Informativeness

85 papers with code • 1 benchmarks • 1 datasets

This task has no description! Would you like to contribute one?

Datasets


Most implemented papers

Learning to Navigate for Fine-grained Classification

yangze0930/NTS-Net ECCV 2018

In consideration of intrinsic consistency between informativeness of the regions and their probability being ground-truth class, we design a novel training paradigm, which enables Navigator to detect most informative regions under the guidance from Teacher.

Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization

dreasysnail/converse_GAN NeurIPS 2018

Responses generated by neural conversational models tend to lack informativeness and diversity.

NRPA: Neural Recommendation with Personalized Attention

microsoft/recommenders 29 May 2019

In this paper we propose a neural recommendation approach with personalized attention to learn personalized representations of users and items from reviews.

Unsupervised Abstractive Meeting Summarization with Multi-Sentence Compression and Budgeted Submodular Maximization

dascim/acl2018_abssumm ACL 2018

We introduce a novel graph-based framework for abstractive meeting speech summarization that is fully unsupervised and does not rely on any annotations.

Response Generation by Context-aware Prototype Editing

MarkWuNLP/ResponseEdit 19 Jun 2018

Open domain response generation has achieved remarkable progress in recent years, but sometimes yields short and uninformative responses.

Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems

andy194673/nlg-sclstm-multiwoz EMNLP 2015

Natural language generation (NLG) is a critical component of spoken dialogue and it has a significant impact both on usability and perceived quality.

Prosody Modifications for Question-Answering in Voice-Only Settings

rmit-ir/clef2019-prosody 11 Jun 2018

Many popular form factors of digital assistants---such as Amazon Echo, Apple Homepod, or Google Home---enable the user to hold a conversation with these systems based only on the speech modality.

Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank

xialeiliu/RankIQA 17 Feb 2019

Our results show that networks trained to regress to the ground truth targets for labeled data and to simultaneously learn to rank unlabeled data obtain significantly better, state-of-the-art results for both IQA and crowd counting.

Pragmatically Informative Text Generation

sIncerass/prag_generation NAACL 2019

We improve the informativeness of models for conditional text generation using techniques from computational pragmatics.

Theory and Evaluation Metrics for Learning Disentangled Representations

clarken92/DisentanglementMetrics ICLR 2020

We make two theoretical contributions to disentanglement learning by (a) defining precise semantics of disentangled representations, and (b) establishing robust metrics for evaluation.