Joint Multitask Learning for Community Question Answering Using Task-Specific Embeddings

2018-09-24 · EMNLP 2018 10 · Shafiq Joty, Lluis Marquez, Preslav Nakov

We address jointly two important tasks for Question Answering in community forums: given a new question, (i) find related existing questions, and (ii) find relevant answers to this new question. We further use an auxiliary task to complement the previous two, i.e., (iii) find good answers with respect to the thread question in a question-comment thread. We use deep neural networks (DNNs) to learn meaningful task-specific embeddings, which we then incorporate into a conditional random field (CRF) model for the multitask setting, performing joint learning over a complex graph structure. While DNNs alone achieve competitive results when trained to produce the embeddings, the CRF, which makes use of the embeddings and the dependencies between the tasks, improves the results significantly and consistently across a variety of evaluation metrics, thus showing the complementarity of DNNs and structured learning.

📄 PDF Abstract BibTeX arXiv:1809.08928

Code (0)

등록된 구현이 없습니다.

Tasks

Community Question Answering Question Answering

Methods 이 논문이 사용한 방법론

CRF Conditional Random Fields or CRFs are a type of probabilistic graph model that take neighboring sample context into account for tasks like classification. Prediction is…

Effective shared representations with Multitask Learning for Community Question Answering

2017-04-01 · EACL 2017 4 · Daniele Bonadiman, Antonio Uva, Aless Moschitti, ro

An important asset of using Deep Neural Networks (DNNs) for text applications is their ability to automatically engineering features. Unfortunately, DNNs usually require a lot of training data, especially for highly sema…

Community Question Answering Document Ranking Named Entity Recognition (NER)Question Answering

Multitask Learning with Deep Neural Networks for Community Question Answering

2017-02-13 · Daniele Bonadiman, Antonio Uva, Alessandro Moschitti

In this paper, we developed a deep neural network (DNN) that learns to solve simultaneously the three tasks of the cQA challenge proposed by the SemEval-2016 Task 3, i.e., question-comment similarity, question-question s…

Community Question Answering Feature Engineering Question Answering Question Similarity

Recurrent Neural Network Encoder with Attention for Community Question Answering

2016-03-23 · Wei-Ning Hsu, Yu Zhang, James Glass

We apply a general recurrent neural network (RNN) encoder framework to community question answering (cQA) tasks. Our approach does not rely on any linguistic processing, and can be applied to different languages or domai…

Community Question Answering Information Retrieval Question Answering Retrieval+1

The Natural Language Decathlon: Multitask Learning as Question Answering

2018-06-20 · ICLR 2019 5 · Bryan McCann, Nitish Shirish Keskar, Caiming Xiong, Richard Socher

Deep learning has improved performance on many natural language processing (NLP) tasks individually. However, general NLP models cannot emerge within a paradigm that focuses on the particularities of a single metric, dat…

Decoder Domain Adaptation Machine Translation Named Entity Recognition+10

Consecutive Question Generation with Multitask Joint Reranking and Dynamic Rationale Search

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Automatic question generation (QG) aims to generate a set of questions for a given passage, and can be viewed as a dual task of question answering (QA). However, most current methods of QG tend to generate question by qu…

Diversity Informativeness Question Answering Question Generation+3