Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Text": models, code, and papers

GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification

Jul 22, 2019
Jie Zhou, Xu Han, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li, Maosong Sun

Fact verification (FV) is a challenging task which requires to retrieve relevant evidence from plain text and use the evidence to verify given claims. Many claims require to simultaneously integrate and reason over several pieces of evidence for verification. However, previous work employs simple models to extract information from evidence without letting evidence communicate with each other, e.g., merely concatenate the evidence for processing. Therefore, these methods are unable to grasp sufficient relational and logical information among the evidence. To alleviate this issue, we propose a graph-based evidence aggregating and reasoning (GEAR) framework which enables information to transfer on a fully-connected evidence graph and then utilizes different aggregators to collect multi-evidence information. We further employ BERT, an effective pre-trained language representation model, to improve the performance. Experimental results on a large-scale benchmark dataset FEVER have demonstrated that GEAR could leverage multi-evidence information for FV and thus achieves the promising result with a test FEVER score of 67.10%. Our code is available at

* Accepted by ACL 2019 

  Access Paper or Ask Questions

News Labeling as Early as Possible: Real or Fake?

Jun 08, 2019
Maryam Ramezani, Mina Rafiei, Soroush Omranpour, Hamid R. Rabiee

Making disguise between real and fake news propagation through online social networks is an important issue in many applications. The time gap between the news release time and detection of its label is a significant step towards broadcasting the real information and avoiding the fake. Therefore, one of the challenging tasks in this area is to identify fake and real news in early stages of propagation. However, there is a trade-off between minimizing the time gap and maximizing accuracy. Despite recent efforts in detection of fake news, there has been no significant work that explicitly incorporates early detection in its model. In this paper, we focus on accurate early labeling of news, and propose a model by considering earliness both in modeling and prediction. The proposed method utilizes recurrent neural networks with a novel loss function, and a new stopping rule. Given the context of news, we first embed it with a class-specific text representation. Then, we utilize the available public profile of users, and speed of news diffusion, for early labeling of the news. Experiments on real datasets demonstrate the effectiveness of our model both in terms of early labelling and accuracy, compared to the state of the art baseline and models.

  Access Paper or Ask Questions

Semantic Drift in Multilingual Representations

May 02, 2019
Lisa Beinborn, Rochelle Choenni

Multilingual representations have mostly been evaluated based on their performance on specific tasks. In this article, we look beyond engineering goals and analyze the relations between languages in computational representations. We introduce a methodology for comparing languages based on their organization of semantic concepts. We propose to conduct an adapted version of representational similarity analysis of a selected set of concepts in computational multilingual representations. Using this analysis method, we can reconstruct a phylogenetic tree that closely resembles those assumed by linguistic experts. These results indicate that multilingual distributional representations which are only trained on monolingual text and bilingual dictionaries preserve relations between languages without the need for any etymological information. In addition, we propose a measure to identify semantic drift between language families. We perform experiments on word-based and sentence-based multilingual models and provide both quantitative results and qualitative examples. Analyses of semantic drift in multilingual representations can serve two purposes: they can indicate unwanted characteristics of the computational models and they provide a quantitative means to study linguistic phenomena across languages. The code is available at

  Access Paper or Ask Questions

Causality Extraction based on Self-Attentive BiLSTM-CRF with Transferred Embeddings

Apr 29, 2019
Zhaoning Li, Qi Li, Xiaotian Zou, Jiangtao Ren

Causality extraction from natural language texts is a challenging open problem in artificial intelligence. Existing methods utilize patterns, constraints, and machine learning techniques to extract causality, heavily depend on domain knowledge and require considerable human efforts and time on feature engineering. In this paper, we formulate causality extraction as a sequence tagging problem based on a novel causality tagging scheme. On this basis, we propose a neural causality extractor with BiLSTM-CRF model as the backbone, named SCIFI (Self-Attentive BiLSTM-CRF with Flair Embeddings), which can directly extract Cause and Effect, without extracting candidate causal pairs and identifying their relations separately. To tackle the problem of data insufficiency, we transfer the contextual string embeddings, also known as Flair embeddings, which trained on a large corpus into our task. Besides, to improve the performance of causality extraction, we introduce the multi-head self-attention mechanism into SCIFI to learn the dependencies between causal words. We evaluate our method on a public dataset, and experimental results demonstrate that our method achieves significant and consistent improvement as compared to other baselines.

* 36 pages, 9 figures, 5 tables 

  Access Paper or Ask Questions

Neural Chinese Named Entity Recognition via CNN-LSTM-CRF and Joint Training with Word Segmentation

Apr 26, 2019
Fangzhao Wu, Junxin Liu, Chuhan Wu, Yongfeng Huang, Xing Xie

Chinese named entity recognition (CNER) is an important task in Chinese natural language processing field. However, CNER is very challenging since Chinese entity names are highly context-dependent. In addition, Chinese texts lack delimiters to separate words, making it difficult to identify the boundary of entities. Besides, the training data for CNER in many domains is usually insufficient, and annotating enough training data for CNER is very expensive and time-consuming. In this paper, we propose a neural approach for CNER. First, we introduce a CNN-LSTM-CRF neural architecture to capture both local and long-distance contexts for CNER. Second, we propose a unified framework to jointly train CNER and word segmentation models in order to enhance the ability of CNER model in identifying entity boundaries. Third, we introduce an automatic method to generate pseudo labeled samples from existing labeled data which can enrich the training data. Experiments on two benchmark datasets show that our approach can effectively improve the performance of Chinese named entity recognition, especially when training data is insufficient.

* 7 pages, 3 figures, accepted by the 2019 World Wide Web Conference (WWW'19) 

  Access Paper or Ask Questions

Creative Procedural-Knowledge Extraction From Web Design Tutorials

Apr 18, 2019
Longqi Yang, Chen Fang, Hailin Jin, Walter Chang, Deborah Estrin

Complex design tasks often require performing diverse actions in a specific order. To (semi-)autonomously accomplish these tasks, applications need to understand and learn a wide range of design procedures, i.e., Creative Procedural-Knowledge (CPK). Prior knowledge base construction and mining have not typically addressed the creative fields, such as design and arts. In this paper, we formalize an ontology of CPK using five components: goal, workflow, action, command and usage; and extract components' values from online design tutorials. We scraped 19.6K tutorial-related webpages and built a web application for professional designers to identify and summarize CPK components. The annotated dataset consists of 819 unique commands, 47,491 actions, and 2,022 workflows and goals. Based on this dataset, we propose a general CPK extraction pipeline and demonstrate that existing text classification and sequence-to-sequence models are limited in identifying, predicting and summarizing complex operations described in heterogeneous styles. Through quantitative and qualitative error analysis, we discuss CPK extraction challenges that need to be addressed by future research.

  Access Paper or Ask Questions

Data augmentation for low resource sentiment analysis using generative adversarial networks

Feb 18, 2019
Rahul Gupta

Sentiment analysis is a task that may suffer from a lack of data in certain cases, as the datasets are often generated and annotated by humans. In cases where data is inadequate for training discriminative models, generate models may aid training via data augmentation. Generative Adversarial Networks (GANs) are one such model that has advanced the state of the art in several tasks, including as image and text generation. In this paper, I train GAN models on low resource datasets, then use them for the purpose of data augmentation towards improving sentiment classifier generalization. Given the constraints of limited data, I explore various techniques to train the GAN models. I also present an analysis of the quality of generated GAN data as more training data for the GAN is made available. In this analysis, the generated data is evaluated as a test set (against a model trained on real data points) as well as a training set to train classification models. Finally, I also conduct a visual analysis by projecting the generated and the real data into a two-dimensional space using the t-Distributed Stochastic Neighbor Embedding (t-SNE) method.

* Accepted to International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019 

  Access Paper or Ask Questions

SECTOR: A Neural Model for Coherent Topic Segmentation and Classification

Feb 13, 2019
Sebastian Arnold, Rudolf Schneider, Philippe Cudré-Mauroux, Felix A. Gers, Alexander Löser

When searching for information, a human reader first glances over a document, spots relevant sections and then focuses on a few sentences for resolving her intention. However, the high variance of document structure complicates to identify the salient topic of a given section at a glance. To tackle this challenge, we present SECTOR, a model to support machine reading systems by segmenting documents into coherent sections and assigning topic labels to each section. Our deep neural network architecture learns a latent topic embedding over the course of a document. This can be leveraged to classify local topics from plain text and segment a document at topic shifts. In addition, we contribute WikiSection, a publicly available dataset with 242k labeled sections in English and German from two distinct domains: diseases and cities. From our extensive evaluation of 20 architectures, we report a highest score of 71.6% F1 for the segmentation and classification of 30 topics from the English city domain, scored by our SECTOR LSTM model with bloom filter embeddings and bidirectional segmentation. This is a significant improvement of 29.5 points F1 compared to state-of-the-art CNN classifiers with baseline segmentation.

* Author's final version, accepted for publication at TACL, 2019 

  Access Paper or Ask Questions

Exploring RNN-Transducer for Chinese Speech Recognition

Nov 13, 2018
Senmao Wang, Pan Zhou, Wei Chen, Jia Jia, Lei Xie

End-to-end approaches have drawn much attention recently for significantly simplifying the construction of an automatic speech recognition (ASR) system. RNN transducer (RNN-T) is one of the popular end-to-end methods. Previous studies have shown that RNN-T is difficult to train and a very complex training process is needed for a reasonable performance. In this paper, we explore RNN-T for a Chinese large vocabulary continuous speech recognition (LVCSR) task and aim to simplify the training process while maintaining performance. First, a new strategy of learning rate decay is proposed to accelerate the model convergence. Second, we find that adding convolutional layers at the beginning of the network and using ordered data can discard the pre-training process of the encoder without loss of performance. Besides, we design experiments to find a balance among the usage of GPU memory, training circle and model performance. Finally, we achieve 16.9% character error rate (CER) on our test set which is 2% absolute improvement from a strong BLSTM CE system with language model trained on the same text corpus.

  Access Paper or Ask Questions