Search Results - "Lambert, Mathias"

Hybrid data fidelity term approach for quantitative susceptibility mapping by Lambert, Mathias, Tejos, Cristian, Langkammer, Christian, Milovic, Carlos

“…Purpose Susceptibility maps are usually derived from local magnetic field estimations by minimizing a functional composed of a data consistency term and a…”
Get full text

DISCRIMINATIVE TRAINING OF DOCUMENT TRANSCRIPTION SYSTEM by Mathias, Lambert

Get full text

Streaking artifact suppression of quantitative susceptibility mapping reconstructions via L1‐norm data fidelity optimization (L1‐QSM) by Milovic, Carlos, Lambert, Mathias, Langkammer, Christian, Bredies, Kristian, Irarrazaval, Pablo, Tejos, Cristian

“…Purpose The presence of dipole‐inconsistent data due to substantial noise or artifacts causes streaking artifacts in quantitative susceptibility mapping (QSM)…”
Get full text

Toward a realistic in silico abdominal phantom for QSM by Silva, Javier, Milovic, Carlos, Lambert, Mathias, Montalba, Cristian, Arrieta, Cristóbal, Irarrazaval, Pablo, Uribe, Sergio, Tejos, Cristian

“…Purpose QSM outside the brain has recently gained interest, particularly in the abdominal region. However, the absence of reliable ground truths makes…”
Get full text

Contextual Slot Carryover for Disparate Schemas by Naik, Chetan, Gupta, Arpit, Ge, Hancheng, Mathias, Lambert, Sarikaya, Ruhi

“…In the slot-filling paradigm, where a user can refer back to slots in the context during a conversation, the goal of the contextual understanding system is to…”
Get full text

Pre-Training for Query Rewriting in a Spoken Language Understanding System by Chen, Zheng, Fan, Xing, Ling, Yuan

“…Query rewriting (QR) is an increasingly important technique to reduce customer friction caused by errors in a spoken language understanding pipeline, where the…”
Get full text

Hybrid Data Fidelity Term Approach for Quantitative Susceptibility Mapping by Lambert, Mathias G

“…Susceptibility maps are usually derived from local magnetic field estimations by minimizing a functional composed of a data consistency term and a…”
Get full text

Time Masking: Leveraging Temporal Information in Spoken Dialogue Systems by Conway, Rylan, Mathias, Lambert

“…In a spoken dialogue system, dialogue state tracker (DST) components track the state of the conversation by updating a distribution of values associated with…”
Get full text

Meta-training with Demonstration Retrieval for Efficient Few-shot Learning by Mueller, Aaron, Narang, Kanika, Mathias, Lambert, Wang, Qifan, Firooz, Hamed

“…Large language models show impressive results on few-shot NLP tasks. However, these models are memory and computation-intensive. Meta-training allows one to…”
Get full text

Leveraging External Knowledge for Out-Of-Vocabulary Entity Labeling by de Wynter, Adrian, Mathias, Lambert

“…Dealing with previously unseen slots is a challenging problem in a real-world multi-domain dialogue state tracking task. Other approaches rely on predefined…”
Get full text

Policy Compliance Detection via Expression Tree Inference by Kotonya, Neema, Vlachos, Andreas, Yazdani, Majid, Mathias, Lambert, Saeidi, Marzieh

“…Policy Compliance Detection (PCD) is a task we encounter when reasoning over texts, e.g. legal frameworks. Previous work to address PCD relies heavily on…”
Get full text

TimelineQA: A Benchmark for Question Answering over Timelines by Tan, Wang-Chiew, Dwivedi-Yu, Jane, Li, Yuliang, Mathias, Lambert, Saeidi, Marzieh, Yan, Jing Nathan, Halevy, Alon Y

“…Lifelogs are descriptions of experiences that a person had during their life. Lifelogs are created by fusing data from the multitude of digital services, such…”
Get full text

Logical Satisfiability of Counterfactuals for Faithful Explanations in NLI by Sia, Suzanna, Belyy, Anton, Almahairi, Amjad, Khabsa, Madian, Zettlemoyer, Luke, Mathias, Lambert

“…Evaluating an explanation's faithfulness is desired for many reasons such as trust, interpretability and diagnosing the sources of model's errors. In this…”
Get full text

PERFECT: Prompt-free and Efficient Few-shot Learning with Language Models by Mahabadi, Rabeeh Karimi, Zettlemoyer, Luke, Henderson, James, Saeidi, Marzieh, Mathias, Lambert, Stoyanov, Veselin, Yazdani, Majid

“…Current methods for few-shot fine-tuning of pretrained masked language models (PLMs) require carefully engineered prompts and verbalizers for each new task to…”
Get full text

Statistical machine translation and automatic speech recognition under uncertainty by Mathias, Lambert

“…Statistical modeling techniques have been applied successfully to natural language processing tasks such as automatic speech recognition (ASR) and statistical…”
Get full text

UNIREX: A Unified Learning Framework for Language Model Rationale Extraction by Chan, Aaron, Sanjabi, Maziar, Mathias, Lambert, Tan, Liang, Nie, Shaoliang, Peng, Xiaochang, Ren, Xiang, Firooz, Hamed

“…An extractive rationale explains a language model's (LM's) prediction on a given task instance by highlighting the text inputs that most influenced the…”
Get full text

Pre-Training for Query Rewriting in A Spoken Language Understanding System by Chen, Zheng, Fan, Xing, Ling, Yuan, Mathias, Lambert, Guo, Chenlei

“…Query rewriting (QR) is an increasingly important technique to reduce customer friction caused by errors in a spoken language understanding pipeline, where the…”
Get full text

ToKen: Task Decomposition and Knowledge Infusion for Few-Shot Hate Speech Detection by AlKhamissi, Badr, Ladhak, Faisal, Iyer, Srini, Stoyanov, Ves, Kozareva, Zornitsa, Li, Xian, Fung, Pascale, Mathias, Lambert, Celikyilmaz, Asli, Diab, Mona

“…In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 2109-2120, Abu Dhabi, United Arab Emirates. Association for…”
Get full text

Improving Long Distance Slot Carryover in Spoken Dialogue Systems by Chen, Tongfei, Naik, Chetan, He, Hua, Rastogi, Pushpendre, Mathias, Lambert

“…Tracking the state of the conversation is a central component in task-oriented spoken dialogue systems. One such approach for tracking the dialogue state is…”
Get full text

A dataset for resolving referring expressions in spoken dialogue via contextual query rewrites (CQR) by Regan, Michael, Rastogi, Pushpendre, Gupta, Arpit, Mathias, Lambert

“…We present Contextual Query Rewrite (CQR) a dataset for multi-domain task-oriented spoken dialogue systems that is an extension of the Stanford dialog corpus…”
Get full text