Dialogue State Tracking

120 papers with code • 7 benchmarks • 11 datasets

Dialogue state tacking consists of determining at each turn of a dialogue the full representation of what the user wants at that point in the dialogue, which contains a goal constraint, a set of requested slots, and the user's dialogue act.

Libraries

Use these libraries to find Dialogue State Tracking models and implementations

Most implemented papers

Language Models are Unsupervised Multitask Learners

openai/gpt-2 Preprint 2019

Natural language processing tasks, such as question answering, machine translation, reading comprehension, and summarization, are typically approached with supervised learning on taskspecific datasets.

MultiWOZ 2.1: A Consolidated Multi-Domain Dialogue Dataset with State Corrections and State Tracking Baselines

budzianowski/multiwoz LREC 2020

To fix the noisy state annotations, we use crowdsourced workers to re-annotate state and utterances based on the original utterances in the dataset.

Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset

google-research-datasets/dstc8-schema-guided-dialogue 12 Sep 2019

In this work, we introduce the the Schema-Guided Dialogue (SGD) dataset, containing over 16k multi-domain conversations spanning 16 domains.

CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases

ryanzhumich/editsql IJCNLP 2019

We present CoSQL, a corpus for building cross-domain, general-purpose database (DB) querying dialogue systems.

Efficient Dialogue State Tracking by Selectively Overwriting Memory

clovaai/som-dst ACL 2020

This mechanism consists of two steps: (1) predicting state operation on each of the memory slots, and (2) overwriting the memory with new values, of which only a few are generated according to the predicted state operations.

MultiWOZ 2.3: A multi-domain task-oriented dialogue dataset enhanced with annotation corrections and co-reference annotation

lexmen318/MultiWOZ-coref 12 Oct 2020

In this paper, we introduce MultiWOZ 2. 3, in which we differentiate incorrect annotations in dialogue acts from dialogue states, identifying a lack of co-reference when publishing the updated dataset.

KLUE: Korean Language Understanding Evaluation

KLUE-benchmark/KLUE 20 May 2021

We introduce Korean Language Understanding Evaluation (KLUE) benchmark.

Counter-fitting Word Vectors to Linguistic Constraints

nmrksic/counter-fitting NAACL 2016

In this work, we present a novel counter-fitting method which injects antonymy and synonymy constraints into vector space representations in order to improve the vectors' capability for judging semantic similarity.

Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints

nmrksic/attract-repel 1 Jun 2017

We present Attract-Repel, an algorithm for improving the semantic quality of word vectors by injecting constraints extracted from lexical resources.