Modeling Context in Answer Sentence Selection Systems on a Latency Budget

• URL: http://arxiv.org/abs/2101.12093v1
• Date: Thu, 28 Jan 2021 16:24:48 GMT
• Title: Modeling Context in Answer Sentence Selection Systems on a Latency Budget
• Authors: Rujun Han, Luca Soldaini, Alessandro Moschitti
• Abstract summary: We present an approach to efficiently incorporate contextual information in AS2 models. For each answer candidate, we first use unsupervised similarity techniques to extract relevant sentences from its source document. Our best approach, which leverages a multi-way attention architecture to efficiently encode context, improves 6% to 11% over nonanswer state of the art in AS2 with minimal impact on system latency.
• Score: 87.45819843513598
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Answer Sentence Selection (AS2) is an efficient approach for the design of open-domain Question Answering (QA) systems. In order to achieve low latency, traditional AS2 models score question-answer pairs individually, ignoring any information from the document each potential answer was extracted from. In contrast, more computationally expensive models designed for machine reading comprehension tasks typically receive one or more passages as input, which often results in better accuracy. In this work, we present an approach to efficiently incorporate contextual information in AS2 models. For each answer candidate, we first use unsupervised similarity techniques to extract relevant sentences from its source document, which we then feed into an efficient transformer architecture fine-tuned for AS2. Our best approach, which leverages a multi-way attention architecture to efficiently encode context, improves 6% to 11% over noncontextual state of the art in AS2 with minimal impact on system latency. All experiments in this work were conducted in English.

Related papers

• Datasets for Multilingual Answer Sentence Selection [59.28492975191415]
  We introduce new high-quality datasets for AS2 in five European languages (French, German, Italian, Portuguese, and Spanish) Results indicate that our datasets are pivotal in producing robust and powerful multilingual AS2 models.
  arXiv  Detail & Related papers  (2024-06-14T16:50:29Z)
• In Situ Answer Sentence Selection at Web-scale [120.69820139008138]
  Passage-based Extracting Answer Sentence In-place (PEASI) is a novel design for AS2 optimized for Web-scale setting. We train PEASI in a multi-task learning framework that encourages feature sharing between the components: passage reranker and passage-based answer sentence extractor. Experiments show PEASI effectively outperforms the current state-of-the-art setting for AS2, i.e., a point-wise model for ranking sentences independently, by 6.51% in accuracy.
  arXiv  Detail & Related papers  (2022-01-16T06:36:00Z)
• Reference-based Weak Supervision for Answer Sentence Selection using Web Data [87.18646699292293]
  We introduce Reference-based Weak Supervision (RWS), a fully automatic large-scale data pipeline. RWS harvests high-quality weakly-supervised answers from abundant Web data. Our experiments indicate that the produced data consistently bolsters TANDA.
  arXiv  Detail & Related papers  (2021-04-18T19:41:17Z)
• Tradeoffs in Sentence Selection Techniques for Open-Domain Question Answering [54.541952928070344]
  We describe two groups of models for sentence selection: QA-based approaches, which run a full-fledged QA system to identify answer candidates, and retrieval-based models, which find parts of each passage specifically related to each question. We show that very lightweight QA models can do well at this task, but retrieval-based models are faster still.
  arXiv  Detail & Related papers  (2020-09-18T23:39:15Z)
• A Study on Efficiency, Accuracy and Document Structure for Answer Sentence Selection [112.0514737686492]
  In this paper, we argue that by exploiting the intrinsic structure of the original rank together with an effective word-relatedness encoder, we can achieve competitive results. Our model takes 9.5 seconds to train on the WikiQA dataset, i.e., very fast in comparison with the $sim 18$ minutes required by a standard BERT-base fine-tuning.
  arXiv  Detail & Related papers  (2020-03-04T22:12:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.