Recent neural retrieval mainly focuses on ranking short texts and is
cha...
Pairing a lexical retriever with a neural re-ranking model has set
state...
Text embeddings are commonly evaluated on a small set of datasets from a...
Recent few-shot methods, such as parameter-efficient fine-tuning (PEFT) ...
Dense retrievers encode documents into fixed dimensional embeddings. How...
Recent advances in NLP and information retrieval have given rise to a di...
Dense retrieval approaches can overcome the lexical gap and lead to
sign...
Neural IR models have often been studied in homogeneous and narrow setti...
Question answering systems should help users to access knowledge on a br...
Learning sentence embeddings often requires large amount of labeled data...
Current state-of-the-art approaches to cross-modal retrieval process tex...
Information Retrieval using dense low-dimensional representations recent...
Cross-document event coreference resolution (CDCR) is an NLP task in whi...
Massively pre-trained transformer models are computationally expensive t...
There are two approaches for pairwise sentence scoring: Cross-encoders, ...
We present an easy and efficient method to extend existing sentence embe...
BERT (Devlin et al., 2018) and RoBERTa (Liu et al., 2019) has set a new
...
We experiment with two recent contextualized word embedding methods (ELM...
Recognizing coreferring events and entities across multiple texts is cru...
ELMo embeddings (Peters et. al, 2018) had a huge impact on the NLP commu...
Developing state-of-the-art approaches for specific tasks is a major dri...
In this paper we show that reporting a single performance score is
insuf...
Selecting optimal parameters for a neural network architecture can often...