End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension

By Yang Yu, Wei Zhang, Kazi Saidul Hasan, Mo Yu, Bing Xiang, Bowen Zhou. 2016

77 citations recorded by the source corpus.

This paper proposes dynamic chunk reader (DCR), an end-to-end neural reading comprehension (RC) model that is able to extract and rank a set of answer candidates from a given document to answer questions. DCR is able to predict answers of variable lengths, whereas previous neural RC models primarily focused on predicting single tokens or entities. DCR encodes a document and an input question with recurrent neural networks, and then applies a word-by-word attention mechanism to acquire question-aware representations for the document, followed by the generation of chunk representations and a ranking module to propose the top-ranked chunk as the answer. Experimental results show that DCR could achieve a 66.3% Exact match and 74.7% F1 score on the Stanford Question Answering Dataset.

Subfields: Artificial Intelligence, Information Retrieval & Search, Question Answering & Reading Comprehension

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Retrieval & Search

In Question Answering & Reading Comprehension

Citations in the corpus

The Effect of Natural Distribution Shift on Question Answering Models (2020, neutral): “Dynamic Chunk Reader (Single) (Yu et al., 2016) https://worksheets.”
Adversarial Examples for Evaluating Reading Comprehension Systems (2017, methodology): “We also validate our major ﬁndings on twelve other published models with publicly available test-time code: ReasoNet Single and Ensemble versions (Shen et al., 2017), Mnemonic Reader Single and Ensemble versions (Hu et al., 2017), Structural Embedding of Dependency Trees (SEDT) Single and Ensemble v”
Dynamic Coattention Networks For Question Answering (2016, methodology): “…model that consists of a Match-LSTM encoder, originally introduced in Wang & Jiang (2016a), and a pointer network decoder (Vinyals et al., 2015); Yu et al. (2016) introduced a dynamic chunk reader, a neural reading comprehension model that extracts a set of answer candidates of variable lengths…”
Machine Comprehension Using Match-LSTM and Answer Pointer (2016, methodology): “The results of our models as well as the results of the baselines given by Rajpurkar et al. (2016) and Yu et al. (2016) are shown in Table 2.”
Multi-Perspective Context Matching for Machine Comprehension (2016, background): “To increase the recall, Yu et al. (2016) extracted candidate chunks based on some part-of-speech patterns, which made over 90% of the questions answerable.”
Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering (2017, background): “…(Sentence) [Wang and Jiang, 2016] 54.505 67.748 Match-LSTM with Ans-Ptr (Boundary) [Wang and Jiang, 2016] 60.474 70.695 Dynamic Chunk Reader [Yu et al., 2016] 62.499 70.956 Fine-Grained Gating [Yang et al., 2016] 62.446 73.327 Match-LSTM with Bi-Ans-Ptr (Boundary) [Wang and Jiang, 2016]…”
R3: Reinforced Reader-Ranker for Open-Domain Question Answering (2017, methodology): “Dividing the pipeline into IR and RC stages leverages an enormous body of research in both IR and RC, including recent successes in RC via neural network techniques (Wang and Jiang, 2017b; Yu et al., 2016; Wang et al., 2016; Xiong et al., 2017; Wang et al., 2017).”
Words or Characters? Fine-grained Gating for Reading Comprehension (2016, background): “Yu et al. (2016) propose a dynamic chunk reader to extract and rank a set of answer candidates from a given document to answer questions.”
S-Net: From Answer Extraction to Answer Generation for Machine Reading Comprehension (2017, background): “Other works which only focus on the SQuAD dataset may also be applied on the MS-MARCO dataset (Yu et al., 2016; Lee et al., 2016; Yang et al., 2016).”
A Unified Query-based Generative Model for Question Generation and Question Answering (2017, background): “…2016; Wang et al., 2016; Shen et al., 2016; Wang et al., 2017; Chen et al., 2017; Xiong, Zhong, and Socher, 2016; Seo et al., 2016; Lee et al., 2016; Yu et al., 2016; Dhingra et al., 2017) focus on the extractive QA scenario, where they assume that the target answer occurs in the passage verbatim.”
Structural Embedding of Syntactic Trees for Machine Comprehension (2017, background): “One of the main issues in reading comprehension is to identify the latent representations of texts and words [3, 8, 20, 21, 23].”
UvA-DARE (Digital Academic Repository) Learning to Transform, Combine, and Reason in Open-domain Question Answering (unknown): “Neural network based models [25, 27, 36, 43] are the most successful approaches in this area.”