Towards Universal Dialogue State Tracking

Ren, Liliang; Xie, Kaige; Chen, Lu; Yu, Kai

doi:10.48550/arxiv.1810.09587

Cited by 5 publications

(8 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experiments here are not intend to get the best performance but to prove our POGD model can handle unseen values, so we only train 20 epochs to get results in Table 3. It is important to emphasize that our POGD can generalize to unseen values without using SLU module or delexicalization like previous works (Rastogi et al, 2017;Ren et al, 2018)…”

Section: Unseen Valuesmentioning

confidence: 95%

“…Rastogi et al (2017) generated a fix set of candidate values using a separate SLU module, so suffered from error accumulation. StateNet (Ren et al, 2018) reduced the dependence of ontology but no verification was done in their work.…”

Section: Related Workmentioning

confidence: 99%

“…WoZ 2.0 (%) Joint Acc. MultiWoZ 2.0 (%) Belief Tracking: CNN(Ramadan et al, 2018) 85.5 25.83 Neural Belief Tracker: NBT-DNN (Mrkšić et al, 2016) 84.4 / GLAD (Zhong et al, 2018) 88.1 35.57 GCE (Nouri and Hosseini-Asl, 2018) 88.5 35.58 GLAD + RC + FS (Sharma et al, 2019) 89.2 / SateNet (Ren et al, 2018) 88.9 / POGD (ours) 88.7 39.15 (Xu and Hu, 2018), we use the last occurrence of the reference value in the dialogue history, if a subsequence of an utterance in history has a Levenshtein distance less than 3 with the value, it will be treated as a successful match. Switcher's labels are generated the same time-matching is successful or not.…”

Section: Implementation Detailsmentioning

confidence: 99%

“…The generalization of new slots is rarely discussed. Recent approaches like NBT (Mrkšić et al, 2016) and PtrNet (Xu and Hu, 2018) those scalable approaches (Zhong et al, 2018;Ren et al, 2018;Rastogi et al, 2017;Nouri and Hosseini-Asl, 2018), they may generalize to a new slot by fine-tuning their models but no experiments were done in their works.…”

Section: New Slotsmentioning

confidence: 99%

See 3 more Smart Citations

Point or Generate Dialogue State Tracker

Song

2020

Preprint

View full text Add to dashboard Cite

Dialogue state tracking is a key part of a taskoriented dialogue system, which estimates the user's goal at each turn of the dialogue. In this paper, we propose the Point-Or-Generate Dialogue State Tracker (POGD). POGD solves the dialogue state tracking task in two perspectives: 1) point out explicitly expressed slot values from the user's utterance, and 2) generate implicitly expressed ones based on slot-specific contexts. It also shares parameters across all slots, which achieves knowledge sharing and gains scalability to largescale across-domain dialogues. Moreover, the training process of its submodules is formulated as a multi-task learning procedure to further promote its capability of generalization. Experiments show that POGD not only obtains state-of-the-art results on both WoZ 2.0 and MultiWoZ 2.0 datasets but also has good generalization on unseen values 1 and new slots.

show abstract

Section: Unseen Valuesmentioning

confidence: 95%

Section: Related Workmentioning

confidence: 99%

Section: Implementation Detailsmentioning

confidence: 99%

Section: New Slotsmentioning

confidence: 99%

See 2 more Smart Citations

Point or Generate Dialogue State Tracker

Song

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Such approaches perform very well on datasets which are defined over fairly small ontologies. Apply these methods to more complex datasets however reveals various limitations (Ren et al, 2018;Nouri and Hosseini-Asl, 2018). First, it is often difficult to obtain a complete ontology for a task.…”

Section: Introductionmentioning

confidence: 99%

TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking

Heck¹,

Niekerk²,

Lubis³

et al. 2020

Preprint

View full text Add to dashboard Cite

Task-oriented dialog systems rely on dialog state tracking (DST) to monitor the user's goal during the course of an interaction. Multidomain and open-vocabulary settings complicate the task considerably and demand scalable solutions. In this paper we present a new approach to DST which makes use of various copy mechanisms to fill slots with values. Our model has no need to maintain a list of candidate values. Instead, all values are extracted from the dialog context on-thefly. A slot is filled by one of three copy mechanisms: (1) Span prediction may extract values directly from the user input; (2) a value may be copied from a system inform memory that keeps track of the system's inform operations; (3) a value may be copied over from a different slot that is already contained in the dialog state to resolve coreferences within and across domains. Our approach combines the advantages of span-based slot filling methods with memory methods to avoid the use of value picklists altogether. We argue that our strategy simplifies the DST task while at the same time achieving state of the art performance on various popular evaluation sets including Mul-tiWOZ 2.1, where we achieve a joint goal accuracy beyond 55%.

show abstract

Long-term Control for Dialogue Generation: Methods and Evaluation

Ramakrishnan¹,

Narangodage²,

Schilman³

et al. 2022

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

Current approaches for controlling dialogue response generation are primarily focused on high-level attributes like style, sentiment, or topic. In this work, we focus on constrained long-term dialogue generation, which involves more fine-grained control and requires a given set of control words to appear in generated responses. This setting requires a model to not only consider the generation of these control words in the immediate context, but also produce utterances that will encourage the generation of the words at some time in the (possibly distant) future. We define the problem of constrained long-term control for dialogue generation, identify gaps in current methods for evaluation, and propose new metrics that better measure long-term control. We also propose a retrieval-augmented method that improves performance of long-term controlled generation via logit modification techniques. We show through experiments on three task-oriented dialogue datasets that our metrics better assess dialogue control relative to current alternatives and that our method outperforms state-of-theart constrained generation baselines. 1

show abstract

Towards Universal Dialogue State Tracking

Cited by 5 publications

References 19 publications

Point or Generate Dialogue State Tracker

Point or Generate Dialogue State Tracker

TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking

Long-term Control for Dialogue Generation: Methods and Evaluation

Contact Info

Product

Resources

About