paper-with-me

Papers

Dialogue Transformers

2019-10-01 · Vladimir Vlasov, Johannes E. M. Mosig, Alan Nichol

We introduce a dialogue policy based on a transformer architecture, where the self-attention mechanism operates over the sequence of dialogue turns. Recent work has used hierarchical recurrent neural networks to encode multiple utterances in a dialogue context, but we argue that a pure self-attention mechanism is more suitable. By default, an RNN assumes that every item in a sequence is relevant for producing an encoding of the full sequence, but a single conversation can consist of multiple overlapping discourse segments as speakers interleave multiple topics. A transformer picks which turns to include in its encoding of the current dialogue state, and is naturally suited to selectively ignoring or attending to dialogue history. We compare the performance of the Transformer Embedding Dialogue (TED) policy to an LSTM and to the REDP, which was specifically designed to overcome this limitation of RNNs.

📄 PDF Abstract BibTeX arXiv:1910.00486

Code (1)

RasaHQ/TED-paper 공식 구현

Methods 이 논문이 사용한 방법론

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
Tanh Activation 설명 없음
Residual Connection 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…
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…

Similar Papers 제목 키워드 기반

Transformers to Learn Hierarchical Contexts in Multiparty Dialogue for Span-based Question Answering

2020-04-07 · ACL 2020 6 · Changmao Li, Jinho D. Choi

We introduce a novel approach to transformers that learns hierarchical representations in multiparty dialogue. First, three language modeling tasks are used to pre-train the transformers, token- and utterance-level langu…

Language ModelingLanguage ModellingMulti-Task LearningPrediction+1

Improving Factual Consistency for Knowledge-Grounded Dialogue Systems via Knowledge Enhancement and Alignment

2023-10-12 · Boyang Xue, Weichao Wang, Hongru Wang, Fei Mi 외

Pretrained language models (PLMs) based knowledge-grounded dialogue systems are prone to generate responses that are factually inconsistent with the provided knowledge source. In such inconsistent responses, the dialogue…

Multi-turn Response Selection using Dialogue Dependency Relations

2020-10-04 · EMNLP 2020 11 · Qi Jia, Yizhu Liu, Siyu Ren, Kenny Q. Zhu 외

Multi-turn response selection is a task designed for developing dialogue agents. The performance on this task has a remarkable improvement with pre-trained language models. However, these models simply concatenate the tu…

Stateful Memory-Augmented Transformers for Efficient Dialogue Modeling

2022-09-15 · Qingyang Wu, Zhou Yu

Transformer encoder-decoder models have achieved great performance in dialogue generation tasks, however, their inability to process long dialogue history often leads to truncation of the context To address this problem,…

DecoderDialogue GenerationLanguage ModelingLanguage Modelling

Variational Transformers for Diverse Response Generation

2020-03-28 · Zhaojiang Lin, Genta Indra Winata, Peng Xu, Zihan Liu 외

Despite the great promise of Transformers in many sequence modeling tasks (e.g., machine translation), their deterministic nature hinders them from generalizing to high entropy tasks such as dialogue response generation.…

DecoderDiversityMachine TranslationResponse Generation+1