Mechanism-Aware Neural Machine for Dialogue Response Generation

By Ganbin Zhou, Ping Luo, Rongyu Cao, Fen Lin, Qing He. 2017

81 citations recorded by the source corpus.

To the same utterance, people's responses in everyday dialogue may be diverse largely in terms of content semantics, speaking styles, communication intentions and so on. Previous generative conversational models ignore these 1-to-n relationships between a post to its diverse responses, and tend to return high-frequency but meaningless responses. In this study we propose a mechanism-aware neural machine for dialogue response generation. It assumes that there exists some latent responding mechanisms, each of which can generate different responses for a single input post. With this assumption we model different responding mechanisms as latent embeddings, and develop a encoder-diverter-decoder framework to train its modules in an end-to-end fashion. With the learned latent mechanisms, for the first time these decomposed modules can be used to encode the input into mechanism-aware context, and decode the responses with the controlled generation styles and topics. Finally, the experiments with human judgements, intuitive examples, detailed discussions demonstrate the quality and diversity of the generated responses with 9.80% increase of acceptable ratio over the best of six baseline methods.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Towards Coherent and Engaging Spoken Dialog Response Generation Using Automatic Conversation Evaluators (2019, background): “Zhou et al. (2017) and Zhang et al. (2018) introduce latent factors in the seq2seq models that control speciﬁcity in neural response generation.”
What makes a good conversation? How controllable attributes affect human judgments (2019, background): “In particular, several works use control to tackle the same common sequence-to-sequence problems we address here (particularly genericness and unrelated output), in the context of single-turn response generation (Baheti et al., 2018; Li et al., 2016a, 2017a; Shen et al., 2017; Xing et al., 2017; Zha”
Challenges in Building Intelligent Open-domain Dialog Systems (2019, methodology): “l. [184] proposed an unsupervised representation learning method to use discrete latent variables, instead of dense continuous ones, which improves the interpretability of representation. Zhou et al. [187, 188] assumed that there exist some latent responding mechanisms, each of which can generates d”
Learning to Control the Specificity in Neural Response Generation (2018, methodology): “Zhou et al. (2017) introduced latent responding factors to the Seq2Seq model to avoid generating safe responses.”
Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context (2019, methodology): “Therefore, previous social response generation methods attempt to model the one-tomany property by modeling responses with other meta information, such as response specificity (Zhou et al. 2017; 2018).”
Neural Response Generation via GAN with an Approximate Embedding Layer (2017, background): “, 2016b) and latent semantics (Zhou et al., 2017; Serban et al., 2017) have also been proven beneficial within this context.”
Aiming to Know You Better Perhaps Makes Me a More Engaging Dialogue Partner (2018, background): “Zhou et al. (2017) maps the input message to the distribution over intermediate factors, each of which produces a different response.”
“Transforming” Delete, Retrieve, Generate Approach for Controlled Text Style Transfer (2019, background): “Text style transfer is an important Natural Language Generation (NLG) task, and has wideranging applications from adapting conversational style in dialogue agents (Zhou et al., 2017), obfuscating personal attributes (such as gender) to pre-”
Sequential Attention-based Network for Noetic End-to-End Response Selection (2019, methodology): “Multi-turn dialogue modeling can be divided into generation-based methods (Serban et al. 2016; Zhou et al. 2017) and retrieval-based methods (Lowe et al. 2015; Wu et al. 2017).”
Cluster-based beam search for pointer-generator chatbot grounded by knowledge (2020, background): “(Zhou et al. 2017) proposed an encoder-diverter-decoder framework to address the 1-to-n relationship between a post and multiple responses so that diverse responses are generated with latent factors.”
Modeling Multi-turn Conversation with Deep Utterance Aggregation (2018, background): “Multi-turn conversation modeling plays a key role in dialogue systems, either for generation-based (Serban et al., 2017b; Serban et al., 2017a; Zhou et al., 2017; Wu et al., 2018) or retrieval-based ones (Wu et al., 2017; Zhou et al., 2016) in which the latter is the focus of this paper.”
Linguistically-Informed Specificity and Semantic Plausibility for Dialogue Generation (2019, background): “Zhou et al. (2017) promoted diversity by training latent embeddings to represent different response mechanisms.”