The Web as a Knowledge-Base for Answering Complex Questions

@inproceedings{Talmor2018TheWA,
  title={The Web as a Knowledge-Base for Answering Complex Questions},
  author={Alon Talmor and Jonathan Berant},
  booktitle={NAACL},
  year={2018}
}
Answering complex questions is a time-consuming activity for humans that requires reasoning and integration of information. [] Key Method To illustrate the viability of our approach, we create a new dataset of complex questions, ComplexWebQuestions, and present a model that decomposes questions and interacts with the web to compute an answer. We empirically demonstrate that question decomposition improves performance from 20.8 precision@1 to 27.5 precision@1 on this new dataset.
Learning to Answer Complex Questions over Knowledge Bases with Query Composition
TLDR
A KB-QA system, TextRay, is proposed, which answers complex questions using a novel decompose-execute-join approach and uses a semantic matching model which is able to learn simple queries using implicit supervision from question-answer pairs, thus eliminating the need for complex query patterns.
Complex Knowledge Base Question Answering: A Survey
TLDR
A review of recent advances on KBQA with the focus on solving complex questions, which usually contain multiple subjects, express compound relations, or involve numerical operations, and two mainstream categories of methods, namely semantic parsing- based (SP-based) methods and information retrieval-based (IR) methods.
Answering Open-Domain Questions of Varying Reasoning Steps from Text
TLDR
A unified system to answer directly from text open-domain questions that may require a varying number of retrieval steps, using a single multi-task transformer model to perform all the necessary subtasks in an iterative fashion.
A Benchmark for Generalizable and Interpretable Temporal Question Answering over Knowledge Bases
TLDR
This paper presents a benchmark dataset for temporal reasoning, TempQA-WD, based on Wikidata, which is the most frequently curated, openly available knowledge base and generalizes to multiple knowledge bases: Freebase andWikidata.
A Survey on Complex Question Answering over Knowledge Base: Recent Advances and Challenges
TLDR
The recent advances in complex QA are introduced, the methods of these branches are described, directions for future research are analyzed and the models proposed by the Alime team are introduced.
A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutions
TLDR
This paper elaborately summarize the typical challenges and solutions for complex KBQA, and presents the two mainstream categories of methods, namely semantic parsing-based (SP-based) methods and information retrieval-based [IR-based] methods.
ConditionalQA: A Complex Reading Comprehension Dataset with Conditional Answers
TLDR
It is shown that ConditionalQA is challenging for many of the existing QA models, especially in selecting answer conditions, and will motivate further research in answering complex questions over long documents.
Answering Complex Questions by Combining Information from Curated and Extracted Knowledge Bases
TLDR
A novel KB-QA system, Multique, is presented, which can map a complex question to a complex query pattern using a sequence of simple queries each targeted at a specific KB.
KQA Pro: A Dataset with Explicit Compositional Programs for Complex Question Answering over Knowledge Base
TLDR
Experimental results show that state-of-the-art KBQA methods cannot achieve promising results on KQA Pro as on current datasets, which suggests that K QA Pro is challenging and Complex KBZA requires further research efforts.
Answering Complex Open-domain Questions Through Iterative Query Generation
TLDR
This work presents GoldEn (Gold Entity) Retriever, which iterates between reading context and retrieving more supporting documents to answer open-domain multi-hop questions, and demonstrates that it outperforms the best previously published model despite not using pretrained language models such as BERT.
...
...

References

SHOWING 1-10 OF 45 REFERENCES
Evaluating Semantic Parsing against a Simple Web-based Question Answering Model
TLDR
This paper proposes to evaluate semantic parsing-based question answering models by comparing them to a question answering baseline that queries the web and extracts the answer only from web snippets, without access to the target knowledge-base, and finds that this approach achieves reasonable performance.
Answering Complicated Question Intents Expressed in Decomposed Question Sequences
TLDR
This work collects a dataset of 6,066 question sequences that inquire about semi-structured tables from Wikipedia, with 17,553 question-answer pairs in total, and proposes strategies to handle questions that contain coreferences to previous questions or answers.
Question Answering from Unstructured Text by Retrieval and Comprehension
TLDR
This work presents a two-step approach to question answering from unstructured text, consisting of a retrieval step and a comprehension step, featuring an RNN based attention model with a novel mixture mechanism for selecting answers from either retrieved articles or a fixed vocabulary.
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.
Compositional Semantic Parsing on Semi-Structured Tables
TLDR
This paper proposes a logical-form driven parsing algorithm guided by strong typing constraints and shows that it obtains significant improvements over natural baselines and is made publicly available.
Constraint-Based Question Answering with Knowledge Graph
TLDR
A novel systematic KBQA approach to solve multi-constraint questions is proposed, which not only obtains comparable results on the two existing benchmark data-sets, but also achieves significant improvements on the ComplexQuestions.
SQuAD: 100,000+ Questions for Machine Comprehension of Text
TLDR
A strong logistic regression model is built, which achieves an F1 score of 51.0%, a significant improvement over a simple baseline (20%).
TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
TLDR
It is shown that, in comparison to other recently introduced large-scale datasets, TriviaQA has relatively complex, compositional questions, has considerable syntactic and lexical variability between questions and corresponding answer-evidence sentences, and requires more cross sentence reasoning to find answers.
The Value of Semantic Parse Labeling for Knowledge Base Question Answering
TLDR
The value of collecting semantic parse labels for knowledge base question answering is demonstrated and the largest semantic-parse labeled dataset to date is created and shared in order to advance research in question answering.
MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
TLDR
This new dataset is aimed to overcome a number of well-known weaknesses of previous publicly available datasets for the same task of reading comprehension and question answering, and is the most comprehensive real-world dataset of its kind in both quantity and quality.
...
...