What is the Jeopardy Model? A Quasi-Synchronous Grammar for QA

By Mengqiu Wang, Noah A. Smith, Teruko Mitamura. 2007

475 citations recorded by the source corpus.

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

Know What You Don’t Know: Unanswerable Questions for SQuAD (2018, methodology): “Wang et al. (2007) constructed the QAS ENT dataset from questions in the TREC 8-13 QA tracks.”
A Neural Network for Factoid Question Answering over Paragraphs (2014, background): “A promising avenue for future work would be to incorporate Wikipedia data into qanta by transforming sentences to look like quiz bowl questions (Wang et al., 2007) and to select relevant sentences, as not every sentence in a Wikipedia article directly describes its subject.”
Key-Value Memory Networks for Directly Reading Documents (2016, methodology): “For this reason, recent initiatives are returning to the original setting of directly answering from text us-ing datasets like T REC QA (Wang et al. , 2007), based on classical T REC resources (Voorhees et al. , 1999), and W IKI QA (Yang et al. , 2015), extracted from Wikipedia.”
WikiQA: A Challenge Dataset for Open-Domain Question Answering (2015, methodology): “In order to eliminate answer sentence biases caused by keyword matching, we consider all the sentences in 1The policy is adopted both by the official QASENT tracks (Voorhees and Tice, 1999) and by Wang et al. (2007).”
How Much Reading Does Reading Comprehension Require? A Critical Investigation of Popular Benchmarks (2018, background): “…Lai et al., 2017; Weston et al., 2016; Miller et al., 2016), span selection (Rajpurkar et al., 2016; Trischler et al., 2017), sentence retrieval (Wang et al., 2007; Yang et al., 2015), or free-form answer generation (Nguyen et al., 2016).1 Researchers have steadily advanced on these…”
Neural Variational Inference for Text Processing (2015, methodology): “QASent (Wang et al., 2007) is created from the TREC QA track, and the WikiQA (Yang et al.”
ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs (2015, methodology): “…examples include methods based on deeper semantic analysis (Shen and Lapata, 2007; Moldovan et al., 2007), tree edit-distance (Punyakanok et al., 2004; Heilman and Smith, 2010) and quasi-synchronous grammars (Wang et al., 2007) that match the dependency parse trees of the two sentences.”
Machine Comprehension with Syntax, Frames, and Semantics (2015, background): “Our simple rule set is inspired by the rich history of QA research into modeling syntactic transformations between questions and answers (Moschitti et al., 2007; Wang et al., 2007; Heilman and Smith, 2010).”
Complex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graph (2018, background): “These datasets can be divided into 5 main types (i) TREC style Open Domain QA (Voorhees and Tice 2000; Wang, Smith, and Mitamura 2007; Yang, Yih, and Meek 2015) where the aim is to answer a question from a collection of documents (ii) factoid QA over structured knowledge graphs (Berant et al. 2013;…”
Attentive Pooling Networks (2016, methodology): “TREC-QA 3 was created by Wang et al. (2007) based on Text REtrieval Conference (TREC) QA track (8-13) data.”
Pairwise Word Interaction Modeling with Deep Neural Networks for Semantic Similarity Measurement (2016, methodology): “The TrecQA dataset (Wang et al., 2007) from the Text Retrieval Conferences has been widely used for the answer selection task during the past decade.”
Bilateral Multi-Perspective Matching for Natural Language Sentences (2017, methodology): “We experiment on two datasets: TREC-QA [ Wang et al. , 2007 ] and WikiQA [ Yang et al. , 2015 ] .”
Universal Conceptual Cognitive Annotation (UCCA) (2013, background): “Examples include text simpliﬁcation (e.g., for second language teaching) (Siddharthan, 2006), para-phrase detection (Dolan et al., 2004), summarization (Knight and Marcu, 2000), and question answering (Wang et al., 2007).”
Rethinking Search: Making Experts out of Dilettantes (2021, background): “Early research into question answering systems primarily focused on ranking and retrieval, whereby models are trained to learn a relevance score between a user question and candidate answers [75, 81, 92, 104].”
Answer Extraction as Sequence Tagging with Tree Edit Distance (2013, methodology): “Such relations have been used in prior approaches to this task (Wang et al., 2007; Wang and Manning, 2010), but not in conjunction with the model of Heilman and Smith (2010).”
Open-Retrieval Conversational Question Answering (2020, background): “As a result, many popular QA tasks and datasets either follow an answer selection setting [16, 47, 57] or a machine comprehension setting [23, 35, 36, 44].”
Paraphrase Identification as Probabilistic Quasi-Synchronous Recognition (2009, methodology): “Since it loosely links the two sentences’ syntactic structures, QG is well suited for problems like word alignment for MT (Smith and Eisner, 2006) and question answering (Wang et al., 2007).”
Modelling input texts: from Tree Kernels to Deep Learning (2015, methodology): “[175], which appears to be one of the most widely used benchmarks for answer sentence reranking.”