Personalizing Dialogue Agents: I have a dog, do you have pets too?

Abstract

Chit-chat models are known to have several problems: they lack specificity, do not display a consistent personality and are often not very captivating. In this work we present the task of making chit-chat more engaging by conditioning on profile information. We collect data and train models to (i) condition on their given profile information; and (ii) information about the person they are talking to, resulting in improved dialogues, as measured by next utterance prediction. Since (ii) is initially unknown, our model is trained to engage its partner with personal topics, and we show the resulting dialogue can be used to predict profile information about the interlocutors.

DeepCopy: Grounded Response Generation with Hierarchical Pointer Networks

“…Another related work (Raghu et al, 2018) applies hierarchical memory network for task oriented dialog problem. In this work, we compare our model with (Zhang et al, 2018) which uses a memoryaugmented sequence-to-sequence response generator grounded on the dialogue history and persona.…”

“…Our proposed approach extends pointer-generator networks (See et al, 2017) by allowing the decoder to hierarchically attend and copy from external knowledge in addition to the dialogue context. We empirically show the effectiveness of the proposed model compared to several baselines including (Ghazvininejad et al, 2018;Zhang et al, 2018) through both automatic evaluation metrics and human evaluation on CONVAI2 dataset.…”

A Gated Self-attention Memory Network for Answer Selection

“…We attribute the diminishing returns in increasing the number of hops to the limited size of the TrecQA and WikiQA datasets. Many previous works related to memory networks also use small number of memory hops Sukhbaatar et al, 2015;Miller et al, 2016;Zhang et al, 2018). Table 2 summarizes the performances of our proposed models and compares them to the baselines on the TrecQA and WikiQA datasets.…”

A Voice Interactive Multilingual Student Support System using IBM Watson

“…Deep learning techniques are used in both retrieval-based and generative models, but research seems to be moving into the generative direction [8]. A popular class of generative-based chatbot models are generative recurrent systems like seq2seq [9] which are rooted in language modelling and are able to produce syntactically coherent novel responses in conjunction with memoryaugmented networks [10].…”

“…Despite the continuous progress in deep learning, which make chatbots quite reliable and able to provide automatic and adaptive human-like conversation behaviour, they need improvement with respect to supporting complex behaviours [4,10]. The infinite number of topics and the fact that a certain amount of world knowledge is required to create reasonable responses makes the development of an open domain chatbot a hard problem [8].…”