scholarly journals Complex Program Induction for Querying Knowledge Bases in the Absence of Gold Programs

2019 ◽  
Vol 7 ◽  
pp. 185-200 ◽  
Author(s):  
Amrita Saha ◽  
Ghulam Ahmed Ansari ◽  
Abhishek Laddha ◽  
Karthik Sankaranarayanan ◽  
Soumen Chakrabarti
Keyword(s):  
Natural Language ◽  
Question Answering ◽  
Knowledge Bases ◽  
Combinatorial Explosion ◽  
Complex Queries ◽  
Present Complex ◽  
Complex Program ◽  
Natural Language Query ◽  
High Level ◽  
Complex Question

Recent years have seen increasingly complex question-answering on knowledge bases (KBQA) involving logical, quantitative, and comparative reasoning over KB subgraphs. Neural Program Induction (NPI) is a pragmatic approach toward modularizing the reasoning process by translating a complex natural language query into a multi-step executable program. While NPI has been commonly trained with the ‘‘gold’’ program or its sketch, for realistic KBQA applications such gold programs are expensive to obtain. There, practically only natural language queries and the corresponding answers can be provided for training. The resulting combinatorial explosion in program space, along with extremely sparse rewards, makes NPI for KBQA ambitious and challenging. We present Complex Imperative Program Induction from Terminal Rewards (CIPITR), an advanced neural programmer that mitigates reward sparsity with auxiliary rewards, and restricts the program space to semantically correct programs using high-level constraints, KB schema, and inferred answer type. CIPITR solves complex KBQA considerably more accurately than key-value memory networks and neural symbolic machines (NSM). For moderately complex queries requiring 2- to 5-step programs, CIPITR scores at least 3× higher F1 than the competing systems. On one of the hardest class of programs (comparative reasoning) with 5–10 steps, CIPITR outperforms NSM by a factor of 89 and memory networks by 9 times. 1

scholarly journals Neural Program Induction for KBQA Without Gold Programs or Query Annotations

2019 ◽  
Author(s):  
Ghulam Ahmed Ansari ◽  
Amrita Saha ◽  
Vishwajeet Kumar ◽  
Mohan Bhambhani ◽  
Karthik Sankaranarayanan ◽  
...  
Keyword(s):  
Question Answering ◽  
State Of The Art ◽  
Knowledge Bases ◽  
Neural Models ◽  
Input Program ◽  
Correct Program ◽  
Final Answer ◽  
High Level ◽  
Executable Programs ◽  
Complex Question

Neural Program Induction (NPI) is a paradigm for decomposing high-level tasks such as complex question-answering over knowledge bases (KBQA) into executable programs by employing neural models. Typically, this involves two key phases: i) inferring input program variables from the high-level task description, and ii) generating the correct program sequence involving these variables. Here we focus on NPI for Complex KBQA with only the final answer as supervision, and not gold programs. This raises major challenges; namely, i) noisy query annotation in the absence of any supervision can lead to catastrophic forgetting while learning, ii) reward becomes extremely sparse owing to the noise. To deal with these, we propose a noise-resilient NPI model, Stable Sparse Reward based Programmer (SSRP) that evades noise-induced instability through continual retrospection and its comparison with current learning behavior. On complex KBQA datasets, SSRP performs at par with hand-crafted rule-based models when provided with gold program input, and in the noisy settings outperforms state-of-the-art models by a significant margin even with a noisier query annotator.

scholarly journals Composing Questions through Conceptual Authoring

2007 ◽  
Vol 33 (1) ◽  
pp. 105-133 ◽  
Author(s):  
Catalina Hallett ◽  
Donia Scott ◽  
Richard Power
Keyword(s):  
Natural Language ◽  
Question Answering ◽  
Free Text ◽  
Risk Averse ◽  
Proof Of Concept ◽  
Concept System ◽  
Complex Queries ◽  
Extensive Training ◽  
Question Answering Systems ◽  
Medical Histories

This article describes a method for composing fluent and complex natural language questions, while avoiding the standard pitfalls of free text queries. The method, based on Conceptual Authoring, is targeted at question-answering systems where reliability and transparency are critical, and where users cannot be expected to undergo extensive training in question composition. This scenario is found in most corporate domains, especially in applications that are risk-averse. We present a proof-of-concept system we have developed: a question-answering interface to a large repository of medical histories in the area of cancer. We show that the method allows users to successfully and reliably compose complex queries with minimal training.

scholarly journals Formal Query Building with Query Structure Prediction for Complex Question Answering over Knowledge Base

2020 ◽  
Author(s):  
Yongrui Chen ◽  
Huiying Li ◽  
Yuncheng Hua ◽  
Guilin Qi
Keyword(s):  
Knowledge Base ◽  
Structure Prediction ◽  
Question Answering ◽  
State Transition ◽  
Knowledge Bases ◽  
Second Stage ◽  
Transition Strategy ◽  
Query Structure ◽  
Two Stages ◽  
Complex Question

Formal query building is an important part of complex question answering over knowledge bases. It aims to build correct executable queries for questions. Recent methods try to rank candidate queries generated by a state-transition strategy. However, this candidate generation strategy ignores the structure of queries, resulting in a considerable number of noisy queries. In this paper, we propose a new formal query building approach that consists of two stages. In the first stage, we predict the query structure of the question and leverage the structure to constrain the generation of the candidate queries. We propose a novel graph generation framework to handle the structure prediction task and design an encoder-decoder model to predict the argument of the predetermined operation in each generative step. In the second stage, we follow the previous methods to rank the candidate queries. The experimental results show that our formal query building approach outperforms existing methods on complex questions while staying competitive on simple questions.

scholarly journals Differentiable Reasoning on Large Knowledge Bases and Natural Language

2020 ◽  
Vol 34 (04) ◽  
pp. 5182-5190
Author(s):  
Pasquale Minervini ◽  
Matko Bošnjak ◽  
Tim Rocktäschel ◽  
Sebastian Riedel ◽  
Edward Grefenstette
Keyword(s):  
Natural Language ◽  
Link Prediction ◽  
Question Answering ◽  
Knowledge Bases ◽  
Small Scale ◽  
Reasoning Systems ◽  
Novel Approach ◽  
Real World Datasets ◽  
Interpretable Models ◽  
Machine Reading

Reasoning with knowledge expressed in natural language and Knowledge Bases (KBs) is a major challenge for Artificial Intelligence, with applications in machine reading, dialogue, and question answering. General neural architectures that jointly learn representations and transformations of text are very data-inefficient, and it is hard to analyse their reasoning process. These issues are addressed by end-to-end differentiable reasoning systems such as Neural Theorem Provers (NTPs), although they can only be used with small-scale symbolic KBs. In this paper we first propose Greedy NTPs (GNTPs), an extension to NTPs addressing their complexity and scalability limitations, thus making them applicable to real-world datasets. This result is achieved by dynamically constructing the computation graph of NTPs and including only the most promising proof paths during inference, thus obtaining orders of magnitude more efficient models 1. Then, we propose a novel approach for jointly reasoning over KBs and textual mentions, by embedding logic facts and natural language sentences in a shared embedding space. We show that GNTPs perform on par with NTPs at a fraction of their cost while achieving competitive link prediction results on large datasets, providing explanations for predictions, and inducing interpretable models.

scholarly journals Introducing External Knowledge to Answer Questions with Implicit Temporal Constraints over Knowledge Base

2020 ◽  
Vol 12 (3) ◽  
pp. 45
Author(s):  
Wenqing Wu ◽  
Zhenfang Zhu ◽  
Qiang Lu ◽  
Dianyuan Zhang ◽  
Qiangqiang Guo
Keyword(s):  
Natural Language ◽  
Knowledge Base ◽  
Question Answering ◽  
Knowledge Bases ◽  
Temporal Information ◽  
Temporal Constraints ◽  
External Knowledge ◽  
Question Answering Systems ◽  
Natural Language Question ◽  
Applied Knowledge

Knowledge base question answering (KBQA) aims to analyze the semantics of natural language questions and return accurate answers from the knowledge base (KB). More and more studies have applied knowledge bases to question answering systems, and when using a KB to answer a natural language question, there are some words that imply the tense (e.g., original and previous) and play a limiting role in questions. However, most existing methods for KBQA cannot model a question with implicit temporal constraints. In this work, we propose a model based on a bidirectional attentive memory network, which obtains the temporal information in the question through attention mechanisms and external knowledge. Specifically, we encode the external knowledge as vectors, and use additive attention between the question and external knowledge to obtain the temporal information, then further enhance the question vector to increase the accuracy. On the WebQuestions benchmark, our method not only performs better with the overall data, but also has excellent performance regarding questions with implicit temporal constraints, which are separate from the overall data. As we use attention mechanisms, our method also offers better interpretability.

scholarly journals Knowledge bases and description logics applications to natural language texts analysis

2020 ◽  
pp. 259-269
Author(s):  
H.I. Hoherchak ◽  
Keyword(s):  
Natural Language ◽  
Language Processing ◽  
Question Answering ◽  
Semantic Analysis ◽  
Description Logics ◽  
Knowledge Bases ◽  
Parts Of Speech ◽  
Resolution Problem ◽  
Concepts Of Knowledge ◽  
Speech Tagging

The article describes some ways of knowledge bases application to natural language texts analysis and solving some of their processing tasks. The basic problems of natural language processing are considered, which are the basis for their semantic analysis: problems of tokenization, parts of speech tagging, dependency parsing, correference resolution. The basic concepts of knowledge bases theory are presented and the approach to their filling based on Universal Dependencies framework and the correference resolution problem is proposed. Examples of applications for knowledge bases filled with natural language texts in practical problems are given, including checking constructed syntactic and semantic models for consistency and question answering.

scholarly journals Natural Language Query Based Question Answering System

2020 ◽  
Vol 9 (3) ◽  
pp. 2977-2981
Keyword(s):  
Natural Language ◽  
Comparative Study ◽  
Question Answering ◽  
Question Answering System ◽  
Natural Language Query ◽  
User Queries

Development of natural language query based automatic question answering system is in huge demand these days and is a rapidly growing field. It is considered to be the most powerful application for answering different user queries not only on limited domains but also in multi domain environments. In this work, a natural language query based intelligible question answering system is presented that extracts relevant answers from the documents and present the answer in a pre-defined format to the user. A comparative study of the presented model with the traditional techniques is also presented.

scholarly journals Special Thematic Section on Semantic Models for Natural Language Processing (Preface)

2018 ◽  
Vol 18 (1) ◽  
pp. 93-94
Author(s):  
Kiril Simov ◽  
Petya Osenova
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Question Answering ◽  
Open Data ◽  
Knowledge Bases ◽  
Lexical Resources ◽  
Text Simplification ◽  
Semantic Models ◽  
Semantic Resources

Abstract With the availability of large language data online, cross-linked lexical resources (such as BabelNet, Predicate Matrix and UBY) and semantically annotated corpora (SemCor, OntoNotes, etc.), more and more applications in Natural Language Processing (NLP) have started to exploit various semantic models. The semantic models have been created on the base of LSA, clustering, word embeddings, deep learning, neural networks, etc., and abstract logical forms, such as Minimal Recursion Semantics (MRS) or Abstract Meaning Representation (AMR), etc. Additionally, the Linguistic Linked Open Data Cloud has been initiated (LLOD Cloud) which interlinks linguistic data for improving the tasks of NLP. This cloud has been expanding enormously for the last four-five years. It includes corpora, lexicons, thesauri, knowledge bases of various kinds, organized around appropriate ontologies, such as LEMON. The semantic models behind the data organization as well as the representation of the semantic resources themselves are a challenge to the NLP community. The NLP applications that extensively rely on the above discussed models include Machine Translation, Information Extraction, Question Answering, Text Simplification, etc.

scholarly journals A Knowledge-Based Sense Disambiguation Method to Semantically Enhanced NL Question for Restricted Domain

Information ◽  
2021 ◽  
Vol 12 (11) ◽  
pp. 452
Author(s):  
Ammar Arbaaeen ◽  
Asadullah Shah
Keyword(s):  
Natural Language ◽  
Language Processing ◽  
Question Answering ◽  
Word Sense Disambiguation ◽  
Knowledge Bases ◽  
Word Sense ◽  
Intended Meaning ◽  
Lexical Semantic ◽  
Knowledge Based ◽  
Sense Disambiguation

Within the space of question answering (QA) systems, the most critical module to improve overall performance is question analysis processing. Extracting the lexical semantic of a Natural Language (NL) question presents challenges at syntactic and semantic levels for most QA systems. This is due to the difference between the words posed by a user and the terms presently stored in the knowledge bases. Many studies have achieved encouraging results in lexical semantic resolution on the topic of word sense disambiguation (WSD), and several other works consider these challenges in the context of QA applications. Additionally, few scholars have examined the role of WSD in returning potential answers corresponding to particular questions. However, natural language processing (NLP) is still facing several challenges to determine the precise meaning of various ambiguities. Therefore, the motivation of this work is to propose a novel knowledge-based sense disambiguation (KSD) method for resolving the problem of lexical ambiguity associated with questions posed in QA systems. The major contribution is the proposed innovative method, which incorporates multiple knowledge sources. This includes the question’s metadata (date/GPS), context knowledge, and domain ontology into a shallow NLP. The proposed KSD method is developed into a unique tool for a mobile QA application that aims to determine the intended meaning of questions expressed by pilgrims. The experimental results reveal that our method obtained comparable and better accuracy performance than the baselines in the context of the pilgrimage domain.

Software architecture of the question-answering subsystem with elements of self-learning

2021 ◽  
Vol 26 (jai2021.26(2)) ◽  
pp. 88-95
Author(s):  
Hlybovets A ◽  
◽  
Tsaruk A ◽  
Keyword(s):  
Natural Language ◽  
Language Processing ◽  
Speech Synthesis ◽  
Question Answering ◽  
Building Blocks ◽  
Knowledge Bases ◽  
Learning Technologies ◽  
Software Systems ◽  
Question Answering Systems ◽  
Self Learning

Within the framework of this paper, the analysis of software systems of question-answering type and their basic architectures has been carried out. With the development of machine learning technologies, creation of natural language processing (NLP) engines, as well as the rising popularity of virtual personal assistant programs that use the capabilities of speech synthesis (text-to-speech), there is a growing need in developing question-answering systems which can provide personalized answers to users' questions. All modern cloud providers proposed frameworks for organization of question answering systems but still we have a problem with personalized dialogs. Personalization is very important, it can put forward additional demands to a question-answering system’s capabilities to take this information into account while processing users’ questions. Traditionally, a question-answering system (QAS) is developed in the form of an application that contains a knowledge base and a user interface, which provides a user with answers to questions, and a means of interaction with an expert. In this article we analyze modern approaches to architecture development and try to build system from the building blocks that already exist on the market. Main criteria for the NLP modules were: support of the Ukrainian language, natural language understanding, functions of automatic definition of entities (attributes), ability to construct a dialogue flow, quality and completeness of documentation, API capabilities and integration with external systems, possibilities of external knowledge bases integration After provided analyses article propose the detailed architecture of the question-answering subsystem with elements of self-learning in the Ukrainian language. In the work you can find detailed description of main semantic components of the system (architecture components)

Sign in / Sign up

Export Citation Format

Share Document