CREDIT: Coarse-to-Fine Sequence Generation for Dialogue State Tracking

Chen, Zhi; Chen, Lu; Xu, Zihan; Zhao, Yuchen; Zhu, Su; Yu, Kai

doi:10.48550/arxiv.2009.10435

Cited by 7 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The similarity matrix is computed via either a fixed combination method or a K-means sharing method. • CREDIT-RL: CREDIT-RL [7] employs a structured representation to represent dialogue states and casts DST as a sequence generation problem. It also uses a reinforcement loss to fine-tune the model.…”

Section: Comparison Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Slot Self-Attentive Dialogue State Tracking

Manotumruksa

Zhang

et al. 2021

Preprint

View full text Add to dashboard Cite

An indispensable component in task-oriented dialogue systems is the dialogue state tracker, which keeps track of users' intentions in the course of conversation. The typical approach towards this goal is to fill in multiple pre-defined slots that are essential to complete the task. Although various dialogue state tracking methods have been proposed in recent years, most of them predict the value of each slot separately and fail to consider the correlations among slots. In this paper, we propose a slot self-attention mechanism that can learn the slot correlations automatically. Specifically, a slottoken attention is first utilized to obtain slot-specific features from the dialogue context. Then a stacked slot self-attention is applied on these features to learn the correlations among slots. We conduct comprehensive experiments on two multi-domain task-oriented dialogue datasets, including MultiWOZ 2.0 and MultiWOZ 2.1. The experimental results demonstrate that our approach achieves stateof-the-art performance on both datasets, verifying the necessity and effectiveness of taking slot correlations into consideration. CCS CONCEPTS• Computing methodologies → Natural language processing; Discourse, dialogue and pragmatics; Machine learning.

show abstract

Section: Comparison Methodsmentioning

confidence: 99%

“…Motivated by the advances in reading comprehension [4], DST has been further formulated as a machine reading comprehension problem [13,14,30,31]. Other techniques such as pointer networks [56] and reinforcement learning [7,8,23] have also been applied to DST.…”

Section: Related Workmentioning

confidence: 99%

Slot Self-Attentive Dialogue State Tracking

Manotumruksa

Zhang

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The multi-stage pipeline has been studied in many other text generation tasks. Some coarse-to-fine frameworks generate the intermediate sketches or the coarse text to help the final generation, such as dialogue state tracking (Chen et al, 2020), neural story generation (Fan et al, 2018), and extractive summarization (Xu and Lapata, 2020). More specifically, multi-stage summarization produces the salient in- formation step by step, such as the extract-andsummarize pipeline Subramanian et al, 2019;.…”

Section: Multi-stage Text Generationmentioning

confidence: 99%

Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents

Zhang¹,

Ni²,

Mao³

et al. 2021

Preprint

View full text Add to dashboard Cite

Text summarization is an essential task to help readers capture salient information from documents, news, interviews, and meetings. However, most state-of-the-art pretrained language models are unable to efficiently process long text commonly seen in the summarization problem domain. In this paper, we propose SUMM N , a simple, flexible, and effective multi-stage framework for input texts that are longer than the maximum context lengths of typical pretrained LMs. SUMM N first generates the coarse summary in multiple stages and then produces the final fine-grained summary based on them. The framework can process input text of arbitrary length by adjusting the number of stages, while keeping the LM context size fixed. Moreover, it can deal with both documents and dialogues, and can be used on top of any underlying backbone abstractive summarization model. Our experiments demonstrate that SUMM N significantly outperforms previous state-of-the-art methods by improving ROUGE scores on three long meeting summarization datasets AMI, ICSI, and QM-Sum, two long TV series datasets from Summ-Screen, and a newly proposed long document summarization dataset GovReport. Our data and code are available at https://github. com/chatc/Summ-N.

show abstract

“…Sequicity (Lei et al, 2018) is a two-step sequence to sequence model which first encodes the dialogue history and generates a belief span, and then generates a language response from the belief span. COMER (Ren et al, 2019) and CREDIT (Chen et al, 2020b) are hierarchical sequence-to-sequence models which represent the relationships between the intents, slots, and values in a hierarchical way, and employ a multistage decoder. Our proposed approach also uses a sequence-to-sequence model.…”

Section: Dialogue State Trackingmentioning

confidence: 99%

“…The methods regard DST as a classification and/or an extraction problem and independently infer the intent and slot value pairs for the current turn. (2) There are also some methods which view DST as a sequence to sequence problem (Lei et al, 2018;Ren et al, 2019;Chen et al, 2020b). The methods sequentially infer the intent and slot value pairs for the current turn on the basis of dialogue history and usually employ a hierarchical structure for the inference (decoding).…”

Section: Introductionmentioning

confidence: 99%

A Sequence-to-Sequence Approach to Dialogue State Tracking

Feng

Wang²,

Li³

2020

Preprint

View full text Add to dashboard Cite

This paper is concerned with dialogue state tracking (DST) in a task-oriented dialogue system. Significant progress has been achieved recently on the development of DST technologies. However, building a DST module that is scalable and effective is still a challenging issue. This paper proposes a new approach to dialogue state tracking, referred to as Seq2Seq-DU, which formalizes DST as a sequence-to-sequence problem. It employs two BERT-based encoders to respectively encode the utterances in the dialogue and the descriptions of schemas, an attender to calculate attentions between the utterance embeddings and the schema embeddings, and a decoder to generate pointers to represent the current state of dialogue. Seq2Seq-DU has the following advantages. It can jointly model the relations between intents, slots, and slot values; it can utilize rich language representations of utterances and schemas; it can effectively deal with categorical slots, noncategorical slots, and unseen schemas. In addition, Seq2Seq-DU can also be used in the NLU (natural language understanding) module of a dialogue system. Experimental results on benchmark datasets in different settings (SGD, MultiWOZ2.2, WOZ2.0, DSTC2, M2M, SNIPS, and ATIS) show that Seq2Seq-DU outperforms the existing methods.

show abstract

CREDIT: Coarse-to-Fine Sequence Generation for Dialogue State Tracking

Cited by 7 publications

References 24 publications

Slot Self-Attentive Dialogue State Tracking

Slot Self-Attentive Dialogue State Tracking

Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents

A Sequence-to-Sequence Approach to Dialogue State Tracking

Contact Info

Product

Resources

About