Point of Interest (POI) search faces unique challenges in effectively combining semantic relevance, geographic context, and location priorities. To address these challenges, we propose a novel two-stage approach that leverages modern text embeddings for both semantic and geographic matching. Our method fuses the user query, user address, and POI metadata into a unified text format for dense retrieval, followed by a re-scoring stage that incorporates distance and popularity biases. Experiments on a 17 million US location database demonstrate that our dense retrieval method significantly surpasses traditional lexical approaches, and the addition of distance and popularity biases further enhances performance achieving an improvement from 55.3% to 81.1% Recall@100.

Current answer sentence selection (AS2) applied in open-domain question answering (ODQA) selects answers by ranking a large set of candidates, i.e., sentences, extracted from the retrieved text. In this paper, we present Passage-based Extracting Answer Sentence In-place (PEASI), a novel answer selection model optimized for Web-scale setting. This is a Transformer-based network that can jointly (i) rerank passages retrieved for a question and (ii) identify a probable answer from the top passages. We train PEASI with multi-task learning for sharing representations between the passage reranker and answer sentence extractor. We construct a new large-scale QA dataset (WQA) consisting of 800,000+ labeled passages/sentences for 60,000+ questions. The experiment results show that PEASI outperforms AS2 state of the art by 6.51% in accuracy on WQA, from 48.86% to 55.37%.

Open-Domain Question Answering (ODQA) systems generate answers from relevant text returned by search engines, e.g., lexical features-based such as BM25, or embeddings-based such as dense passage retrieval (DPR). Few datasets are available for this task: they mainly focus on QA systems based on machine reading (MR) approach, and show problematic evaluation, mostly based on uncontextualized short answer matching. In this paper, we present WDRASS, a dataset for ODQA based on answer sentence selection (AS2) models, which consider sentences as candidate answers for QA systems. WDRASS consists of ∼64k questions and 800k+ labeled passages and sentences extracted from 30M documents. We evaluate the dataset by training models on it and comparing with the same models trained on Google NQ. Our experiments show that WDRASS significantly improves the performance of retrieval and reranking models, thus boosting the accuracy of downstream QA tasks. We believe our dataset can produce significant impact in advancing IR research.

Zeyu Zhang, Thuy Vu, Alessandro Moschitti. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Concept normalization, the task of linking textual mentions of concepts to concepts in an ontology, is challenging because ontologies are large.In most cases, annotated datasets cover only a small sample of the concepts, yet concept normalizers are expected to predict all concepts in the ontology.In this paper, we propose an architecture consisting of a candidate generator and a list-wise ranker based on BERT.The ranker considers pairings of concept mentions and candidate concepts, allowing it to make predictions for any concept, not just those seen during training.We further enhance this list-wise approach with a semantic type regularizer that allows the model to incorporate semantic type information from the ontology during training.Our proposed concept normalization framework achieves stateof-the-art performance on multiple datasets.

Named entity recognition identifies common classes of entities in text, but these entity labels are generally sparse, limiting utility to downstream tasks. In this work we present ScienceExamCER, a densely-labeled semantic classification corpus of 133k mentions in the science exam domain where nearly all (96%) of content words have been annotated with one or more fine-grained semantic class labels including taxonomic groups, meronym groups, verb/action groups, properties and values, and synonyms. Semantic class labels are drawn from a manually-constructed fine-grained typology of 601 classes generated through a data-driven analysis of 4,239 science exam questions. We show an off-the-shelf BERT-based named entity recognition model modified for multi-label classification achieves an accuracy of 0.85 F1 on this task, suggesting strong utility for downstream tasks in science domain question answering requiring densely-labeled semantic classification.