Customers interacting with product search engines are increasingly
formu...
Spoken Question Answering (QA) is a key feature of voice assistants, usu...
The goal of unbiased learning to rank (ULTR) is to leverage implicit use...
We present the findings of SemEval-2023 Task 2 on Fine-grained Multiling...
Embodied agents have achieved prominent performance in following human
i...
Conversational Question Answering (CQA) aims to answer questions contain...
Integrating free-text explanations to in-context learning of large langu...
With the recent advance in large pre-trained language models, researcher...
Processing-in-memory (PIM), an increasingly studied neuromorphic hardwar...
Unbiased Learning to Rank (ULTR) that learns to rank documents with bias...
Existing studies in dialogue system research mostly treat task-oriented
...
A large amount of information is stored in data tables. Users can search...
Neural network quantization is a promising compression technique to redu...
Accelerating finite automata processing is critical for advancing real-t...
The sheer volume of financial statements makes it difficult for humans t...
Even with generational improvements in DRAM technology, memory access la...
A compact, accurate, and bitwidth-programmable in-memory computing (IMC)...
Transmission electron microscopy (TEM) is one of the primary tools to sh...
Deep neural networks are found to be prone to adversarial examples which...
We describe the development, characteristics and availability of a test
...
Relation prediction in knowledge graphs is dominated by embedding based
...
Ranking models are the main components of information retrieval systems....
Existing conversational systems are mostly agent-centric, which assumes ...
Extreme multi-label text classification (XMTC) is a task for tagging a g...
Pretrained contextualized language models such as BERT have achieved
imp...
Previous works on Natural Language Generation (NLG) from structured data...
Neural natural language generation (NLG) models have recently shown
rema...
Existing question answering datasets focus on dealing with homogeneous
i...
Computation-intensive pretrained models have been taking the lead of man...
A search engine's ability to retrieve desirable datasets is important fo...
Pre-trained embeddings such as word embeddings and sentence embeddings a...
Natural language generation (NLG) from structured data or knowledge is
e...
With the rapid development in deep learning, deep neural networks have b...
Deep convolutional neural network (DCNN) is the state-of-the-art method ...