison of ASR and human errors for transcription of non-native spontaneous speech. Published in the proceedings of the 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
• Validation of the Use of Automated Scoring and Feedback in an Earth Science Assessment. Symposium presented at NERA in 2015.
• Utilizing Depth Sensors for Analyzing Multimodal Presentations: Hardware, Software and Toolkits. Published in the proceedings of the 2015 ACM on International Conference on Multimodal Interaction.
• Predicting grammaticality on an ordinal scale. Published in proceedings of ACL 2014.
• Suicidal Tendencies: The Automatic Classification of Suicidal and Non-Suicidal Lyricists Using NLP. Published in proceedings of IJCNLP 2013.
• Patterns of misspellings in L2 English – a view from the ETS Spelling Corpus. Presented at Learner Corpus Research Conference (LCR2013), Bergen, Norway, September 27-29, 2013.