Explanipedia

Locus coeruleus tonic upregulation increases selectivity to inconspicuous auditory information in autistic compared to non-autistic individuals: a combined pupillometry and electroencephalography study Open

Nico Bast, Jumana Ahmad, Luke Mason, Emily J. H. Jones, Magdalena Matyjek , et al. · 2025

Background Sensory processing requires selectivity to salient sensory input. Many autistic individuals report different sensory processing, which has been associated with altered sensory selectivity. The locus-coeruleus norepinephrine (LC-…

Physically-constrained evapotranspiration models with machine learning parameterization outperform pure machine learning: Critical role of domain knowledge Open

Yeonuk Kim, Mónica García, T. Andrew Black, Mark Johnson · 2025

Physics-informed machine learning techniques have emerged to tackle challenges inherent in pure machine learning (ML) approaches. One such technique, the hybrid approach, has been introduced to estimate terrestrial evapotranspiration (ET),…

Mastering the Craft of Data Synthesis for CodeLLMs Open

Meng Chen, Philip Arthur, Q. Feng, Chuong D. Hoang, Yu-Heng Hong , et al. · 2025

Mastering the Craft of Data Synthesis for CodeLLMs Open

Meng Chen, Philip Arthur, Q. Feng, Chuong D. Hoang, Yu-Heng Hong , et al. · 2024

Large language models (LLMs) have shown impressive performance in \emph{code} understanding and generation, making coding tasks a key focus for researchers due to their practical applications and value as a testbed for LLM evaluation. Data…

A language-agnostic model of child language acquisition Open

Louis Mahon, Omri Abend, Uri Berger, Katherine Demuth, Mark Johnson , et al. · 2024

A Language-agnostic Model of Child Language Acquisition Open

Louis Mahon, Omri Abend, Uri Berger, Katherine Demuth, Mark Johnson , et al. · 2024

This work reimplements a recent semantic bootstrapping child-language acquisition model, which was originally designed for English, and trains it to learn a new language: Hebrew. The model learns from pairs of utterances and logical forms …

A Multilingual Model of Child Language Acquisition Open

Louis Mahon, Omri Abend, Uri Berger, Katherine Demuth, Mark Johnson , et al. · 2024

Sources of Hallucination by Large Language Models on Inference Tasks Open

Nick McKenna, Tianyi Li, Liang Cheng, Mohammad Javad Hosseini, Mark Johnson , et al. · 2023

Large Language Models (LLMs) are claimed to be capable of Natural Language Inference (NLI), necessary for applied tasks like question answering and summarization. We present a series of behavioral studies on several LLM families (LLaMA, GP…

Language Open

Michelle de Haan, Mark Johnson, Iroise Dumontheil · 2023

Language is a system for communicating with other people using sounds, symbols, and words to express a meaning, idea, or thought. This chapter starts with the question of whether language is “biologically special”. This issue refers to the…

Opening Doors to Recovery Open

Michael T. Compton, Mary E. Kelley, Simone Anderson, Samantha Ellis, JaShala Graves , et al. · 2023

Trial Registration: ClinicalTrials.gov identifier: NCT04612777.

Smoothing Entailment Graphs with Language Models Open

Nick McKenna, Tianyi Li, Mark Johnson, Mark Steedman · 2023

Nick McKenna, Tianyi Li, Mark Johnson, Mark Steedman. Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics…

Sources of Hallucination by Large Language Models on Inference Tasks Open

Nick McKenna, Tianyi Li, Liang Cheng, Mohammad Javad Hosseini, Mark Johnson , et al. · 2023

Large Language Models (LLMs) are claimed to be capable of Natural Language Inference (NLI), necessary for applied tasks like question answering and summarization. We present a series of behavioral studies on several LLM families (LLaMA, GP…

Impressions of the GDMC AI Settlement Generation Challenge in Minecraft Open

Christoph Salge, Claus Aranha, Adrian Brightmoore, Sean Butler, Rodrigo Canaan , et al. · 2022

The GDMC AI settlement generation challenge is a procedural content generation (PCG) competition about producing an algorithm that can create a settlement in the game Minecraft. In contrast to the majority of AI competitions, the GDMC entr…

Disfluency detection using a noisy channel model and deep neural language model Open

Paria Jamshid Lou, Mark Johnson · 2022

Although speech recognition technology has improved considerably in recent years, current systems still output simply a sequence of words without any useful information about the location of disfluencies. On the other hand, such informatio…

Speakers NMDC 2021 Plenary and Invited Speakers Open

Naomi J. Halas, Mark Johnson, Jessica E. Koehne · 2021

Incorporating Temporal Information in Entailment Graph Mining Open

Liane Guillou, Sander Bijl de Vroe, Mohammad Javad Hosseini, Mark Johnson, Mark Steedman · 2021

We present a novel method for injecting temporality into entailment graphs to address the problem of spurious entailments, which may arise from similar but temporally distinct events involving the same pair of entities. We focus on the spo…

Neural Rule-Execution Tracking Machine For Transformer-Based Text Generation Open

Yufei Wang, Can Xu, Huang Hu, Chongyang Tao, Stephen Wan , et al. · 2021

Sequence-to-Sequence (S2S) neural text generation models, especially the pre-trained ones (e.g., BART and T5), have exhibited compelling performance on various natural language generation tasks. However, the black-box nature of these model…

ECOL-R: Encouraging Copying in Novel Object Captioning with Reinforcement Learning Open

Yufei Wang, I. G. Wood, Stephen Wan, Mark Johnson · 2021

Novel Object Captioning is a zero-shot Image Captioning task requiring describing objects not seen in the training captions, but for which information is available from external object detectors. The key challenge is to select and describe…

Blindness to Modality Helps Entailment Graph Mining Open

Liane Guillou, Sander Bijl de Vroe, Mark Johnson, Mark Steedman · 2021

Understanding linguistic modality is widely seen as important for downstream tasks such as Question Answering and Knowledge Graph Population. Entailment Graph learning might also be expected to benefit from attention to modality. We build …

Mention Flags (MF): Constraining Transformer-based Text Generators Open

Yufei Wang, I. G. Wood, Stephen Wan, Mark Dras, Mark Johnson · 2021

Yufei Wang, Ian Wood, Stephen Wan, Mark Dras, Mark Johnson. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long …

ECOL-R: Encouraging Copying in Novel Object Captioning with Reinforcement Learning Open

Yufei Wang, I. G. Wood, Stephen Wan, Mark Johnson · 2021

Novel Object Captioning is a zero-shot Image Captioning task requiring describing objects not seen in the training captions, but for which information is available from external object detectors. The key challenge is to select and describe…

Open-Domain Contextual Link Prediction and its Complementarity with Entailment Graphs Open

Mohammad Javad Hosseini, Shay B. Cohen, Mark Johnson, Mark Steedman · 2021

An open-domain knowledge graph (KG) has entities as nodes and natural language relations as edges, and is constructed by extracting (subject, relation, object) triples from text. The task of open-domain link prediction is to infer missing …

Integrating Lexical Information into Entity Neighbourhood Representations for Relation Prediction Open

I. G. Wood, Mark Johnson, Stephen Wan · 2021

Relation prediction informed from a combination of text corpora and curated knowledge bases, combining knowledge graph completion with relation extraction, is a relatively little studied task. A system that can perform this task has the ab…

Detecting and Exorcising Statistical Demons from Language Models with Anti-Models of Negative Data Open

Michael Wick, Kate Silverstein, Jean-Baptiste Tristan, Adam Pocock, Mark Johnson · 2020

It's been said that "Language Models are Unsupervised Multitask Learners." Indeed, self-supervised language models trained on "positive" examples of English text generalize in desirable ways to many natural language tasks. But if such mode…

Animal Record Management Using an Embedded RFID-Based System Open

D. E. Bowker, Saleh Sbenaty, Mark Johnson · 2020

ANIMAL RECORD MANAGEMENT USING AN EMBEDDED RFID-BASED SYSTEMThe current paper describes the design and implementation of a Radio Frequency Identification(RFID) system that uses an embedded microchip in conjunction with an RFID reader for t…

Tablets For Timely Design Documentation Open

David G. Meyer, Mark Johnson, Cordelia Brown · 2020

NOTE: The first page of text has been automatically extracted and included below in lieu of an abstract Tablets for Timely Design Documentation Abstract One of the biggest challenges we have experienced in supervising digital systems senio…

Gene Sequence Inspired Vhdl Plagiarism Screening Open

Shawn Davidson, Mark Johnson, Douglas Eschbach, Curtis Watson · 2020

NOTE: The first page of text has been automatically extracted and included below in lieu of an abstract Session 3232 Gene Sequence Inspired Design Plagiarism Screening Mark C. Johnson, Curtis Watson, Shawn Davidson, Douglas Eschbach Purdue…

Saccade dysmetria indicates attenuated visual exploration in autism spectrum disorder Open

Nico Bast, Luke Mason, Christine M. Freitag, T. J. Smith, Ana Maria Portugal , et al. · 2020

The results leading to this publication have received funding from the Innovative Medicines Initiative 2 Joint Undertaking under grant agreement No 777394 for the project AIMS-2-TRIALS. This Joint Undertaking receives support from the Euro…

Incorporating Temporal Information in Entailment Graph Mining Open

Liane Guillou, Sander Bijl de Vroe, Mohammad Javad Hosseini, Mark Johnson, Mark Steedman · 2020

We present a novel method for injecting temporality into entailment graphs to address the problem of spurious entailments, which may arise from similar but temporally distinct events involving the same pair of entities. We focus on the spo…

Proceedings of the 5th Workshop on Representation Learning for NLP Open

Lin Chen, Danlu Chen, Yue Chen, Yu Cheng, Manuel R. Ciosici , et al. · 2020

Existing models for cross-domain named entity recognition (NER) rely on numerous unlabeled corpus or labeled NER training data in target domains.However, collecting data for low-resource target domains is not only expensive but also time-c…

Mark Johnson YOU? Author Swipe