Using large language models (LMs) for query or document expansion can im...
Bias evaluation benchmarks and dataset and model documentation have emer...
Many real-world applications require surfacing extracted snippets to use...
This is the first year of the TREC Neural CLIR (NeuCLIR) track, which ai...
We present Queer in AI as a case study for community-led participatory d...
Dealing with unjudged documents ("holes") in relevance assessments is a
...
The volume of scientific output is creating an urgent need for automated...
Multi-document summarization (MDS) has traditionally been studied assumi...
Recent studies show that Question Answering (QA) based on Answer Sentenc...
Training and inference with large neural models is expensive. However, f...
An important task for designing QA systems is answer sentence selection
...
Inference tasks such as answer sentence selection (AS2) or fact verifica...
Large transformer models can highly improve Answer Sentence Selection (A...
Open-Retrieval Generative Question Answering (GenQA) is proven to delive...
Answer Sentence Selection (AS2) is an efficient approach for the design ...
Large transformer-based language models have been shown to be very effec...
Virtual assistants such as Amazon Alexa, Apple Siri, and Google Assistan...
In a modern spoken language understanding (SLU) system, the natural lang...
While billions of non-English speaking users rely on search engines ever...
Many questions cannot be answered simply; their answers must include num...
Self-reported diagnosis statements have been widely employed in studying...
Mental health is a significant and growing public health concern. As lan...
Complex answer retrieval (CAR) is the process of retrieving answers to
q...
In recent years, online communities have formed around suicide and self-...
SemEval 2018 Task 7 focuses on relation ex- traction and classification ...