Диалог генерациясы

Recent neural models of dialogue generation offer great promise for generating responses for conversational agents, but tend to be short- sighted, predicting utterances one at a time while ignoring their …...

AbstractRecognising dialogue acts (DA) is important for many natural language processing tasks such as dialogue generation and intention recognition. In this paper, we propose a dual-attention hierarchical recurrent neural network …...

AbstractThis paper is concerned with improving dialogue generation models through injection of knowledge, e.g., content relevant to the post that can increase the quality of responses. Past research extends the …...

AbstractSentence function is an important linguistic feature indicating the communicative purpose in uttering a sentence. Incorporating sentence functions into conversations has shown improvements in the quality of generated responses. However, …...

AbstractNeural network-based sequence-to-sequence (seq2seq) models strongly suffer from the low-diversity problem when it comes to open-domain dialogue generation. As bland and generic utterances usually dominate the frequency distribution in our …...

AbstractAs an important research topic, customer service dialogue generation tends to generate generic seller responses by leveraging current dialogue information. In this study, we propose a novel and extensible dialogue …...

AbstractLarge-scale pretrained language models have achieved outstanding performance on natural language understanding tasks. However, it is still under investigating how to apply them to dialogue generation tasks, especially those with …...

AbstractWe present a general approach towards controllable societal biases in natural language generation (NLG). Building upon the idea of adversarial triggers, we develop a method to induce societal biases in …...

AbstractAlthough pre-training models have achieved great success in dialogue generation, their performance drops dramatically when the input contains an entity that does not appear in pre-training and fine-tuning datasets (unseen …...

AbstractSeq2seq models have demonstrated their incredible effectiveness in a large variety of applications. However, recent research has shown that inappropriate language in training samples and well-designed testing cases can induce …...

Knowledge selection is an important and chal- lenging task which could provide the appropri- ate knowledge for informative dialogue gen- eration. However, the needed gold knowl- edge label is difficult …...

AbstractTowards building intelligent dialogue agents, there has been a growing interest in introducing explicit personas in generation models. However, with limited persona-based dialogue data at hand, it may be difficult …...

AbstractEvery model is only as strong as the data that it is trained on. In this paper, we present a new dataset, obtained by merging four publicly available annotated corpora …...

AbstractGrounding dialogue on external knowledge and interpreting linguistic patterns in dialogue history context, such as ellipsis, anaphora, and co-reference is critical for dialogue comprehension and generation. In this paper, we …...

AbstractRecent advances in large-scale pre-training provide large models with the potential to learn knowledge from the raw text. It is thus natural to ask whether it is possible to leverage …...

AbstractOpen-ended text generation tasks, such as dialogue generation and story completion, require models to generate a coherent continuation given limited preceding context. The open-ended nature of these tasks brings new …...

AbstractGrounding dialogue generation by extra knowledge has shown great potentials towards building a system capable of replying with knowledgeable and engaging responses. Existing studies focus on how to synthesize a …...

AbstractIncorporating multi-modal contexts in conversation is an important step for developing more engaging dialogue systems. In this work, we explore this direction by introducing MMChat: a large scale Chinese multi-modal …...

AbstractBuilding dialogue generation systems in a zero-shot scenario remains a huge challenge, since the typical zero-shot approaches in dialogue generation rely heavily on large-scale pre-trained language generation models such as …...

AbstractIn knowledge-grounded dialogue generation, pre-trained language models (PLMs) can be expected to deepen the fusing of dialogue context and knowledge because of their superior ability of semantic understanding. Unlike adopting …...

AbstractGenerating natural and informative texts has been a long-standing problem in NLP. Much effort has been dedicated into incorporating pre-trained language models (PLMs) with various open-world knowledge, such as knowledge …...

AbstractWith the availability of massive general-domain dialogue data, pre-trained dialogue generation appears to be super appealing to transfer knowledge from the general domain to downstream applications. In most existing work, …...

AbstractExisting evaluation metrics for natural language generation (NLG) tasks face the challenges on generalization ability and interpretability. Specifically, most of the well-performed metrics are required to train on evaluation datasets …...

AbstractIncorporating external graph knowledge into neural chatbot models has been proven effective for enhancing dialogue generation. However, in conventional graph neural networks (GNNs), message passing on a graph is independent …...

AbstractHuman conversations contain natural and reasonable topic shifts, reflected as the concept flows across utterances. Previous researches prove that explicitly modeling concept flows with a large commonsense knowledge graph effectively …...

AbstractVideo-grounded dialogue understanding is a challenging problem that requires machine to perceive, parse and reason over situated semantics extracted from weakly aligned video and dialogues. Most existing benchmarks treat both …...

AbstractPre-trained transformers are popular in state-of-the-art dialogue generation (DG) systems. Such language models are, however, vulnerable to various adversarial samples as studied in traditional tasks such as text classification, which …...