Paraphrase-Driven Learning for Open Question Answering

By Anthony Fader, Luke S. Zettlemoyer, Oren Etzioni. 2013

393 citations recorded by the source corpus.

Subfields: Natural Language Processing, 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 Natural Language Processing

In Question Answering & Reading Comprehension

Citations in the corpus

A Decomposable Attention Model for Natural Language Inference (2016, methodology): “Our method is motivated by the central role played by alignment in machine translation (Koehn, 2009) and previous approaches to sentence similarity modeling (Haghighi et al., 2005; Das and Smith, 2009; Chang et al., 2010; Fader et al., 2013), natural language inference (Marsi and Krahmer, 2005; MacC”
Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks (2015, methodology): “It can be considered the simplest case of some real world QA datasets such as in (Fader et al., 2013).”
VQA: Visual Question Answering (2015, background): “Text-based Q&A is a well studied problem in the NLP and text processing communities (recent examples being [12, 11, 46, 38]).”
Large-scale Simple Question Answering with Memory Networks (2015, methodology): “The Reverb test set, based on the KB of the same name and introduced in (Fader et al., 2013) is used for evaluation only.”
Yin and Yang: Balancing and Answering Binary Visual Questions (2015, background): “Text-based QA is a well studied problem in the natural language processing (NLP) community, recent examples being [14, 15, 33, 40].”
Modeling Biological Processes for Reading Comprehension (2014, methodology): “Such methods rely on redundancy, and are thus suitable for answering common factoid questions which have ample evidence in text (Fader et al., 2013).”
Question Answering with Subgraph Embeddings (2014, methodology): “To overcome this issue, we follow (Fader et al., 2013) and supplement our training data with an indirect supervision signal made of pairs of question paraphrases collected from the WIKIANSWERS website.”
Semantic Parsing via Paraphrasing (2014, methodology): “Fader et al. (2013) presented a QA system that maps questions onto simple queries against Open IE extractions, by learning paraphrases from a large mono-lingual parallel corpus, and performing a single paraphrasing step.”
Scaling Semantic Parsers with On-the-Fly Ontology Matching (2013, methodology): “Fader et al. (2013) recently presented a scalable approach to learning an open domain QA system, where ontological mismatches are resolved with learned paraphrases.”
Building a Semantic Parser Overnight (2015, methodology): “Paraphrasing has been applied to singleproperty question answering (Fader et al., 2013) and semantic parsing (Berant and Liang, 2014).”
Open Question Answering with Weakly Supervised Embedding Models (2014, methodology): “Following [10], we hence decided to create such question-triple pairs automatically.”
Semantic Parsing for Single-Relation Question Answering (2014, methodology): “Following (Huang et al., 2013), for every pattern, the corresponding relation is treated as a positive example and 100 randomly selected other relations are used as negative examples.”
Ask the Right Questions: Active Question Reformulation with Reinforcement Learning (2017, methodology): “The monolingual data is extracted from the Paralex database of question paraphrases [Fader et al., 2013].”
Information Extraction over Structured Data: Question Answering with Freebase (2014, background): “Fader et al. (2013) learned question paraphrases from aligning multiple questions with the same answers generated by WikiAnswers.”
Answering Complex Questions Using Open Information Extraction (2017, methodology): “QA systems using semi-structured Open IE tuples (Fader et al., 2013, 2014; Yin et al., 2015) or automatically extracted web tables (Sun et al., 2016; Pasupat and Liang, 2015) have broader coverage but are limited to simple questions with a single query.”