Open AccessPosted Content
Incorporating Loose-Structured Knowledge into LSTM with Recall Gate for Conversation Modeling.
TLDR
The loose structured domain knowledge base is introduced, which can be built with slight amount of manual work and easily adopted by the Recall gate, so as to enhance LSTM by cooperating with its local memory to capture the implicit semantic relevance between sentences within conversations.Abstract:
Modeling human conversations is the essence for building satisfying chat-bots
with multi-turn dialog ability. Conversation modeling will notably benefit from
domain knowledge since the relationships between sentences can be clarified due
to semantic hints introduced by knowledge. In this paper, a deep neural network
is proposed to incorporate background knowledge for conversation modeling.
Through a specially designed Recall gate, domain knowledge can be transformed
into the extra global memory of Long Short-Term Memory (LSTM), so as to enhance
LSTM by cooperating with its local memory to capture the implicit semantic
relevance between sentences within conversations. In addition, this paper
introduces the loose structured domain knowledge base, which can be built with
slight amount of manual work and easily adopted by the Recall gate. Our model
is evaluated on the context-oriented response selecting task, and experimental
results on both two datasets have shown that our approach is promising for
modeling human conversations and building key components of automatic chatting
systems.read more
Citations
More filters
Proceedings ArticleDOI
Deep Reinforcement Learning for Dialogue Generation
TL;DR: This work simulates dialogues between two virtual agents, using policy gradient methods to reward sequences that display three useful conversational properties: informativity, non-repetitive turns, coherence, and ease of answering.
Posted Content
Adversarial Learning for Neural Dialogue Generation
TL;DR: This paper proposed using adversarial training for open-domain dialogue generation, where the generator is trained to generate sequences that are indistinguishable from human-generated dialogue utterances, and the outputs from the discriminator are used as rewards for the generator.
Proceedings ArticleDOI
Adversarial Learning for Neural Dialogue Generation
TL;DR: This work applies adversarial training to open-domain dialogue generation, training a system to produce sequences that are indistinguishable from human-generated dialogue utterances, and investigates models for adversarial evaluation that uses success in fooling an adversary as a dialogue evaluation metric, while avoiding a number of potential pitfalls.
Proceedings Article
Targeted Aspect-Based Sentiment Analysis via Embedding Commonsense Knowledge into an Attentive LSTM
TL;DR: A novel solution to targeted aspect-based sentiment analysis, which tackles the challenges of both aspect- based sentiment analysis and targeted sentiment analysis by exploiting commonsense knowledge by augmenting the LSTM network with a hierarchical attention mechanism.
Posted Content
Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots
TL;DR: This paper proposed a sequential matching network (SMN) to match a response with each utterance in the context on multiple levels of granularity, and distill important matching information from each pair as a vector with convolution and pooling operations.
References
More filters
Journal ArticleDOI
Long short-term memory
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
Proceedings ArticleDOI
Learning Phrase Representations using RNN Encoder--Decoder for Statistical Machine Translation
Kyunghyun Cho,Bart van Merriënboer,Caglar Gulcehre,Dzmitry Bahdanau,Fethi Bougares,Holger Schwenk,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio +8 more
TL;DR: In this paper, the encoder and decoder of the RNN Encoder-Decoder model are jointly trained to maximize the conditional probability of a target sequence given a source sequence.
Proceedings Article
Sequence to Sequence Learning with Neural Networks
TL;DR: The authors used a multilayered Long Short-Term Memory (LSTM) to map the input sequence to a vector of a fixed dimensionality, and then another deep LSTM to decode the target sequence from the vector.
Posted Content
Sequence to Sequence Learning with Neural Networks
TL;DR: This paper presents a general end-to-end approach to sequence learning that makes minimal assumptions on the sequence structure, and finds that reversing the order of the words in all source sentences improved the LSTM's performance markedly, because doing so introduced many short term dependencies between the source and the target sentence which made the optimization problem easier.
Proceedings Article
End-to-end memory networks
TL;DR: This paper proposed an end-to-end memory network with a recurrent attention model over a possibly large external memory, which can be seen as an extension of RNNsearch to the case where multiple computational steps (hops) are performed per output symbol.