Related papers: Why Do Neural Response Generation Models Prefer Un…
Neural conversation models tend to generate safe, generic responses for most inputs. This is due to the limitations of likelihood-based decoding objectives in generation tasks with diverse outputs, such as conversation. To address this…
Existing open-domain dialogue generation models are usually trained to mimic the gold response in the training set using cross-entropy loss on the vocabulary. However, a good response does not need to resemble the gold response, since there…
Avoiding the generation of responses that contradict the preceding context is a significant challenge in dialogue response generation. One feasible method is post-processing, such as filtering out contradicting responses from a resulting…
Open-domain human-computer conversation has attracted much attention in the field of NLP. Contrary to rule- or template-based domain-specific dialog systems, open-domain conversation usually requires data-driven approaches, which can be…
Using a sequence-to-sequence framework, many neural conversation models for chit-chat succeed in naturalness of the response. Nevertheless, the neural conversation models tend to give generic responses which are not specific to given…
We present open domain response generation with meta-words. A meta-word is a structured record that describes various attributes of a response, and thus allows us to explicitly model the one-to-many relationship within open domain dialogues…
Sequence generation models for dialogue are known to have several problems: they tend to produce short, generic sentences that are uninformative and unengaging. Retrieval models on the other hand can surface interesting responses, but are…
Question answer generation using Natural Language Processing models is ubiquitous in the world around us. It is used in many use cases such as the building of chat bots, suggestive prompts in google search and also as a way of navigating…
Modern machine learning models are deployed in diverse, non-stationary environments where they must continually adapt to new tasks and evolving knowledge. Continual fine-tuning and in-context learning are costly and brittle, whereas neural…
Open-domain neural dialogue models have achieved high performance in response ranking and evaluation tasks. These tasks are formulated as a binary classification of responses given in a dialogue context, and models generally learn to make…
We introduce the multiresolution recurrent neural network, which extends the sequence-to-sequence framework to model natural language generation as two parallel discrete stochastic processes: a sequence of high-level coarse tokens, and a…
Sequence-to-Sequence (seq2seq) models have become overwhelmingly popular in building end-to-end trainable dialogue systems. Though highly efficient in learning the backbone of human-computer communications, they suffer from the problem of…
The predominant approach to open-domain dialog generation relies on end-to-end training of neural models on chat datasets. However, this approach provides little insight as to what these models learn (or do not learn) about engaging in…
Sequence-to-sequence models have been applied to the conversation response generation problem where the source sequence is the conversation history and the target sequence is the response. Unlike translation, conversation responding is…
In this paper, we focus on the personalized response generation for conversational systems. Based on the sequence to sequence learning, especially the encoder-decoder framework, we propose a two-phase approach, namely initialization then…
This paper proposes a novel neural machine reading model for open-domain question answering at scale. Existing machine comprehension models typically assume that a short piece of relevant text containing answers is already identified and…
Although pre-trained sequence-to-sequence models have achieved great success in dialogue response generation, chatbots still suffer from generating inconsistent responses in real-world practice, especially in multi-turn settings. We argue…
Although recent neural conversation models have shown great potential, they often generate bland and generic responses. While various approaches have been explored to diversify the output of the conversation model, the improvement often…
We study multi-turn response generation for open-domain dialogues. The existing state-of-the-art addresses the problem with deep neural architectures. While these models improved response quality, their complexity also hinders the…
We introduce a unified probabilistic framework for solving sequential decision making problems ranging from Bayesian optimisation to contextual bandits and reinforcement learning. This is accomplished by a probabilistic model-based approach…