natural-language-processing-7

Goal-Oriented Dialog

3260 papers • 126 benchmarks • 313 datasets

Achieving a pre-defined goal through a dialog.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in goal-oriented-dialog-14

Trend

Dataset

Best Model

Actions

Kvret

Libraries

i

Use these libraries to find goal-oriented-dialog-14 models and implementations

Datasets

Permuted bAbI dialog task

Subtasks

User Simulation

Most implemented papers

Learning End-to-End Goal-Oriented Dialog

Antoine Bordes, J. Weston•Mon May 23 2016

It is shown that an end-to-end dialog system based on Memory Networks can reach promising, yet imperfect, performance and learn to perform non-trivial operations and be compared to a hand-crafted slot-filling baseline on data from the second Dialog State Tracking Challenge.

785

Content

0

Paper Graph

Sequential Attention-based Network for Noetic End-to-End Response Selection

Qian Chen, Wen Wang•Tue Jan 08 2019

This paper investigates a sequential matching model based only on chain sequence for multi-turn response selection, which outperforms all previous models, including state-of-the-art hierarchy-based models, and achieves new state of the art performances on two large-scale public multi- turn response selection benchmark datasets.

41 0

Paper Graph

SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Tracking

Hwaran Lee, Jinsik Lee, Tae-Yoon Kim•Sun Jun 30 2019

A new approach to universal and scalable belief tracker, called slot-utterance matching belief tracker (SUMBT), which learns the relations between domain-slot-types and slot-values appearing in utterances through attention mechanisms based on contextual semantic vectors.

172 0

Paper Graph

End-to-End Slot Alignment and Recognition for Cross-Lingual NLU

Weijia Xu, Batool Haider, Saab Mansour•Tue Mar 31 2020

This work proposes a novel end-to-end model that learns to align and predict slots in a multilingual NLU system and uses the corpus to explore various cross-lingual transfer methods focusing on the zero-shot setting and leveraging MT for language expansion.

166 0

Paper Graph

Zero-Shot Dialog Generation with Cross-Domain Latent Actions

M. Eskénazi, Tiancheng Zhao•Mon Apr 30 2018

Experimental results show that the proposed zero-shot dialog generation method is able to achieve superior performance in learning dialog models that can rapidly adapt their behavior to new domains and suggests promising future research.

77 0

Paper Graph

Query-Reduction Networks for Question Answering

Ali Farhadi, Minjoon Seo, Hannaneh Hajishirzi, Sewon Min•Mon Jun 13 2016

Query-Reduction Network (QRN), a variant of Recurrent Neural Network (RNN) that effectively handles both short-term and long-term sequential dependencies to reason over multiple facts, is proposed.

101 0

Paper Graph

Efficient Dialog Policy Learning via Positive Memory Retention

Volker Tresp, Rui Zhao•Mon Oct 01 2018

This paper describes an efficient policy gradient method using positive memory retention, which significantly increases the sample-efficiency and shows state-of-the-art performance in a real-word visual object discovery game.

10 0

Paper Graph

Personalization in Goal-Oriented Dialog

B. Faltings, Fei Mi, Chaitanya K. Joshi•Wed Jun 21 2017

This paper analyzes the shortcomings of an existing end-to-end dialog system based on Memory Networks and proposes modifications to the architecture which enable personalization, and investigates personalization in dialog as a multi-task learning problem.

106 0

Paper Graph

Answerer in Questioner's Mind: Information Theoretic Approach to Goal-Oriented Visual Dialog

Sang-Woo Lee, Byoung-Tak Zhang, Y. Heo•Sun Feb 11 2018

Answerer in Questioner's Mind (AQM) is proposed, a novel information theoretic algorithm for goal-oriented dialog that a questioner asks and infers based on an approximated probabilistic model of the answerer.

35 0

Paper Graph

NE-Table: A Neural key-value table for Named Entities

Jatin Ganhotra, L. Polymenakos, Janarthanan Rajendran, Satinder Singh, Mo Yu, Xiaoxiao Guo•Sat Apr 21 2018

This paper presents empirical evaluations on a structured Question-Answering task, three related Goal-Oriented dialog tasks, and a Reading-Comprehension task, which show that the proposed method can be effective in dealing with both in-vocabulary and OOV NEs.

0 0

Paper Graph

Adding a benchmark result helps the community track progress.