Position Matters! Empirical Study of Order Effect in Knowledge-grounded Dialogue

• URL: http://arxiv.org/abs/2302.05888v1
• Date: Sun, 12 Feb 2023 10:13:00 GMT
• Title: Position Matters! Empirical Study of Order Effect in Knowledge-grounded Dialogue
• Authors: Hsuan Su, Shachi H Kumar, Sahisnu Mazumder, Wenda Chen, Ramesh Manuvinakurike, Eda Okur, Saurav Sahay, Lama Nachman, Shang-Tse Chen, Hung-yi Lee
• Abstract summary: We investigate how the order of the knowledge set can influence autoregressive dialogue systems' responses. We propose a simple and novel technique to alleviate the order effect by modifying the position embeddings of knowledge input.
• Score: 54.98184262897166
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the power of large pretrained language models, various research works have integrated knowledge into dialogue systems. The traditional techniques treat knowledge as part of the input sequence for the dialogue system, prepending a set of knowledge statements in front of dialogue history. However, such a mechanism forces knowledge sets to be concatenated in an ordered manner, making models implicitly pay imbalanced attention to the sets during training. In this paper, we first investigate how the order of the knowledge set can influence autoregressive dialogue systems' responses. We conduct experiments on two commonly used dialogue datasets with two types of transformer-based models and find that models view the input knowledge unequally. To this end, we propose a simple and novel technique to alleviate the order effect by modifying the position embeddings of knowledge input in these models. With the proposed position embedding method, the experimental results show that each knowledge statement is uniformly considered to generate responses.

Related papers

• Bridging Information Gaps in Dialogues With Grounded Exchanges Using Knowledge Graphs [4.449835214520727]
  We study the potential of large language models for conversational grounding. Our approach involves annotating human conversations across five knowledge domains to create a new dialogue corpus called BridgeKG. Our findings offer insights into how these models use in-context learning for conversational grounding tasks and common prediction errors.
  arXiv  Detail & Related papers  (2024-08-02T08:07:15Z)
• PK-Chat: Pointer Network Guided Knowledge Driven Generative Dialogue Model [79.64376762489164]
  PK-Chat is a Pointer network guided generative dialogue model, incorporating a unified pretrained language model and a pointer network over knowledge graphs. The words generated by PK-Chat in the dialogue are derived from the prediction of word lists and the direct prediction of the external knowledge graph knowledge. Based on the PK-Chat, a dialogue system is built for academic scenarios in the case of geosciences.
  arXiv  Detail & Related papers  (2023-04-02T18:23:13Z)
• KPT: Keyword-guided Pre-training for Grounded Dialog Generation [82.68787152707455]
  We propose KPT (guided Pre-Training), a novel self-supervised pre-training method for grounded dialog generation. Specifically, we use a pre-trained language model to extract the most uncertain tokens in the dialog as keywords. We conduct extensive experiments on various few-shot knowledge-grounded generation tasks, including grounding on dialog acts, knowledge graphs, persona descriptions, and Wikipedia passages.
  arXiv  Detail & Related papers  (2022-12-04T04:05:01Z)
• DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue Generation [9.186215038100904]
  We propose DialoKG, a novel task-oriented dialogue system that effectively incorporates knowledge into a language model. Our proposed system views relational knowledge as a knowledge graph and introduces a structure-aware knowledge embedding technique. An empirical evaluation demonstrates the effectiveness of DialoKG over state-of-the-art methods on several standard benchmark datasets.
  arXiv  Detail & Related papers  (2022-04-19T22:26:18Z)
• Achieving Conversational Goals with Unsupervised Post-hoc Knowledge Injection [37.15893335147598]
  A limitation of current neural dialog models is that they tend to suffer from a lack of specificity and informativeness in generated responses. We propose a post-hoc knowledge-injection technique where we first retrieve a diverse set of relevant knowledge snippets conditioned on both the dialog history and an initial response from an existing dialog model. We construct multiple candidate responses, individually injecting each retrieved snippet into the initial response using a gradient-based decoding method, and then select the final response with an unsupervised ranking step.
  arXiv  Detail & Related papers  (2022-03-22T00:42:27Z)
• Towards Large-Scale Interpretable Knowledge Graph Reasoning for Dialogue Systems [109.16553492049441]
  We propose a novel method to incorporate the knowledge reasoning capability into dialogue systems in a more scalable and generalizable manner. To the best of our knowledge, this is the first work to have transformer models generate responses by reasoning over differentiable knowledge graphs.
  arXiv  Detail & Related papers  (2022-03-20T17:51:49Z)
• Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representation [78.85622982191522]
  Existing systems perform poorly on unseen topics due to limited topics covered in the training data. We present PLUG, a language model that homogenizes different knowledge sources to a unified knowledge representation. It can achieve comparable performance with state-of-the-art methods under a fully-supervised setting.
  arXiv  Detail & Related papers  (2021-12-15T07:11:02Z)
• Multi-turn Dialogue Reading Comprehension with Pivot Turns and Knowledge [43.352833140317486]
  Multi-turn dialogue reading comprehension aims to teach machines to read dialogue contexts and solve tasks such as response selection and answering questions. This work makes the first attempt to tackle the above two challenges by extracting substantially important turns as pivot utterances. We propose a pivot-oriented deep selection model (PoDS) on top of the Transformer-based language models for dialogue comprehension.
  arXiv  Detail & Related papers  (2021-02-10T15:00:12Z)
• Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue [51.513276162736844]
  We propose a sequential latent variable model as the first approach to this matter. The model named sequential knowledge transformer (SKT) can keep track of the prior and posterior distribution over knowledge.
  arXiv  Detail & Related papers  (2020-02-18T11:59:59Z)

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.