Videoclip: Contrastive pre-training for zero-shot video-text understanding
We present VideoCLIP, a contrastive approach to pre-train a unified model for zero-shot
video and text understanding, without using any labels on downstream tasks. VideoCLIP …
video and text understanding, without using any labels on downstream tasks. VideoCLIP …
State-of-the-art generalisation research in NLP: a taxonomy and review
The ability to generalise well is one of the primary desiderata of natural language
processing (NLP). Yet, what'good generalisation'entails and how it should be evaluated is …
processing (NLP). Yet, what'good generalisation'entails and how it should be evaluated is …
Out-of-domain detection for natural language understanding in dialog systems
Natural Language Understanding (NLU) is a vital component of dialogue systems, and its
ability to detect Out-of-Domain (OOD) inputs is critical in practical applications, since the …
ability to detect Out-of-Domain (OOD) inputs is critical in practical applications, since the …
Out-of-domain detection for low-resource text classification tasks
Out-of-domain (OOD) detection for low-resource text classification is a realistic but
understudied task. The goal is to detect the OOD cases with limited in-domain (ID) training …
understudied task. The goal is to detect the OOD cases with limited in-domain (ID) training …
Policy optimization of dialogue management in spoken dialogue system for out-of-domain utterances
Y Xu, P Huang, J Tang, Q Huang… - … Conference on Asian …, 2016 - ieeexplore.ieee.org
This paper addresses the policy optimization of a dialogue management scheme based on
partially observable Markov decision processes (POMDP), which is designed for out-of …
partially observable Markov decision processes (POMDP), which is designed for out-of …
Intent determination and spoken utterance classification
As a special form of spoken language understanding (SLU), spoken utterance classification
(SUC) has found many practical applications, among which call routing or call type …
(SUC) has found many practical applications, among which call routing or call type …
Benchmarking out-of-distribution detection in visual question answering
When faced with an out-of-distribution (OOD) question or image, visual question answering
(VQA) systems may provide unreliable answers. If relied on by real users or secondary …
(VQA) systems may provide unreliable answers. If relied on by real users or secondary …
Out-of-domain detection based on generative adversarial network
The main goal of this paper is to develop out-of-domain (OOD) detection for dialog systems.
We propose to use only in-domain (IND) sentences to build a generative adversarial …
We propose to use only in-domain (IND) sentences to build a generative adversarial …
Neural sentence embedding using only in-domain sentences for out-of-domain sentence detection in dialog systems
To ensure satisfactory user experience, dialog systems must be able to determine whether
an input sentence is in-domain (ID) or out-of-domain (OOD). We assume that only ID …
an input sentence is in-domain (ID) or out-of-domain (OOD). We assume that only ID …
Joint learning of domain classification and out-of-domain detection with dynamic class weighting for satisficing false acceptance rates
JK Kim, YB Kim - arxiv preprint arxiv:1807.00072, 2018 - arxiv.org
In domain classification for spoken dialog systems, correct detection of out-of-domain (OOD)
utterances is crucial because it reduces confusion and unnecessary interaction costs …
utterances is crucial because it reduces confusion and unnecessary interaction costs …