Evaluating open-domain dialogue systems is challenging for reasons such ...
The research field of Information Retrieval (IR) has evolved significant...
Answer selection in open-domain dialogues aims to select an accurate ans...
In open-domain question answering, due to the ambiguity of questions,
mu...
Explanations in conventional recommender systems have demonstrated benef...
Summarization quality evaluation is a non-trivial task in text summariza...
Learning reinforcement learning (RL)-based recommenders from historical
...
Recent work on knowledge graph completion (KGC) focused on learning
embe...
Recommender systems that learn from implicit feedback often use large vo...
Large Language Models (LLMs) have demonstrated a remarkable ability to
g...
Knowledge selection is the key in knowledge-grounded dialogues (KGD), wh...
Conventional document retrieval techniques are mainly based on the
index...
Sequential recommendations aim to capture users' preferences from their
...
Dialogue structure discovery is essential in dialogue generation.
Well-s...
Side information is being used extensively to improve the effectiveness ...
Conversational recommender systems (CRSs) often utilize external knowled...
Pre-trained language models (LMs) store knowledge in their parameters an...
Natural language understanding (NLU) models often rely on dataset biases...
Knowledge tracing aims to trace students' evolving knowledge states by
p...
Modern recommender systems are trained to predict users potential future...
Learned recommender systems may inadvertently leak information about the...
Modern recommender systems aim to improve user experience. As reinforcem...
Open-ended text generation tasks, such as dialogue generation and story
...
Pre-trained language models (PLM) have demonstrated their effectiveness ...
Task-oriented dialogue systems (TDSs) are assessed mainly in an offline
...
Recently, recommender systems have achieved promising performances and b...
Medical dialogue systems (MDSs) aim to assist doctors and patients with ...
Electronic health record (EHR) coding is the task of assigning ICD codes...
One of the key challenges in Sequential Recommendation (SR) is how to ex...
Conversational information seeking (CIS) is playing an increasingly impo...
Contract element extraction (CEE) is the novel task of automatically
ide...
Medical dialogue generation aims to provide automatic and accurate respo...
Evaluation is crucial in the development process of task-oriented dialog...
In e-commerce, opinion tags refer to a ranked list of tags provided by t...
Cross-domain sequential recommendation is the task of predict the next i...
Enabling the machines with empathetic abilities to provide context-consi...
Text summarization is the research area aiming at creating a short and
c...
In this paper, we address the problem of answering complex information n...
Unstructured Persona-oriented Dialogue Systems (UPDS) has been demonstra...
Conventional emotional dialogue system focuses on generating emotion-ric...
Matrix factorization (MF) techniques have been shown to be effective for...
Sequential Recommendation (SR) has been attracting a growing attention f...
Sequential Recommendation (SR) has been attracting a growing attention f...
The task of fashion recommendation includes two main challenges: visual
...
In e-commerce portals, generating answers for product-related questions ...
In neural abstractive summarization field, conventional sequence-to-sequ...
Recurrent neural networks for session-based recommendation have attracte...
Graphs, which describe pairwise relations between objects, are essential...
The task of dialogue generation aims to automatically provide responses ...
Most previous work on fashion recommendation focuses on designing visual...