Dialogue State Tracking with a Language Model using Schema-Driven Prompting

• URL: http://arxiv.org/abs/2109.07506v1
• Date: Wed, 15 Sep 2021 18:11:25 GMT
• Title: Dialogue State Tracking with a Language Model using Schema-Driven Prompting
• Authors: Chia-Hsuan Lee, Hao Cheng, Mari Ostendorf
• Abstract summary: We introduce a new variation of the language modeling approach that uses schema-driven prompting to provide task-aware history encoding. Our purely generative system achieves state-of-the-art performance on MultiWOZ 2.2 and achieves competitive performance on two other benchmarks: MultiWOZ 2.1 and M2M.
• Score: 18.83983018421701
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Task-oriented conversational systems often use dialogue state tracking to represent the user's intentions, which involves filling in values of pre-defined slots. Many approaches have been proposed, often using task-specific architectures with special-purpose classifiers. Recently, good results have been obtained using more general architectures based on pretrained language models. Here, we introduce a new variation of the language modeling approach that uses schema-driven prompting to provide task-aware history encoding that is used for both categorical and non-categorical slots. We further improve performance by augmenting the prompting with schema descriptions, a naturally occurring source of in-domain knowledge. Our purely generative system achieves state-of-the-art performance on MultiWOZ 2.2 and achieves competitive performance on two other benchmarks: MultiWOZ 2.1 and M2M. The data and code will be available at https://github.com/chiahsuan156/DST-as-Prompting.

Related papers

• Less is More: Making Smaller Language Models Competent Subgraph Retrievers for Multi-hop KGQA [51.3033125256716]
  We model the subgraph retrieval task as a conditional generation task handled by small language models. Our base generative subgraph retrieval model, consisting of only 220M parameters, competitive retrieval performance compared to state-of-the-art models. Our largest 3B model, when plugged with an LLM reader, sets new SOTA end-to-end performance on both the WebQSP and CWQ benchmarks.
  arXiv  Detail & Related papers  (2024-10-08T15:22:36Z)
• ChatterBox: Multi-round Multimodal Referring and Grounding [108.9673313949746]
  We present a new benchmark and an efficient vision-language model for this purpose. The proposed model, named ChatterBox, utilizes a two-branch architecture to collaboratively handle vision and language tasks. Experiments show that ChatterBox outperforms existing models in MRG both quantitatively and qualitatively.
  arXiv  Detail & Related papers  (2024-01-24T09:02:00Z)
• Automated Few-shot Classification with Instruction-Finetuned Language Models [76.69064714392165]
  We show that AuT-Few outperforms state-of-the-art few-shot learning methods. We also show that AuT-Few is the best ranking method across datasets on the RAFT few-shot benchmark.
  arXiv  Detail & Related papers  (2023-05-21T21:50:27Z)
• DiSTRICT: Dialogue State Tracking with Retriever Driven In-Context Tuning [7.5700317050237365]
  We propose DiSTRICT, a generalizable in-context tuning approach for Dialogue State Tracking (DST) DSTRICT retrieves highly relevant training examples for a given dialogue to fine-tune the model without any hand-crafted templates. Experiments with the MultiWOZ benchmark datasets show that DiSTRICT outperforms existing approaches in various zero-shot and few-shot settings.
  arXiv  Detail & Related papers  (2022-12-06T09:40:15Z)
• Multi-Modal Few-Shot Object Detection with Meta-Learning-Based Cross-Modal Prompting [77.69172089359606]
  We study multi-modal few-shot object detection (FSOD) in this paper, using both few-shot visual examples and class semantic information for detection. Our approach is motivated by the high-level conceptual similarity of (metric-based) meta-learning and prompt-based learning. We comprehensively evaluate the proposed multi-modal FSOD models on multiple few-shot object detection benchmarks, achieving promising results.
  arXiv  Detail & Related papers  (2022-04-16T16:45:06Z)
• Show, Don't Tell: Demonstrations Outperform Descriptions for Schema-Guided Task-Oriented Dialogue [27.43338545216015]
  Show, Don't Tell is a prompt format for seq2seq modeling which uses a short labeled example dialogue to show the semantics of schema elements. While requiring similar effort from service developers, we show that using short examples as schema representations with large language models results in stronger performance and better generalization.
  arXiv  Detail & Related papers  (2022-04-08T23:27:18Z)
• Description-Driven Task-Oriented Dialog Modeling [29.200221289845533]
  We show that a language description-driven system exhibits better understanding of task specifications, higher performance on state tracking, improved data efficiency, and effective zero-shot transfer to unseen tasks. We present a simple yet effective Description-Driven Dialog State Tracking (D3ST) model, which relies purely on schema descriptions and an "index-picking" mechanism.
  arXiv  Detail & Related papers  (2022-01-21T22:07:41Z)
• Infusing Finetuning with Semantic Dependencies [62.37697048781823]
  We show that, unlike syntax, semantics is not brought to the surface by today's pretrained models. We then use convolutional graph encoders to explicitly incorporate semantic parses into task-specific finetuning.
  arXiv  Detail & Related papers  (2020-12-10T01:27:24Z)
• A Sequence-to-Sequence Approach to Dialogue State Tracking [17.81139775400199]
  Seq2Seq-DU formalizes dialogue state tracking as a sequence-to-sequence problem. It can jointly model intents, slots, and slot values. It can effectively deal with categorical and non-categorical slots, and unseen schemas.
  arXiv  Detail & Related papers  (2020-11-18T21:42:44Z)
• Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue System [49.39150449455407]
  HDNO is an option framework for designing latent dialogue acts to avoid designing specific dialogue act representations. We test HDNO on MultiWoz 2.0 and MultiWoz 2.1, the datasets on multi-domain dialogues, in comparison with word-level E2E model trained with RL, LaRL and HDSA.
  arXiv  Detail & Related papers  (2020-06-11T20:55:28Z)
• MA-DST: Multi-Attention Based Scalable Dialog State Tracking [13.358314140896937]
  Dialog State Tracking dialog agents provide a natural language interface for users to complete their goal. To enable accurate multi-domain DST, the model needs to encode dependencies between past utterances and slot semantics. We introduce a novel architecture for this task to encode the conversation history and slot semantics.
  arXiv  Detail & Related papers  (2020-02-07T05:34:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.