BiEncoder
Related Papers
Moving Down the Long Tail of Word Sense Disambiguation with Gloss Informed Bi-encoders
AbstractA major obstacle in Word Sense Disambiguation (WSD) is that word senses are not uniformly distributed, causing existing models to generally perform poorly on senses that are either rare or …...
Scalable Zero-shot Entity Linking with Dense Entity Retrieval
AbstractThis paper introduces a conceptually simple, scalable, and highly effective BERT-based entity linking model, along with an extensive evaluation of its accuracy-speed trade-off. We present a two-stage zero-shot linking algorithm, …...
Improving Document Representations by Generating Pseudo Query Embeddings for Dense Retrieval
AbstractRecently, the retrieval models based on dense representations have been gradually applied in the first stage of the document retrieval tasks, showing better performance than traditional sparse vector space models. …...
Nikkei at SemEval-2022 Task 8: Exploring BERT-based Bi-Encoder Approach for Pairwise Multilingual News Article Similarity
AbstractThis paper describes our system in SemEval-2022 Task 8, where participants were required to predict the similarity of two multilingual news articles. In the task of pairwise sentence and document …...
Pseudo-Relevance for Enhancing Document Representation
AbstractThis paper studies how to enhance the document representation for the bi-encoder approach in dense document retrieval. The bi-encoder, separately encoding a query and a document as a single vector, …...
Question Answering Infused Pre-training of General-Purpose Contextualized Representations
AbstractWe propose a pre-training objective based on question answering (QA) for learning general-purpose contextual representations, motivated by the intuition that the representation of a phrase in a passage should encode …...
Virtual Knowledge Graph Construction for Zero-Shot Domain-Specific Document Retrieval
AbstractDomain-specific documents cover terminologies and specialized knowledge. This has been the main challenge of domain-specific document retrieval systems. Previous approaches propose domain-adaptation and transfer learning methods to alleviate this problem. …...
CORE: Cooperative Training of Retriever-Reranker for Effective Dialogue Response Selection
AbstractEstablishing retrieval-based dialogue systems that can select appropriate responses from the pre-built index has gained increasing attention. Recent common practice is to construct a two-stage pipeline with a fast retriever …...
The Devil is in the Details: On Models and Training Regimes for Few-Shot Intent Classification
AbstractIn task-oriented dialog (ToD) new intents emerge on regular basis, with a handful of available utterances at best. This renders effective Few-Shot Intent Classification (FSIC) a central challenge for modular …...