In conversational search, the user's real search intent for the current ...
Large language models (LLMs), such as ChatGPT, are prone to generate
hal...
Large language models (LLMs) encode a large amount of world knowledge.
H...
Graph Convolutional Networks (GCNs) have shown strong performance in lea...
Diffusion models have become a new generative paradigm for text generati...
In this paper, we introduce a new NLP task – generating short factual
ar...
Conversational search is a difficult task as it aims at retrieving docum...
To facilitate research on text generation, this paper presents a
compreh...
In the prompt-specific holistic score prediction task for Automatic Essa...
We study the text generation task under the approach of pre-trained lang...
Contextual information in search sessions is important for capturing use...
Beyond topical relevance, passage ranking for open-domain factoid questi...
In Natural Language Understanding (NLU) applications, training an effect...
Expressive speech synthesis, like audiobook synthesis, is still challeng...
Pretrained language models (PLMs) have made remarkable progress in text
...
Text Generation aims to produce plausible and readable text in human lan...
Context information in search sessions has proven to be useful for captu...
A proactive dialogue system has the ability to proactively lead the
conv...
Deep learning models for automatic readability assessment generally disc...
Scientific digital libraries play a critical role in the development and...
Sentence ordering aims to arrange the sentences of a given text in the
c...
Sentence ordering aims at arranging a list of sentences in the correct o...
Grounding human-machine conversation in a document is an effective way t...
Distant supervision provides a means to create a large number of weakly
...
We investigate the problem of multi-domain Dialogue State Tracking (DST)...
Pre-trained language models have been successfully used in response
gene...
We investigate the general problem of conditioned dialogue, in which a
c...
We investigate the problem of multi-domain Dialogue State Tracking (DST)...
It is appealing to have a system that generates a story or scripts
autom...
Much progress has been made recently on text classification with methods...
Search results personalization has become an effective way to improve th...
Keyphrase extraction from documents is useful to a variety of applicatio...
We study the problem of learning representations of entities and relatio...
Recommending the right products is the central problem in recommender
sy...
Vision is a common source of inspiration for poetry. The objects and the...
Users may strive to formulate an adequate textual query for their inform...
We present a novel response generation system that can be trained end to...