activity
20152022
most citedA Bi-model based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling

12 citations · 75 across the 23 of their papers we have counts for

collaborators

29 papers

cs.LG2022

Explainable Slot Type Attentions to Improve Joint Intent Detection and Slot Filling

Kalpa Gunaratna, Vijay Srinivasan, Akhila Yerukola +1

Joint intent detection and slot filling is a key research topic in natural language understanding (NLU). Existing joint intent and slot filling systems analyze and compute features…

cs.LG20228 cited

A Closer Look at Knowledge Distillation with Features, Logits, and Gradients

Yen-Chang Hsu, James Smith, Yilin Shen +2

Knowledge distillation (KD) is a substantial strategy for transferring learned knowledge from one neural network model to another. A vast number of methods have been developed for…

cs.CV202210 cited

MGA-VQA: Multi-Granularity Alignment for Visual Question Answering

Peixi Xiong, Yilin Shen, Hongxia Jin

Learning to answer visual questions is a challenging task since the multi-modal inputs are within two feature spaces. Moreover, reasoning in visual question answering requires the…

cs.CL20223 cited

Hyperparameter-free Continuous Learning for Domain Classification in Natural Language Understanding

Ting Hua, Yilin Shen, Changsheng Zhao +2

Domain classification is the fundamental task in natural language understanding (NLU), which often requires fast accommodation to new emerging domains. This constraint makes it imp…

cs.LG20213 cited

Using Neighborhood Context to Improve Information Extraction from Visual Documents Captured on Mobile Phones

Kalpa Gunaratna, Vijay Srinivasan, Sandeep Nama +1

Information Extraction from visual documents enables convenient and intelligent assistance to end users. We present a Neighborhood-based Information Extraction (NIE) approach that…

cs.CL2021

Enhancing the Generalization for Intent Classification and Out-of-Domain Detection in SLU

Yilin Shen, Yen-Chang Hsu, Avik Ray +1

Intent classification is a major task in spoken language understanding (SLU). Since most models are built with pre-collected in-domain (IND) training utterances, their ability to d…