paper-with-me

홈 › Papers

Learning-by-Narrating: Narrative Pre-Training for Zero-Shot Dialogue Comprehension

2022-03-19 · ACL 2022 5 · Chao Zhao, Wenlin Yao, Dian Yu, Kaiqiang Song, Dong Yu, Jianshu Chen

Comprehending a dialogue requires a model to capture diverse kinds of key information in the utterances, which are either scattered around or implicitly implied in different turns of conversations. Therefore, dialogue comprehension requires diverse capabilities such as paraphrasing, summarizing, and commonsense reasoning. Towards the objective of pre-training a zero-shot dialogue comprehension model, we develop a novel narrative-guided pre-training strategy that learns by narrating the key information from a dialogue input. However, the dialogue-narrative parallel corpus for such a pre-training strategy is currently unavailable. For this reason, we first construct a dialogue-narrative parallel corpus by automatically aligning movie subtitles and their synopses. We then pre-train a BART model on the data and evaluate its performance on four dialogue-based tasks that require comprehension. Experimental results show that our model not only achieves superior zero-shot performance but also exhibits stronger fine-grained dialogue comprehension capabilities. The data and code are available at https://github.com/zhaochaocs/Diana

📄 PDF Abstract BibTeX arXiv:2203.10249

Code (1)

zhaochaocs/diana 공식 구현

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Adam 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

A Preliminary Evaluation of ChatGPT for Zero-shot Dialogue Understanding

2023-04-09 · Wenbo Pan, Qiguang Chen, Xiao Xu, Wanxiang Che 외

Zero-shot dialogue understanding aims to enable dialogue to track the user's needs without any training data, which has gained increasing attention. In this work, we investigate the understanding ability of ChatGPT for z…

Dialogue State TrackingDialogue Understandingslot-fillingSlot Filling+1

MulZDG: Multilingual Code-Switching Framework for Zero-shot Dialogue Generation

2022-08-18 · COLING 2022 10 · Yongkang Liu, Shi Feng, Daling Wang, Yifei Zhang

Building dialogue generation systems in a zero-shot scenario remains a huge challenge, since the typical zero-shot approaches in dialogue generation rely heavily on large-scale pre-trained language generation models such…

Data AugmentationDialogue GenerationText Generation

NEST: Narrative Event Structures in Time for Long Video Understanding

2026-06-18 · Ali Asgarov, Kaushik Narasimhan, Najibul Haque Sarker, Hani Alomari 외 arxiv

Recent progress in vision-language models has enabled the processing of increasingly long video sequences, but the ability to handle extended token streams does not translate to understanding of narrative structure in lo…

Relation Extraction

Zero-shot narrative detection in social messaging

2026-09-15 · Jesús M. Fraile-Hernández, Anselmo Peñas, Patrick Giedemann arxiv

This study investigates the zero-shot ability of large language models (LLMs) to identify and classify hidden narratives in social messages. Our research hypothesis is that LLMs' extensive contextual knowledge allows the…

Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking

2020-05-02 · ACL 2020 6 · Giovanni Campagna, Agata Foryciarz, Mehrad Moradshahi, Monica S. Lam

Zero-shot transfer learning for multi-domain dialogue state tracking can allow us to handle new domains without incurring the high cost of data acquisition. This paper proposes new zero-short transfer learning technique …

Data AugmentationDialogue State TrackingMulti-domain Dialogue State TrackingTransfer Learning+1