scholarly journals Improving Knowledge-Aware Dialogue Generation via Knowledge Base Question Answering

2020 ◽  
Vol 34 (05) ◽  
pp. 9169-9176
Author(s):  
Jian Wang ◽  
Junhao Liu ◽  
Wei Bi ◽  
Xiaojiang Liu ◽  
Kejing He ◽  
...  
Keyword(s):  
Knowledge Base ◽  
Question Answering ◽  
Network Models ◽  
Factual Knowledge ◽  
Generation Model ◽  
Dialogue Systems ◽  
Open Domain ◽  
Neural Network Models ◽  
Benchmark Datasets ◽  
Selection For

Neural network models usually suffer from the challenge of incorporating commonsense knowledge into the open-domain dialogue systems. In this paper, we propose a novel knowledge-aware dialogue generation model (called TransDG), which transfers question representation and knowledge matching abilities from knowledge base question answering (KBQA) task to facilitate the utterance understanding and factual knowledge selection for dialogue generation. In addition, we propose a response guiding attention and a multi-step decoding strategy to steer our model to focus on relevant features for response generation. Experiments on two benchmark datasets demonstrate that our model has robust superiority over compared methods in generating informative and fluent dialogues. Our code is available at https://github.com/siat-nlp/TransDG.

Predicting Lexical Answer Types in Open Domain QA

2012 ◽  
Vol 8 (3) ◽  
pp. 74-88 ◽  
Author(s):  
Alfio Massimiliano Gliozzo ◽  
Aditya Kalyanpur
Keyword(s):  
Knowledge Acquisition ◽  
Knowledge Base ◽  
Large Scale ◽  
Question Answering ◽  
General Purpose ◽  
Open Domain ◽  
Lexical Knowledge ◽  
Research Challenge ◽  
Lexical Knowledge Base

Automatic open-domain Question Answering has been a long standing research challenge in the AI community. IBM Research undertook this challenge with the design of the DeepQA architecture and the implementation of Watson. This paper addresses a specific subtask of Deep QA, consisting of predicting the Lexical Answer Type (LAT) of a question. Our approach is completely unsupervised and is based on PRISMATIC, a large-scale lexical knowledge base automatically extracted from a Web corpus. Experiments on the Jeopardy! data shows that it is possible to correctly predict the LAT in a substantial number of questions. This approach can be used for general purpose knowledge acquisition tasks such as frame induction from text.

scholarly journals O ONTOLOGY-BASED PARAGRAPH EXTRACTION AND CAUSALITY DETECTION-BASED SIMILARITY FOR ANSWERING WHY-QUESTION

2018 ◽  
Vol 11 (1) ◽  
pp. 9
Author(s):  
A A I N Eka Karyawati
Keyword(s):  
Knowledge Base ◽  
Main Part ◽  
Question Answering ◽  
Document Retrieval ◽  
Domain Ontology ◽  
Typical Problem ◽  
Scoring Method ◽  
Method Performance ◽  
Question Answering System ◽  
Selection For

Paragraph extraction is a main part of an automatic question answering system, especially in answering why-question. It is because the answer of a why-question usually contained in one paragraph instead of one or two sentences. There have been some researches on paragraph extraction approaches, but there are still few studies focusing on involving the domain ontology as a knowledge base. Most of the paragraph extraction studies used keyword-based method with small portion of semantic approaches. Thus, the question answering system faces a typical problem often occuring in keyword-based method that is word mismatches problem. The main contribution of this research is a paragraph scoring method that incorporates the TFIDF-based and causality-detection-based similarity. This research is a part of the ontology-based why-question answering method, where ontology is used as a knowledge base for each steps of the method including indexing, question analyzing, document retrieval, and paragraph extraction/selection. For measuring the method performance, the evaluations were conducted by comparing the proposed method over two baselines methods that did not use causality-detection-based similarity. The proposed method shown improvements over the baseline methods regarding MRR (95%, 0.82-0.42), P@1 (105%, 0.78-0.38), P@5(91%, 0.88-0.46), Precision (95%, 0.80-0.41), and Recall (66%, 0.88-0.53).

Information theoretic subset selection for neural network models

1998 ◽  
Vol 22 (4-5) ◽  
pp. 613-626 ◽  
Author(s):  
Dasaratha V. Sridhar ◽  
Eric B. Bartlett ◽  
Richard C. Seagrave
Keyword(s):  
Neural Network ◽  
Subset Selection ◽  
Network Models ◽  
Neural Network Models ◽  
Information Theoretic ◽  
Selection For

scholarly journals Reinforcement adaptation of an attention-based neural natural language generator for spoken dialogue systems

2019 ◽  
Vol 10 (1) ◽  
pp. 1-19
Author(s):  
Matthieu Riou ◽  
Bassam Jabaian ◽  
Stéphane Huet ◽  
Fabrice Lefèvre
Keyword(s):  
Natural Language ◽  
Short Term Memory ◽  
Network Models ◽  
Dialogue Systems ◽  
Neural Network Models ◽  
Spoken Dialogue Systems ◽  
Spoken Dialogue ◽  
Automatic Transcription ◽  
Long Short Term Memory ◽  
Expected Payoffs

Following some recent propositions to handle natural language generation in spoken dialogue systems with long short-term memory recurrent neural network models~\citep{Wen2016a} we first investigate a variant thereof with the objective of a better integration of the attention subnetwork. Then our next objective is to propose and evaluate a framework to adapt the NLG module online through direct interactions with the users. When doing so the basic way is to ask the user to utter an alternative sentence to express a particular dialogue act. But then the system has to decide between using an automatic transcription or to ask for a manual transcription. To do so a reinforcement learning approach based on an adversarial bandit scheme is retained. We show that by defining appropriately the rewards as a linear combination of expected payoffs and costs of acquiring the new data provided by the user, a system design can balance between improving the system's performance towards a better match with the user's preferences and the burden associated with it. Then the actual benefits of this system is assessed with a human evaluation, showing that the addition of more diverse utterances allows to produce sentences more satisfying for the user.

Dual Gated Graph Attention Networks with Dynamic Iterative Training for Cross-Lingual Entity Alignment

2022 ◽  
Vol 40 (3) ◽  
pp. 1-30
Author(s):  
Zhiwen Xie ◽  
Runjie Zhu ◽  
Kunsong Zhao ◽  
Jin Liu ◽  
Guangyou Zhou ◽  
...  
Keyword(s):  
Neural Network ◽  
Structural Information ◽  
Contextual Information ◽  
Network Models ◽  
Neural Network Models ◽  
Attention Networks ◽  
Individual Knowledge ◽  
Benchmark Datasets ◽  
Cross Lingual ◽  
Network Approaches

Cross-lingual entity alignment has attracted considerable attention in recent years. Past studies using conventional approaches to match entities share the common problem of missing important structural information beyond entities in the modeling process. This allows graph neural network models to step in. Most existing graph neural network approaches model individual knowledge graphs (KGs) separately with a small amount of pre-aligned entities served as anchors to connect different KG embedding spaces. However, this characteristic can cause several major problems, including performance restraint due to the insufficiency of available seed alignments and ignorance of pre-aligned links that are useful in contextual information in-between nodes. In this article, we propose DuGa-DIT, a dual gated graph attention network with dynamic iterative training, to address these problems in a unified model. The DuGa-DIT model captures neighborhood and cross-KG alignment features by using intra-KG attention and cross-KG attention layers. With the dynamic iterative process, we can dynamically update the cross-KG attention score matrices, which enables our model to capture more cross-KG information. We conduct extensive experiments on two benchmark datasets and a case study in cross-lingual personalized search. Our experimental results demonstrate that DuGa-DIT outperforms state-of-the-art methods.

Multi-task learning model for aspect term extraction and aspect polarity classification based on dual-labels

2020 ◽  
Vol 39 (3) ◽  
pp. 2763-2774
Author(s):  
Biqing Zeng ◽  
Feng Zeng ◽  
Heng Yang ◽  
Wu Zhou ◽  
Ruyang Xu
Keyword(s):  
Language Processing ◽  
Network Models ◽  
Learning Model ◽  
Neural Network Models ◽  
Task Learning ◽  
Term Extraction ◽  
Proposed Model ◽  
Great Performance ◽  
Benchmark Datasets ◽  
Polarity Classification

Aspect-based sentiment analysis (ABSA) is a hot and significant task of natural language processing, which is composed of two subtasks, the aspect term extraction (ATE) and aspect polarity classification (APC). Previous researches generally studied two subtasks independently and designed neural network models for ATE and APC respectively. However, it integrates various manual features into the model, which will consume plenty of computing resources and labor. Moreover, the quality of the ATE results will affect the performance of APC. This paper proposes a multi-task learning model based on dual auxiliary labels for ATE and APC. In this paper, general IOB labels, and sentimental IOB labels are equipped to efficiently solve both ATE and APC tasks without manual features adopted. Experiments are conducted on two general ABSA benchmark datasets of SemEval-2014. The experimental results reveal that the proposed model is of great performance and efficient for both ATE and APC tasks compared to the main baseline models.

scholarly journals An Empirical Study on Deep Neural Network Models for Chinese Dialogue Generation

Symmetry ◽  
2020 ◽  
Vol 12 (11) ◽  
pp. 1756
Author(s):  
Zhe Li ◽  
Mieradilijiang Maimaiti ◽  
Jiabao Sheng ◽  
Zunwang Ke ◽  
Wushour Silamu ◽  
...  
Keyword(s):  
Neural Network ◽  
Empirical Study ◽  
Deep Neural Network ◽  
Question Answering ◽  
State Of The Art ◽  
Network Models ◽  
Superior Performance ◽  
Research Progress ◽  
Neural Network Models ◽  
Wide Range

The task of dialogue generation has attracted increasing attention due to its diverse downstream applications, such as question-answering systems and chatbots. Recently, the deep neural network (DNN)-based dialogue generation models have achieved superior performance against conventional models utilizing statistical machine learning methods. However, despite that an enormous number of state-of-the-art DNN-based models have been proposed, there lacks detailed empirical comparative analysis for them on the open Chinese corpus. As a result, relevant researchers and engineers might find it hard to get an intuitive understanding of the current research progress. To address this challenge, we conducted an empirical study for state-of-the-art DNN-based dialogue generation models in various Chinese corpora. Specifically, extensive experiments were performed on several well-known single-turn and multi-turn dialogue corpora, including KdConv, Weibo, and Douban, to evaluate a wide range of dialogue generation models that are based on the symmetrical architecture of Seq2Seq, RNNSearch, transformer, generative adversarial nets, and reinforcement learning respectively. Moreover, we paid special attention to the prevalent pre-trained model for the quality of dialogue generation. Their performances were evaluated by four widely-used metrics in this area: BLEU, pseudo, distinct, and rouge. Finally, we report a case study to show example responses generated by these models separately.

Sign in / Sign up

Export Citation Format

Share Document