![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
244 Result(s)
-
Chapter and Conference Paper
Out-of-Domain Semantics to the Rescue! Zero-Shot Hybrid Retrieval Models
The pre-trained language model (eg, BERT) based deep retrieval models achieved superior performance over lexical retrieval models (eg, BM25) in many passage retrieval tasks. However, limited work has been done to...
-
Chapter and Conference Paper
Incorporating Feature Labeling into Crowdsourcing for More Accurate Aggregation Labels
Crowdsourcing is a popular way of collecting crowd wisdom and has been deployed in various senarios. Effective answer collection and answer aggregation are two important crowdsourcing topics as workers may give i...
-
Chapter and Conference Paper
Incorporating Complete Syntactical Knowledge for Spoken Language Understanding
Spoken Language Processing (SLU) is important in task-oriented dialog systems. Intent detection and slot filling are two significant tasks of SLU. State-of-the-art methods for SLU jointly solve these two tasks...
-
Chapter and Conference Paper
CSDQA: Diagram Question Answering in Computer Science
Visual Question Answering (VQA) has been a research focus of the computer vision community for recent years. Most of them are accomplished and verified on images of natural scenes. However, Diagram Question An...
-
Chapter and Conference Paper
SPAN: Subgraph Prediction Attention Network for Dynamic Graphs
This paper proposes a novel model for predicting subgraphs in dynamic graphs, an extension of traditional link prediction. This proposed end-to-end model learns a map** from the subgraph structures in the cu...
-
Chapter and Conference Paper
Generating Pseudo Connectives with MLMs for Implicit Discourse Relation Recognition
Due to the lack of connectives, the recognition of implicit discourse relations faces a big challenge. An early attempt overcomes this difficulty by predicting connectives with the use of the statistical langu...
-
Chapter and Conference Paper
Generating Short Product Descriptors Based on Very Little Training Data
We propose a pipeline model for summarising a short textual product description for inclusion in an online advertisement banner. While a standard approach is to truncate the advertiser’s original product descr...
-
Chapter and Conference Paper
Near-Duplicate Video Retrieval Through Toeplitz Kernel Partial Least Squares
The existence of huge volumes of near-duplicate videos shows a rising demand on effective near-duplicate video retrieval technique in copyright violation and search result re-ranking. In this paper, Kernel Par...
-
Chapter and Conference Paper
Research on Fine-Grained Sentiment Classification
Aiming at the fine-grained sentiment classification that distinguishes the emotional intensity, the commonly used dataset SST-1 is analyzed in depth. Through the analysis, it is found that the dataset has ser...
-
Chapter and Conference Paper
Classification over Clustering: Augmenting Text Representation with Clusters Helps!
Considering that words with different characteristic in the text have different importance for classification, grou** them together separately can strengthen the semantic expression of each part. Thus we pro...
-
Chapter and Conference Paper
Domain Information Enhanced Dependency Parser
Dependency parsing has been an important task in the natural language processing (NLP) community. Supervised methods have achieved great success these years. However, these models can suffer significant perfor...
-
Chapter and Conference Paper
Learning Relational Fractals for Deep Knowledge Graph Embedding in Online Social Networks
Knowledge Graphs (KGs) have deep and impactful applications in a wide-array of information networks such as natural language processing, recommendation systems, predictive analysis, recognition, classificatio...
-
Chapter and Conference Paper
Correction to: Filtering Techniques for Regular Expression Matching in Strings
The original version of the chapter starting on p. 118 was revised.
-
Chapter and Conference Paper
Filtering Techniques for Regular Expression Matching in Strings
Matching a regular expression (regex) on a text is widely used in many applications, such as text editing, information extraction and instruction detection (IDS). Traditional algorithms generally compile an eq...
-
Chapter and Conference Paper
Emotion Classification with Data Augmentation Using Generative Adversarial Networks
It is a difficult task to classify images with multiple class labels using only a small number of labeled examples, especially when the label (class) distribution is imbalanced. Emotion classification is such ...
-
Chapter and Conference Paper
Text Generation Based on Generative Adversarial Nets with Latent Variables
In this paper, we propose a model using generative adversarial net (GAN) to generate realistic text. Instead of using standard GAN, we combine variational autoencoder (VAE) with generative adversarial net. The...
-
Chapter and Conference Paper
Convolutional Neural Networks for Text Classification with Multi-size Convolution and Multi-type Pooling
Text classification is a very important problem in Nature Language Processing (NLP). The text classification based on shallow machine-learning models takes too much time and energy to extract features of data,...
-
Chapter and Conference Paper
Enhanced Embedding Based Attentive Pooling Network for Answer Selection
Document-based Question Answering tries to rank the candidate answers for given questions, which needs to evaluate matching score between the question sentence and answer sentence. Existing works usually utili...
-
Chapter and Conference Paper
Model and Practice of Crowd-Based Education
Based on connectivism pedagogy crowd-based education provides a practical method to extensively exploit wisdoms of core learners in education organization and external crowds on Internet. However, when applyin...
-
Chapter and Conference Paper
SeRI: A Dataset for Sub-event Relation Inference from an Encyclopedia
Mining sub-event relations of major events is an important research problem, which is useful for building event taxonomy, event knowledge base construction, and natural language understanding. To advance the s...