Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userAdaptive Information Seeking for Open-Domain Question Answering
معلومات تكيف تسعى للحصول على سؤال مفتوح
424
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تعد المعلومات التي تطلبها خطوة أساسية للسؤال المفتوح الإجابة على جمع الأدلة الكفاءة من كوربوس كبيرة. في الآونة الأخيرة، أثبتت النهج التكرارية أن تكون فعالة للأسئلة المعقدة، من خلال استرداد أدلة جديدة بشكل متكرر في كل خطوة. ومع ذلك، فإن جميع الأساليب التكرارية الحالية تقريبا تستخدم استراتيجيات محددة مسبقا، إما تطبيق نفس وظيفة الاسترجاع عدة مرات أو إصلاح ترتيب وظائف استرجاع مختلفة، والتي لا يمكنها الوفاء بالمتطلبات المتنوعة من الأسئلة المختلفة. في هذه الورقة، نقترح استراتيجية رواية تكيفية تسعى للحصول على معلومات عن أسئلة مفتوحة، وهي AISO. على وجه التحديد، يتم تصميم عملية الاسترجاع والأجوبة بأكملها كعملية اتخاذ قرار Markov الملحوظ جزئيا، حيث يتم تعريف ثلاثة أنواع من عمليات استرجاع (مثل E.G.، BM25 و DPR وارتباط التشعبي) وعملية إجابة واحدة كإجراءات. وفقا للسياسة المستفادة، يمكن ل AISO اختيار إجراءات استرجاع مناسبة ستكيفا للبحث عن الأدلة المفقودة في كل خطوة، بناء على الأدلة التي تم جمعها واستفسلة إعادة صياغة، أو إخراج الإجابة مباشرة عندما تكون مجموعة الأدلة كافية للسؤال. تبين تجارب في تشكيلة مفتوحة و hotpotqa fullwiki، التي تخدم مع معايير قافلة واحدة مفتوحة ومتعددة النطاق، أن AISO تفوقت على جميع الأساليب الأساسية مع استراتيجيات محددة مسبقا فيما يتعلق بتقييمات الاسترجاع والإجابة.
Information seeking is an essential step for open-domain question answering to efficiently gather evidence from a large corpus. Recently, iterative approaches have been proven to be effective for complex questions, by recursively retrieving new evidence at each step. However, almost all existing iterative approaches use predefined strategies, either applying the same retrieval function multiple times or fixing the order of different retrieval functions, which cannot fulfill the diverse requirements of various questions. In this paper, we propose a novel adaptive information-seeking strategy for open-domain question answering, namely AISO. Specifically, the whole retrieval and answer process is modeled as a partially observed Markov decision process, where three types of retrieval operations (e.g., BM25, DPR, and hyperlink) and one answer operation are defined as actions. According to the learned policy, AISO could adaptively select a proper retrieval action to seek the missing evidence at each step, based on the collected evidence and the reformulated query, or directly output the answer when the evidence set is sufficient for the question. Experiments on SQuAD Open and HotpotQA fullwiki, which serve as single-hop and multi-hop open-domain QA benchmarks, show that AISO outperforms all baseline methods with predefined strategies in terms of both retrieval and answer evaluations.
References used
https://aclanthology.org/
rate research
Read More
Multilingual question answering tasks typically assume that answers exist in the same language as the question. Yet in practice, many languages face both information scarcity---where languages have few reference articles---and information asymmetry--
-where questions reference concepts from other cultures. This work extends open-retrieval question answering to a cross-lingual setting enabling questions from one language to be answered via answer content from another language. We construct a large-scale dataset built on 40K information-seeking questions across 7 diverse non-English languages that TyDi QA could not find same-language answers for. Based on this dataset, we introduce a task framework, called Cross-lingual Open-Retrieval Question Answering (XOR QA), that consists of three new tasks involving cross-lingual document retrieval from multilingual and English resources. We establish baselines with state-of-the-art machine translation systems and cross-lingual pretrained models. Experimental results suggest that XOR QA is a challenging task that will facilitate the development of novel techniques for multilingual question answering. Our data and code are available at https://nlp.cs.washington.edu/xorqa/.
Readers of academic research papers often read with the goal of answering specific questions. Question Answering systems that can answer those questions can make consumption of the content much more efficient. However, building such tools requires da
ta that reflect the difficulty of the task arising from complex reasoning about claims made in multiple parts of a paper. In contrast, existing information-seeking question answering datasets usually contain questions about generic factoid-type information. We therefore present Qasper, a dataset of 5049 questions over 1585 Natural Language Processing papers. Each question is written by an NLP practitioner who read only the title and abstract of the corresponding paper, and the question seeks information present in the full text. The questions are then answered by a separate set of NLP practitioners who also provide supporting evidence to answers. We find that existing models that do well on other QA tasks do not perform well on answering these questions, underperforming humans by at least 27 F1 points when answering them from entire papers, motivating further research in document-grounded, information-seeking QA, which our dataset is designed to facilitate.
Recent advances in open-domain QA have led to strong models based on dense retrieval, but only focused on retrieving textual passages. In this work, we tackle open-domain QA over tables for the first time, and show that retrieval can be improved by a
retriever designed to handle tabular context. We present an effective pre-training procedure for our retriever and improve retrieval quality with mined hard negatives. As relevant datasets are missing, we extract a subset of Natural Questions (Kwiatkowski et al., 2019) into a Table QA dataset. We find that our retriever improves retrieval results from 72.0 to 81.1 recall@10 and end-to-end QA results from 33.8 to 37.7 exact match, over a BERT based retriever.
In open-domain question answering (QA), retrieve-and-read mechanism has the inherent benefit of interpretability and the easiness of adding, removing, or editing knowledge compared to the parametric approaches of closed-book QA models. However, it is
also known to suffer from its large storage footprint due to its document corpus and index. Here, we discuss several orthogonal strategies to drastically reduce the footprint of a retrieve-and-read open-domain QA system by up to 160x. Our results indicate that retrieve-and-read can be a viable option even in a highly constrained serving environment such as edge devices, as we show that it can achieve better accuracy than a purely parametric model with comparable docker-level system size.
Many datasets have been created for training reading comprehension models, and a natural question is whether we can combine them to build models that (1) perform better on all of the training datasets and (2) generalize and transfer better to new dat
asets. Prior work has addressed this goal by training one network simultaneously on multiple datasets, which works well on average but is prone to over- or under-fitting different sub- distributions and might transfer worse compared to source models with more overlap with the target dataset. Our approach is to model multi-dataset question answering with an ensemble of single-dataset experts, by training a collection of lightweight, dataset-specific adapter modules (Houlsby et al., 2019) that share an underlying Transformer model. We find that these Multi-Adapter Dataset Experts (MADE) outperform all our baselines in terms of in-distribution accuracy, and simple methods based on parameter-averaging lead to better zero-shot generalization and few-shot transfer performance, offering a strong and versatile starting point for building new reading comprehension systems.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
