SanjabiM. x 7

Références · 2022-10-14

bookCOFFEE: Counterfactual Fairness for Personalized Text Generation in Explainable Recommendation

… that sentiment analysis systems yield different sentiment scores for sentences containi...

WangY.C.SanjabiM.NieS.WangN.WangQ.

Références · 2022-06-28

bookUnirex: A unified learning framework for language model rationale extraction

… the sentiment analysis task. For task performance, Ftask is trained via gold label y* i...

SanjabiM.TanL.ChanA.MathiasL.

Références · 2022-05-25

bookEr-test: Evaluating explanation regularization methods for nlp models

… Functional Tests Figure 4 demonstrates the failure rates on functional tests (as listed...

LiuZ.SanjabiM.NieS.JoshiB.ChanA.

Références · 2022-01-01

bookEr-test: Evaluating explanation regularization methods for language models

… We observe (Table 2) the drop in performance (∆) for sentiment analysis and NLI when ...

LiuZ.SanjabiM.NieS.JoshiB.ChanA.

Références · 2022-01-01

bookDetection, disambiguation, re-ranking: autoregressive entity linking as a multi-task problem

We propose an autoregressive entity linking model, that is trained with two auxiliary tasks, and lea...

GuJ.SanjabiM.NieS.MriniK.WangS.

Références · 2021-01-01

bookMSD: Saliency-aware Knowledge Distillation for Multimodal Understanding

To reduce a model size but retain performance, we often rely on knowledge distillation (KD) which tr...

JinW.SanjabiM.NieS.TanL.RenX.

Références · 2021-01-01

bookModality-specific distillation

… The task is a binary classification problem, which is to detect hate speech in multimod...

JinW.SanjabiM.NieS.TanL.RenX.