paper-with-me

Papers

A Knowledge-Grounded Dialog System Based on Pre-Trained Language Models

2021-06-28 · Weijie Zhang, Jiaoxuan Chen, Haipang Wu, Sanhui Wan, Gongfeng Li

We present a knowledge-grounded dialog system developed for the ninth Dialog System Technology Challenge (DSTC9) Track 1 - Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access. We leverage transfer learning with existing language models to accomplish the tasks in this challenge track. Specifically, we divided the task into four sub-tasks and fine-tuned several Transformer models on each of the sub-tasks. We made additional changes that yielded gains in both performance and efficiency, including the combination of the model with traditional entity-matching techniques, and the addition of a pointer network to the output layer of the language model.

📄 PDF Abstract BibTeX arXiv:2106.14444

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingTransfer Learning

Methods 이 논문이 사용한 방법론

[LivE@PeRson]How do I talk to a real person at Expedia? How do I talk to a real person at Expedia? To speak with a live Expedia agent, call 1 (888) 829-0881 anytime. The customer support team is available 24/7 to help with…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Sigmoid Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
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…
Adam 설명 없음

Similar Papers 제목 키워드 기반

Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representation

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Knowledge-grounded dialogue systems are challenging to build due to the lack of training data and heterogeneous knowledge sources. Existing systems perform poorly on unseen topics due to limited topics covered in the tra…

Dialogue GenerationLanguage ModelingLanguage Modelling

A Model of Cross-Lingual Knowledge-Grounded Response Generation for Open-Domain Dialogue Systems

2021-11-01 · Findings (EMNLP) 2021 11 · San Kim, Jin Yea Jang, Minyoung Jung, Saim Shin

Research on open-domain dialogue systems that allow free topics is challenging in the field of natural language processing (NLP). The performance of the dialogue system has been improved recently by the method utilizing …

Language ModelingLanguage ModellingResponse Generation

Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representation

2021-12-15 · NAACL 2022 7 · Yu Li, Baolin Peng, Yelong Shen, Yi Mao 외

Knowledge-grounded dialogue systems are challenging to build due to the lack of training data and heterogeneous knowledge sources. Existing systems perform poorly on unseen topics due to limited topics covered in the tra…

Dialogue GenerationLanguage ModelingLanguage Modelling

Knowledge-Grounded Dialogue Generation with Pre-trained Language Models

2020-10-17 · EMNLP 2020 11 · Xueliang Zhao, Wei Wu, Can Xu, Chongyang Tao 외

We study knowledge-grounded dialogue generation with pre-trained language models. To leverage the redundant external knowledge under capacity constraint, we propose equipping response generation defined by a pre-trained …

Dialogue GenerationLanguage ModelingLanguage ModellingResponse Generation

Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark

2021-04-30 · Nouha Dziri, Hannah Rashkin, Tal Linzen, David Reitter

Knowledge-grounded dialogue systems powered by large language models often generate responses that, while fluent, are not attributable to a relevant source of information. Progress towards models that do not exhibit this…

Language ModellingNatural Language Inference