前言

自從小夕前不久推送了這篇《文本匹配打卡點(diǎn)總結(jié)》，收到了不少小伙伴對于問答方向的問題，其中問的最多的就是，求！更！多！論！文！好了，于是小夕就在萬能的知乎上找到了這篇良心回答，分享給有需要的小伙伴們~下面的內(nèi)容就轉(zhuǎn)載自知乎用戶Y.Shu的回答，傳送門如下（關(guān)注問答、閱讀理解的小伙伴們快去關(guān)注一波良心答主）

https://www.zhihu.com/question/349499033/answer/900173774

非事實(shí)類問題

大多數(shù)研究關(guān)注于事實(shí)類問題，而非事實(shí)類問題的研究相對不足，包括數(shù)學(xué)類的問題、判斷類的問題等。

[EMNLP 2019] NumNet: Machine Reading Comprehension with Numerical Reasoning 數(shù)學(xué)類問題

[NAACL19] MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms

[NAACL19] BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions

多跳推理

多跳（multi-hop）在最近的頂會上關(guān)注度非常高，目前實(shí)現(xiàn)這一機(jī)制的方法也比較復(fù)雜。

[EMNLP 2019] What's Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answering

[EMNLP 2019] Self-Assembling Modular Networks for Interpretable Multi-Hop Reasoning

[EMNLP 2019] Avoiding Reasoning Shortcuts: Adversarial Evaluation, Training, and Model Development for Multi-Hop QA

[ACL 2019] Multi-Hop Paragraph Retrieval for Open-Domain Question Answering

[ACL 2019] Dynamically Fused Graph Network for Multi-hop Reasoning

[ACL 2019] Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension

[ACL 2019] Multi-hop Reading Comprehension through Question Decomposition and Rescoring

[ACL 2019] Compositional Questions Do Not Necessitate Multi-hop Reasoning

[ACL 2019] Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extraction

[ACL 2019] Cognitive Graph for Multi-Hop Reading Comprehension at Scale

[ACL 2019] Understanding Dataset Design Choices for Multi-hop Reasoning

[NAACL 2019] Repurposing Entailment for Multi-Hop Question Answering Tasks

[NAACL 2019] BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering

[ACL 2019] Exploiting Explicit Paths for Multi-hop Reading Comprehension

[ACL 2019] Multi-hop reading comprehension across multiple documents by reasoning over heterogeneous graphs

多語言/跨語言的問答

包括英法德等主流語言之間的研究，也包括特定于使用人數(shù)較少的語言的研究。

[EMNLP 2019] Cross-Lingual Machine Reading Comprehension

[EMNLP 2019] BiPaR: A Bilingual Parallel Dataset for Multilingual and Cross-lingual Reading Comprehension Novels

[ACL 2019] XQA: A Cross-lingual Open-domain Question Answering Dataset

知識庫問答和基于文本的問答的結(jié)合

前者通常是限定域的，知識容量有限，結(jié)構(gòu)化信息比較好查詢；后者通常是開放域的，信息量很大，但是提取知識比較困難。

[EMNLP 2019] Language Models as Knowledge Bases? 探索語言模型作為知識來源的可能性
[ACL 2019] Interpretable Question Answering on Knowledge Bases and Text

[ACL 2019] Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension

[EMNLP 2019] Incorporating External Knowledge into Machine Reading for Generative Question Answering

長文本/多段落

MRC 的研究在向多段落/長文本擴(kuò)展。

[EMNLP 2019] BookQA: Stories of Challenges and Opportunities

[ACL 2019] Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives

[ACL 2019] ELI5: Long Form Question Answering

[ACL 2018] Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification

[ACL 2019] Token-level Dynamic Self-Attention Network for Multi-Passage Reading Comprehension

[EMNLP 2019] Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering

[ACL 2019] Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension

[ACL 2019] Multi-hop reading comprehension across multiple documents by reasoning over heterogeneous graphs

[EMNLP19]?PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text

QA 系統(tǒng)的可解釋性

比如可以將對答案的解釋也作為訓(xùn)練數(shù)據(jù)的一部分，讓模型學(xué)會解釋。

[NAACL 2019] Enhancing Key-Value Memory Neural Networks for Knowledge Based Question Answering

[EMNLP 2017] QUINT: Interpretable Question Answering over Knowledge Bases

[ACL 2019] Interpretable Question Answering on Knowledge Bases and Text

[ACL 2019] Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension

不可回答的問題

這個(gè)問題包括無法回答的問題和合理答案的判別兩個(gè)任務(wù)。

[AAAI 2019] Read + Verify: Machine Reading Comprehension with Unanswerable Questions

[ACL 2019] Learning to Ask Unanswerable Questions for Machine Reading Comprehension

數(shù)據(jù)集的構(gòu)建

更實(shí)用、智能、強(qiáng)大的 QA 系統(tǒng)需要更多優(yōu)質(zhì)的數(shù)據(jù)集來推動(dòng)。

[EMNLP 2019] BiPaR: A Bilingual Parallel Dataset for Multilingual and Cross-lingual Reading Comprehension on Novels 多語言與跨語言的小說閱讀理解

[EMNLP 2019] GeoSQA: A Benchmark for Scenario-based Question Answering in the Geography Domain at High School Level 高中地理場景下的問答基準(zhǔn)測試

[EMNLP 2019] Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning 共指解析問題

[IJCAI 2019] AmazonQA: A Review-Based Question Answering Task 基于評論的問答

[EMNLP 2019] BiPaR: A Bilingual Parallel Dataset for Multilingual and Cross-lingual Reading Comprehension Novels 多語言和跨語言閱讀理解小說的雙語并行數(shù)據(jù)集

[ACL 2019] XQA: A Cross-lingual Open-domain Question Answering Dataset 跨語言開放域問答數(shù)據(jù)集

[ACL 2019] WEETQA: A Social Media Focused Question Answering Dataset 社交媒體問答數(shù)據(jù)集

[EMNLP 2019] A Span-Extraction Dataset for Chinese Machine Reading Comprehension 中文閱讀跨度提取數(shù)據(jù)集

總結(jié)

以上是生活随笔為你收集整理的2019 年，智能问答（Question Answering）的主要研究方向有哪些？的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。