Proceedings ArticleDOI
Noise-Contrastive Estimation for Answer Selection with Deep Neural Networks
Jinfeng Rao,Hua He,Jimmy Lin +2 more
- pp 1913-1916
Reads0
Chats0
TLDR
The Noise-Contrastive Estimation approach is extended with a triplet ranking loss function to exploit interactions in triplet inputs over the question paired with positive and negative examples and achieves state-of-the-art effectiveness without the need for external knowledge sources or feature engineering.Abstract:
We study answer selection for question answering, in which given a question and a set of candidate answer sentences, the goal is to identify the subset that contains the answer. Unlike previous work which treats this task as a straightforward pointwise classification problem, we model this problem as a ranking task and propose a pairwise ranking approach that can directly exploit existing pointwise neural network models as base components. We extend the Noise-Contrastive Estimation approach with a triplet ranking loss function to exploit interactions in triplet inputs over the question paired with positive and negative examples. Experiments on TrecQA and WikiQA datasets show that our approach achieves state-of-the-art effectiveness without the need for external knowledge sources or feature engineering.read more
Citations
More filters
Posted Content
Bilateral Multi-Perspective Matching for Natural Language Sentences
TL;DR: This work proposes a bilateral multi-perspective matching (BiMPM) model under the "matching-aggregation" framework that achieves the state-of-the-art performance on all tasks.
Journal ArticleDOI
A Deep Look into neural ranking models for information retrieval
Jiafeng Guo,Yixing Fan,Liang Pang,Liu Yang,Qingyao Ai,Hamed Zamani,Chen Wu,W. Bruce Croft,Xueqi Cheng +8 more
TL;DR: A deep look into the neural ranking models from different dimensions is taken to analyze their underlying assumptions, major design principles, and learning strategies to obtain a comprehensive empirical understanding of the existing techniques.
Proceedings ArticleDOI
Improved Lexically Constrained Decoding for Translation and Monolingual Rewriting
J. Edward Hu,Huda Khayrallah,Ryan Culkin,Patrick Xia,Tongfei Chen,Matt Post,Benjamin Van Durme +6 more
TL;DR: The authors describe vectorized dynamic beam allocation, which extends work in lexically-constrained decoding to work with batching, leading to a five-fold improvement in throughput when working with positive constraints.
Proceedings Article
Polisis: Automated Analysis and Presentation of Privacy Policies Using Deep Learning
TL;DR: In this paper, the authors propose an automated framework for privacy Policies analysis, called Polisis, which enables scalable, dynamic, and multi-dimensional queries on privacy policies, and demonstrate the modularity and utility with two robust applications that support structured and free-form querying.
Posted Content
Semantic Sentence Matching with Densely-connected Recurrent and Co-attentive Information
TL;DR: The authors proposed a densely-connected co-attentive recurrent neural network (C-RNN), which uses concatenated information of attentive features as well as hidden features of all the preceding recurrent layers.
References
More filters
Proceedings ArticleDOI
Glove: Global Vectors for Word Representation
TL;DR: A new global logbilinear regression model that combines the advantages of the two major model families in the literature: global matrix factorization and local context window methods and produces a vector space with meaningful substructure.
Proceedings Article
Distributed Representations of Words and Phrases and their Compositionality
TL;DR: This paper presents a simple method for finding phrases in text, and shows that learning good vector representations for millions of phrases is possible and describes a simple alternative to the hierarchical softmax called negative sampling.
Proceedings Article
Signature Verification using a "Siamese" Time Delay Neural Network
TL;DR: An algorithm for verification of signatures written on a pen-input tablet based on a novel, artificial neural network called a "Siamese" neural network, which consists of two identical sub-networks joined at their outputs.
Journal ArticleDOI
Signature verification using a “siamese” time delay neural network
Jane Bromley,James W. Bentz,James W. Bentz,Léon Bottou,Léon Bottou,Isabelle Guyon,Yann LeCun,Cliff Moore,Cliff Moore,E. Sackinger,Roopak Shah +10 more
TL;DR: In this article, a Siamese time delay neural network is used to measure the similarity between pairs of signatures, and the output of this half network is the feature vector for the input signature.
Journal ArticleDOI
ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs
TL;DR: This paper proposed three attention schemes that integrate mutual influence between sentences into CNNs, thus the representation of each sentence takes into consideration its counterpart, and achieved state-of-the-art performance on answer selection, paraphrase identification, and textual entailment.