• Corpus ID: 2278470

LSTM-based Deep Learning Models for non-factoid answer selection

  title={LSTM-based Deep Learning Models for non-factoid answer selection},
  author={Ming Tan and Bing Xiang and Bowen Zhou},
In this paper, we apply a general deep learning (DL) framework for the answer selection task, which does not depend on manually defined features or linguistic tools. [] Key Method One direction is to define a more composite representation for questions and answers by combining convolutional neural network with the basic framework. The other direction is to utilize a simple but efficient attention mechanism in order to generate the answer representation according to the question context.

Figures and Tables from this paper

Inner Attention Based bi-LSTMs with Indexing for non-Factoid Question Answering

This paper focussed on non-factoid question answering problem using a bidirectional LSTM with an inner attention mechanism and indexing for better accuracy and showed an improvement in accuracy over the referred model and respective baselines and also with respect to the answer lengths.

A Stacked BiLSTM Neural Network Based on Coattention Mechanism for Question Answering

A stacked Bidirectional Long Short-Term Memory (BiLSTM) neural network based on the coattention mechanism to extract the interaction between questions and answers, combining cosine similarity and Euclidean distance to score the question and answer sentences is proposed.

Combine multi-features with deep learning for answer selection

This paper develops a basic framework based on bidirectional long short term memory (Bi-LSTM), and then it extracts lexical and topic features in question and answer respectively, and append these features to Bi-L STM models.

Research on Question-Answering System Based on Deep Learning

The proposed model employs a bidirectional long-short term memory (BLSTM) to solve the problem of lack features and uses the attention mechanism which allows the question to focus on a certain part of the candidate answer.

LSTM-based Deep Learning Models for Answer Ranking

This paper defines a composite representation for questions and answers by combining convolutional neural network (CNN) with bidirectional long short-term memory (biLSTM) models, and learns a similarity function to relate them in a supervised way from the available training data.

Question-Question Similarity in Online Forums

In this paper, we applied deep learning framework to tackle the tasks of finding duplicate questions. We implemented some models following the siamese architecture using the popular recurrent network

Attention-based neural network for short-text question answering

An attention-based convolutional neural network model is proposed to obtain word- and phrase-level interactive information and generate correct probability to re-rank candidate answers and results show that the proposed model can obtain a significant performance improvement.

Two layers LSTM with attention for multi-choice question answering in exams

This paper uses general deep learning model to solve the multi-choice question answering task and builds distributed word embedding of question and answers instead of manually extracting features or linguistic tools, meanwhile, for improving the accuracy, the external corpus is introduced.

Multi-Modal Similarity Metric Learning for Answer Selection

A deep convolutional network is constituted directly on pairwise token matching, multi-modal similarity metric learning is then adopted to enrich the lexical modality matching and demonstrates its performance by surpassing previous state-of-the-art systems on the answer selection benchmark.

Full-Time Supervision based Bidirectional RNN for Factoid Question Answering

A novel BRNN model called full-time supervision based BRNN (FTS-BRNN), which can put supervision at every time step is proposed and can outperform other baselines to achieve the state-of-the-art accuracy.



Applying deep learning to answer selection: A study and an open task

A general deep learning framework is applied to address the non-factoid question answering task and demonstrates superior performance compared to the baseline methods and various technologies give further improvements.

Deep Learning for Answer Sentence Selection

This work proposes a novel approach to solving the answer sentence selection task via means of distributed representations, and learns to match questions with answers by considering their semantic encoding.

Weakly Supervised Memory Networks

This paper introduces a variant of Memory Networks that needs significantly less supervision to perform question and answering tasks and applies it to the synthetic bAbI tasks, showing that the approach is competitive with the supervised approach, particularly when trained on a sufficiently large amount of data.

Question Answering Using Enhanced Lexical Semantic Models

This work focuses on improving the performance using models of lexical semantic resources and shows that these systems can be consistently and significantly improved with rich lexical semantics information, regardless of the choice of learning algorithms.

A Neural Attention Model for Sentence Summarization

This work proposes a fully data-driven approach to abstractive sentence summarization by utilizing a local attention-based model that generates each word of the summary conditioned on the input sentence.

Sequence to Sequence Learning with Neural Networks

This paper presents a general end-to-end approach to sequence learning that makes minimal assumptions on the sequence structure, and finds that reversing the order of the words in all source sentences improved the LSTM's performance markedly, because doing so introduced many short term dependencies between the source and the target sentence which made the optimization problem easier.

Answer Extraction as Sequence Tagging with Tree Edit Distance

A linear-chain Conditional Random Field based on pairs of questions and their possible answer sentences, learning the association between questions and answer types is constructed, casting answer extraction as an answer sequence tagging problem for the first time.

End-To-End Memory Networks

A neural network with a recurrent attention model over a possibly large external memory that is trained end-to-end, and hence requires significantly less supervision during training, making it more generally applicable in realistic settings.

What is the Jeopardy Model? A Quasi-Synchronous Grammar for QA

A probabilistic quasi-synchronous grammar, inspired by one proposed for machine translation, and parameterized by mixtures of a robust nonlexical syntax/alignment model with a(n optional) lexical-semantics-driven log-linear model is proposed.

Learning deep structured semantic models for web search using clickthrough data

A series of new latent semantic models with a deep structure that project queries and documents into a common low-dimensional space where the relevance of a document given a query is readily computed as the distance between them are developed.