Improving Semantic Parsing via Answer Type Inference

@inproceedings{Yavuz2016ImprovingSP,
  title={Improving Semantic Parsing via Answer Type Inference},
  author={Semih Yavuz and Izzeddin Gur and Yu Su and Mudhakar Srivatsa and Xifeng Yan},
  booktitle={EMNLP},
  year={2016}
}
In this work, we show the possibility of inferring the answer type before solving a factoid question and leveraging the type information to improve semantic parsing. By replacing the topic entity in a question with its type, we are able to generate an abstract form of the question, whose answer corresponds to the answer type of the original question. A bidirectional LSTM model is built to train over the abstract form of questions and infer their answer types. It is also observed that if we… 
Efficiency-aware Answering of Compositional Questions using Answer Type Prediction
TLDR
Experiments show that TIPI results in state-of-the-art performance under the real-world assumption that only a single SPARQL query can be executed over the KB, and substantial reduction in the number of queries in the more general case.
Knowledge Base Question Answering With a Matching-Aggregation Model and Question-Specific Contextual Relations
TLDR
This paper explores the use of a “matching-aggregation” framework to match candidate answers with questions and makes use of question-specific contextual relations to enhance the representations of candidate answer entities.
Novel knowledge-based system with relation detection and textual evidence for question answering research
TLDR
This work proposes a novel Question Answering method with Relation Detection and Textual Evidence (QARDTE), which uses bidirectional long-short term memory networks with different levels of abstraction to better capture sentence structures and addresses the semantic gap problem in relation detection.
Recovering Question Answering Errors via Query Revision
TLDR
This work proposes to crosscheck the corresponding KB relations behind the predicted answers and identifies potential inconsistencies to improve the F1 score of STAGG, one of the leading QA systems, from 52.5% to 53.9% on WEBQUESTIONS data.
Improving Semantic Parsing with Neural Generator-Reranker Architecture
TLDR
A generator-reranker architecture for semantic parsing that consists of a pre-processing step for the candidates followed by a novel critic network, which reranks these candidates based on the similarity between each candidate and the input sentence.
A Methodology for Hierarchical Classification of Semantic Answer Types of Questions
TLDR
This work proposes a 3-step approach for answer type prediction using the datasets provided for the ISWC 2020 SMART Task Challenge, which starts with building a classifier that predicts the category of the types and builds another classifier just for resource types.
Bidirectional Attentive Memory Networks for Question Answering over Knowledge Bases
TLDR
This work proposes to directly model the two-way flow of interactions between the questions and the KB via a novel Bidirectional Attentive Memory Network, called BAMnet, and significantly outperforms existing information-retrieval based methods, and remains competitive with (hand-crafted) semantic parsing based methods.
Fine and Ultra-Fine Entity Type Embeddings for Question Answering
TLDR
This work proposes a flexible framework for both entity types using paragraph vectors and word embeddings to obtain high quality contextualized question representations and augment the document similarity provided by paragraph vectors with semantic modeling and sentence alignment using word embeddeddings.
Question Answering in Knowledge Bases
TLDR
A novel model architecture, APVA, which takes advantage of KB-based information to improve relation prediction but verifies the correctness of the predicted relation by means of simple negative sampling in a logistic regression framework is presented.
Learning to Paraphrase for Question Answering
TLDR
This paper presents a general framework which learns felicitous paraphrases for various QA tasks and shows that this framework consistently improves performance, achieving competitive results despite the use of simple QA models.
...
1
2
3
4
...

References

SHOWING 1-10 OF 35 REFERENCES
Semantic Parsing on Freebase from Question-Answer Pairs
TLDR
This paper trains a semantic parser that scales up to Freebase and outperforms their state-of-the-art parser on the dataset of Cai and Yates (2013), despite not having annotated logical forms.
Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base
TLDR
This work proposes a novel semantic parsing framework for question answering using a knowledge base that leverages the knowledge base in an early stage to prune the search space and thus simplifies the semantic matching problem.
Question Answering on Freebase via Relation Extraction and Textual Evidence
TLDR
This work first presents a neural network based relation extractor to retrieve the candidate answers from Freebase, and then infer over Wikipedia to validate these answers, a substantial improvement over the state-of-the-art.
Semantic Parsing via Paraphrasing
TLDR
This paper presents two simple paraphrase models, an association model and a vector space model, and trains them jointly from question-answer pairs, improving state-of-the-art accuracies on two recently released question-answering datasets.
Open Domain Question Answering via Semantic Enrichment
TLDR
A new QA system that mines answers directly from the Web, and meanwhile employs KBs as a significant auxiliary to further boost the QA performance, and makes the first attempt to link answer candidates to entities in Freebase, during answer candidate generation.
Scaling Semantic Parsers with On-the-Fly Ontology Matching
TLDR
A new semantic parsing approach that learns to resolve ontological mismatches, which is learned from question-answer pairs, uses a probabilistic CCG to build linguistically motivated logicalform meaning representations, and includes an ontology matching model that adapts the output logical forms for each target ontology.
Joint Relational Embeddings for Knowledge-based Question Answering
TLDR
This paper proposes a novel embedding-based approach that maps NL-questions into LFs for KBQA by leveraging semantic associations between lexical representations and KBproperties in the latent space.
Knowledge-Based Question Answering as Machine Translation
TLDR
A translation-based approach to solve knowledge-based question answering tasks in one unified framework based on CYK parsing, which achieves better results than previous methods.
Information Extraction over Structured Data: Question Answering with Freebase
TLDR
It is shown that relatively modest information extraction techniques, when paired with a webscale corpus, can outperform these sophisticated approaches by roughly 34% relative gain.
Learning Question Classifiers
  • Xin Li, D. Roth
  • Computer Science
    COLING
  • 2002
TLDR
A hierarchical classifier is learned that is guided by a layered semantic hierarchy of answer types, and eventually classifies questions into fine-grained classes.
...
1
2
3
4
...