当前期刊: arXiv - CS - Computation and Language Go to current issue    加入关注   
显示样式:        排序: 导出
我的关注
我的收藏
您暂时未登录!
登录
  • Forensic Authorship Analysis of Microblogging Texts Using N-Grams and Stylometric Features
    arXiv.cs.CL Pub Date : 2020-03-24
    Nicole Mariah Sharon Belvisi; Naveed Muhammad; Fernando Alonso-Fernandez

    In recent years, messages and text posted on the Internet are used in criminal investigations. Unfortunately, the authorship of many of them remains unknown. In some channels, the problem of establishing authorship may be even harder, since the length of digital texts is limited to a certain number of characters. In this work, we aim at identifying authors of tweet messages, which are limited to 280

    更新日期:2020-03-27
  • Predicting Legal Proceedings Status: an Approach Based on Sequential Text Data
    arXiv.cs.CL Pub Date : 2020-03-13
    Felipe Maia Polo; Itamar Ciochetti; Emerson Bertolo

    Machine learning applications in the legal field are numerous and diverse. In order to make contribution to both the machine learning community and the legal community, we have made efforts to create a model compatible with the classification of text sequences, valuing the interpretability of the results. The purpose of this paper is to classify legal proceedings in three possible status classes, which

    更新日期:2020-03-27
  • Finnish Language Modeling with Deep Transformer Models
    arXiv.cs.CL Pub Date : 2020-03-14
    Abhilash Jain

    Transformers have recently taken the center stage in language modeling after LSTM's were considered the dominant model architecture for a long time. In this project, we investigate the performance of the Transformer architectures-BERT and Transformer-XL for the language modeling task. We use a sub-word model setting with the Finnish language and compare it to the previous State of the art (SOTA) LSTM

    更新日期:2020-03-27
  • Cost-Sensitive BERT for Generalisable Sentence Classification with Imbalanced Data
    arXiv.cs.CL Pub Date : 2020-03-16
    Harish Tayyar Madabushi; Elena Kochkina; Michael Castelle

    The automatic identification of propaganda has gained significance in recent years due to technological and social changes in the way news is generated and consumed. That this task can be addressed effectively using BERT, a powerful new architecture which can be fine-tuned for text classification tasks, is not surprising. However, propaganda detection, like other tasks that deal with news documents

    更新日期:2020-03-27
  • Heavy-tailed Representations, Text Polarity Classification & Data Augmentation
    arXiv.cs.CL Pub Date : 2020-03-25
    Hamid Jalalzai; Pierre Colombo; Chloé Clavel; Eric Gaussier; Giovanna Varni; Emmanuel Vignon; Anne Sabourin

    The dominant approaches to text representation in natural language rely on learning embeddings on massive corpora which have convenient properties such as compositionality and distance preservation. In this paper, we develop a novel method to learn a heavy-tailed embedding with desirable regularity properties regarding the distributional tails, which allows to analyze the points far away from the distribution

    更新日期:2020-03-27
  • VIOLIN: A Large-Scale Dataset for Video-and-Language Inference
    arXiv.cs.CL Pub Date : 2020-03-25
    Jingzhou Liu; Wenhu Chen; Yu Cheng; Zhe Gan; Licheng Yu; Yiming Yang; Jingjing Liu

    We introduce a new task, Video-and-Language Inference, for joint multimodal understanding of video and text. Given a video clip with aligned subtitles as premise, paired with a natural language hypothesis based on the video content, a model needs to infer whether the hypothesis is entailed or contradicted by the given video clip. A new large-scale dataset, named Violin (VIdeO-and-Language INference)

    更新日期:2020-03-27
  • Predicting Unplanned Readmissions with Highly Unstructured Data
    arXiv.cs.CL Pub Date : 2020-03-19
    Constanza Fierro; Jorge Pérez; Javier Mora

    Deep learning techniques have been successfully applied to predict unplanned readmissions of patients in medical centers. The training data for these models is usually based on historical medical records that contain a significant amount of free-text from admission reports, referrals, exam notes, etc. Most of the models proposed so far are tailored to English text data and assume that electronic medical

    更新日期:2020-03-27
  • Author2Vec: A Framework for Generating User Embedding
    arXiv.cs.CL Pub Date : 2020-03-17
    Xiaodong Wu; Weizhe Lin; Zhilin Wang; Elena Rastorgueva

    Online forums and social media platforms provide noisy but valuable data every day. In this paper, we propose a novel end-to-end neural network-based user embedding system, Author2Vec. The model incorporates sentence representations generated by BERT (Bidirectional Encoder Representations from Transformers) with a novel unsupervised pre-training objective, authorship classification, to produce better

    更新日期:2020-03-27
  • Sentiment Analysis in Drug Reviews using Supervised Machine Learning Algorithms
    arXiv.cs.CL Pub Date : 2020-03-21
    Sairamvinay Vijayaraghavan; Debraj Basu

    Sentiment Analysis is an important algorithm in Natural Language Processing which is used to detect sentiment within some text. In our project, we had chosen to work on analyzing reviews of various drugs which have been reviewed in form of texts and have also been given a rating on a scale from 1-10. We had obtained this data set from the UCI machine learning repository which had 2 data sets: train

    更新日期:2020-03-27
  • Multi-Label Text Classification using Attention-based Graph Neural Network
    arXiv.cs.CL Pub Date : 2020-03-22
    Ankit Pal; Muru Selvakumar; Malaikannan Sankarasubbu

    In Multi-Label Text Classification (MLTC), one sample can belong to more than one class. It is observed that most MLTC tasks, there are dependencies or correlations among labels. Existing methods tend to ignore the relationship among labels. In this paper, a graph attention network-based model is proposed to capture the attentive dependency structure among the labels. The graph attention network uses

    更新日期:2020-03-27
  • Word2Vec: Optimal Hyper-Parameters and Their Impact on NLP Downstream Tasks
    arXiv.cs.CL Pub Date : 2020-03-23
    Tosin P. Adewumi; Foteini Liwicki; Marcus Liwicki

    Word2Vec is a prominent tool for Natural Language Processing (NLP) tasks. Similar inspiration is found in distributed embeddings for state-of-the-art (sota) deep neural networks. However, wrong combination of hyper-parameters can produce poor quality vectors. The objective of this work is to show optimal combination of hyper-parameters exists and evaluate various combinations. We compare them with

    更新日期:2020-03-27
  • Common-Knowledge Concept Recognition for SEVA
    arXiv.cs.CL Pub Date : 2020-03-26
    Jitin Krishnan; Patrick Coronado; Hemant Purohit; Huzefa Rangwala

    We build a common-knowledge concept recognition system for a Systems Engineer's Virtual Assistant (SEVA) which can be used for downstream tasks such as relation extraction, knowledge graph construction, and question-answering. The problem is formulated as a token classification task similar to named entity extraction. With the help of a domain expert and text processing methods, we construct a dataset

    更新日期:2020-03-27
  • Rat big, cat eaten! Ideas for a useful deep-agent protolanguage
    arXiv.cs.CL Pub Date : 2020-03-17
    Marco Baroni

    Deep-agent communities developing their own language-like communication protocol are a hot (or at least warm) topic in AI. Such agents could be very useful in machine-machine and human-machine interaction scenarios long before they have evolved a protocol as complex as human language. Here, I propose a small set of priorities we should focus on, if we want to get as fast as possible to a stage where

    更新日期:2020-03-27
  • TLDR: Token Loss Dynamic Reweighting for Reducing Repetitive Utterance Generation
    arXiv.cs.CL Pub Date : 2020-03-26
    Shaojie Jiang; Thomas Wolf; Christof Monz; Maarten de Rijke

    Natural Language Generation (NLG) models are prone to generating repetitive utterances. In this work, we study the repetition problem for encoder-decoder models, using both recurrent neural network (RNN) and transformer architectures. To this end, we consider the chit-chat task, where the problem is more prominent than in other tasks that need encoder-decoder architectures. We first study the influence

    更新日期:2020-03-27
  • Towards Making the Most of BERT in Neural Machine Translation
    arXiv.cs.CL Pub Date : 2019-08-15
    Jiacheng Yang; Mingxuan Wang; Hao Zhou; Chengqi Zhao; Yong Yu; Weinan Zhang; Lei Li

    GPT-2 and BERT demonstrate the effectiveness of using pre-trained language models (LMs) on various natural language processing tasks. However, LM fine-tuning often suffers from catastrophic forgetting when applied to resource-rich tasks. In this work, we introduce a concerted training framework (\method) that is the key to integrate the pre-trained LMs to neural machine translation (NMT). Our proposed

    更新日期:2020-03-27
  • Enhancing Out-Of-Domain Utterance Detection with Data Augmentation Based on Word Embeddings
    arXiv.cs.CL Pub Date : 2019-11-24
    Yueqi Feng; Jiali Lin

    For most intelligent assistant systems, it is essential to have a mechanism that detects out-of-domain (OOD) utterances automatically to handle noisy input properly. One typical approach would be introducing a separate class that contains OOD utterance examples combined with in-domain text samples into the classifier. However, since OOD utterances are usually unseen to the training datasets, the detection

    更新日期:2020-03-27
  • XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization
    arXiv.cs.CL Pub Date : 2020-03-24
    Junjie Hu; Sebastian Ruder; Aditya Siddhant; Graham Neubig; Orhan Firat; Melvin Johnson

    Much recent progress in applications of machine learning models to NLP has been driven by benchmarks that evaluate models across a wide variety of tasks. However, these broad-coverage benchmarks have been mostly limited to English, and despite an increasing interest in multilingual models, a benchmark that enables the comprehensive evaluation of such methods on a diverse range of languages and tasks

    更新日期:2020-03-26
  • Can Embeddings Adequately Represent Medical Terminology? New Large-Scale Medical Term Similarity Datasets Have the Answer!
    arXiv.cs.CL Pub Date : 2020-03-24
    Claudia Schulz; Damir Juric

    A large number of embeddings trained on medical data have emerged, but it remains unclear how well they represent medical terminology, in particular whether the close relationship of semantically similar medical terms is encoded in these embeddings. To date, only small datasets for testing medical term similarity are available, not allowing to draw conclusions about the generalisability of embeddings

    更新日期:2020-03-26
  • EQL -- an extremely easy to learn knowledge graph query language, achieving highspeed and precise search
    arXiv.cs.CL Pub Date : 2020-03-19
    Han Liu; Shantao Liu

    EQL, also named as Extremely Simple Query Language, can be widely used in the field of knowledge graph, precise search, strong artificial intelligence, database, smart speaker ,patent search and other fields. EQL adopt the principle of minimalism in design and pursues simplicity and easy to learn so that everyone can master it quickly. EQL language and lambda calculus are interconvertible, that reveals

    更新日期:2020-03-26
  • COVID-19 and Computer Audition: An Overview on What Speech & Sound Analysis Could Contribute in the SARS-CoV-2 Corona Crisis
    arXiv.cs.CL Pub Date : 2020-03-24
    Björn W. Schuller; Dagmar M. Schuller; Kun Qian; Juan Liu; Huaiyuan Zheng; Xiao Li

    At the time of writing, the world population is suffering from more than 10,000 registered COVID-19 disease epidemic induced deaths since the outbreak of the Corona virus more than three months ago now officially known as SARS-CoV-2. Since, tremendous efforts have been made worldwide to counter-steer and control the epidemic by now labelled as pandemic. In this contribution, we provide an overview

    更新日期:2020-03-26
  • Learning Syntactic and Dynamic Selective Encoding for Document Summarization
    arXiv.cs.CL Pub Date : 2020-03-25
    Haiyang Xu; Yahao He; Kun Han; Junwen Chen; Xiangang Li

    Text summarization aims to generate a headline or a short summary consisting of the major information of the source text. Recent studies employ the sequence-to-sequence framework to encode the input with a neural network and generate abstractive summary. However, most studies feed the encoder with the semantic word embedding but ignore the syntactic information of the text. Further, although previous

    更新日期:2020-03-26
  • Adversarial Multi-Binary Neural Network for Multi-class Classification
    arXiv.cs.CL Pub Date : 2020-03-25
    Haiyang Xu; Junwen Chen; Kun Han; Xiangang Li

    Multi-class text classification is one of the key problems in machine learning and natural language processing. Emerging neural networks deal with the problem using a multi-output softmax layer and achieve substantial progress, but they do not explicitly learn the correlation among classes. In this paper, we use a multi-task framework to address multi-class classification, where a multi-class classifier

    更新日期:2020-03-26
  • BaitWatcher: A lightweight web interface for the detection of incongruent news headlines
    arXiv.cs.CL Pub Date : 2020-03-23
    Kunwoo Park; Taegyun Kim; Seunghyun Yoon; Meeyoung Cha; Kyomin Jung

    In digital environments where substantial amounts of information are shared online, news headlines play essential roles in the selection and diffusion of news articles. Some news articles attract audience attention by showing exaggerated or misleading headlines. This study addresses the \textit{headline incongruity} problem, in which a news headline makes claims that are either unrelated or opposite

    更新日期:2020-03-26
  • Hurtful Words: Quantifying Biases in Clinical Contextual Word Embeddings
    arXiv.cs.CL Pub Date : 2020-03-11
    Haoran Zhang; Amy X. Lu; Mohamed Abdalla; Matthew McDermott; Marzyeh Ghassemi

    In this work, we examine the extent to which embeddings may encode marginalized populations differently, and how this may lead to a perpetuation of biases and worsened performance on clinical tasks. We pretrain deep embedding models (BERT) on medical notes from the MIMIC-III hospital dataset, and quantify potential disparities using two approaches. First, we identify dangerous latent relationships

    更新日期:2020-03-26
  • Keyword-Attentive Deep Semantic Matching
    arXiv.cs.CL Pub Date : 2020-03-11
    Changyu Miao; Zhen Cao; Yik-Cheung Tam

    Deep Semantic Matching is a crucial component in various natural language processing applications such as question and answering (QA), where an input query is compared to each candidate question in a QA corpus in terms of relevance. Measuring similarities between a query-question pair in an open domain scenario can be challenging due to diverse word tokens in the queryquestion pair. We propose a keyword-attentive

    更新日期:2020-03-26
  • From Algebraic Word Problem to Program: A Formalized Approach
    arXiv.cs.CL Pub Date : 2020-03-11
    Adam Wiemerslage; Shafiuddin Rehan Ahmed

    In this paper, we propose a pipeline to convert grade school level algebraic word problem into program of a formal languageA-IMP. Using natural language processing tools, we break the problem into sentence fragments which can then be reduced to functions. The functions are categorized by the head verb of the sentence and its structure, as defined by (Hosseini et al., 2014). We define the function signature

    更新日期:2020-03-26
  • Hybrid Attention-Based Transformer Block Model for Distant Supervision Relation Extraction
    arXiv.cs.CL Pub Date : 2020-03-10
    Yan Xiao; Yaochu Jina; Ran Cheng; Kuangrong Hao

    With an exponential explosive growth of various digital text information, it is challenging to efficiently obtain specific knowledge from massive unstructured text information. As one basic task for natural language processing (NLP), relation extraction aims to extract the semantic relation between entity pairs based on the given text. To avoid manual labeling of datasets, distant supervision relation

    更新日期:2020-03-26
  • Vector logic and counterfactuals
    arXiv.cs.CL Pub Date : 2020-03-09
    Eduardo Mizraji

    In this work we investigate the representation of counterfactual conditionals using the vector logic, a matrix-vectors formalism for logical functions and truth values. With this formalism, we can describe the counterfactuals as complex matrix operators that appear preprocessing the implication matrix with one of the square roots of the negation, a complex matrix. This mathematical approach puts in

    更新日期:2020-03-26
  • Joint Multiclass Debiasing of Word Embeddings
    arXiv.cs.CL Pub Date : 2020-03-09
    Radomir Popović; Florian Lemmerich; Markus Strohmaier

    Bias in Word Embeddings has been a subject of recent interest, along with efforts for its reduction. Current approaches show promising progress towards debiasing single bias dimensions such as gender or race. In this paper, we present a joint multiclass debiasing approach that is capable of debiasing multiple bias dimensions simultaneously. In that direction, we present two approaches, HardWEAT and

    更新日期:2020-03-26
  • Matching Text with Deep Mutual Information Estimation
    arXiv.cs.CL Pub Date : 2020-03-09
    Xixi ZhouZhejiang University; Chengxi LiZhejiang University; Jiajun BuZhejiang University; Chengwei YaoZhejiang University; Keyue ShiZhejiang University; Zhi YuZhejiang University; Zhou YuUniversity of California, Davis

    Text matching is a core natural language processing research problem. How to retain sufficient information on both content and structure information is one important challenge. In this paper, we present a neural approach for general-purpose text matching with deep mutual information estimation incorporated. Our approach, Text matching with Deep Info Max (TIM), is integrated with a procedure of unsupervised

    更新日期:2020-03-26
  • Utilizing Deep Learning to Identify Drug Use on Twitter Data
    arXiv.cs.CL Pub Date : 2020-03-08
    Joseph Tassone; Peizhi Yan; Mackenzie Simpson; Chetan Mendhe; Vijay Mago; Salimur Choudhury

    The collection and examination of social media has become a useful mechanism for studying the mental activity and behavior tendencies of users. Through the analysis of collected Twitter data, models were developed for classifying drug-related tweets. Using topic pertaining keywords, such as slang and methods of drug consumption, a set of tweets was generated. Potential candidates were then preprocessed

    更新日期:2020-03-26
  • Tigrinya Neural Machine Translation with Transfer Learning for Humanitarian Response
    arXiv.cs.CL Pub Date : 2020-03-09
    Alp Öktem; Mirko Plitt; Grace Tang

    We report our experiments in building a domain-specific Tigrinya-to-English neural machine translation system. We use transfer learning from other Ge'ez script languages and report an improvement of 1.3 BLEU points over a classic neural baseline. We publish our development pipeline as an open-source library and also provide a demonstration application.

    更新日期:2020-03-26
  • Generating Major Types of Chinese Classical Poetry in a Uniformed Framework
    arXiv.cs.CL Pub Date : 2020-03-13
    Jinyi Hu; Maosong Sun

    Poetry generation is an interesting research topic in the field of text generation. As one of the most valuable literary and cultural heritages of China, Chinese classical poetry is very familiar and loved by Chinese people from generation to generation. It has many particular characteristics in its language structure, ranging from form, sound to meaning, thus is regarded as an ideal testing task for

    更新日期:2020-03-26
  • Masakhane -- Machine Translation For Africa
    arXiv.cs.CL Pub Date : 2020-03-13
    Iroro Orife; Julia Kreutzer; Blessing Sibanda; Daniel Whitenack; Kathleen Siminyu; Laura Martinus; Jamiil Toure Ali; Jade Abbott; Vukosi Marivate; Salomon Kabongo; Musie Meressa; Espoir Murhabazi; Orevaoghene Ahia; Elan van Biljon; Arshath Ramkilowan; Adewale Akinfaderin; Alp Öktem; Wole Akin; Ghollah Kioko; Kevin Degila; Herman Kamper; Bonaventure Dossou; Chris Emezue; Kelechi Ogueji; Abdallah Bashir

    Africa has over 2000 languages. Despite this, African languages account for a small portion of available resources and publications in Natural Language Processing (NLP). This is due to multiple factors, including: a lack of focus from government and funding, discoverability, a lack of community, sheer language complexity, difficulty in reproducing papers and no benchmarks to compare techniques. To

    更新日期:2020-03-26
  • Meta-CoTGAN: A Meta Cooperative Training Paradigm for Improving Adversarial Text Generation
    arXiv.cs.CL Pub Date : 2020-03-12
    Haiyan Yin; Dingcheng Li; Xu Li; Ping Li

    Training generative models that can generate high-quality text with sufficient diversity is an important open problem for Natural Language Generation (NLG) community. Recently, generative adversarial models have been applied extensively on text generation tasks, where the adversarially trained generators alleviate the exposure bias experienced by conventional maximum likelihood approaches and result

    更新日期:2020-03-26
  • The Medical Scribe: Corpus Development and Model Performance Analyses
    arXiv.cs.CL Pub Date : 2020-03-12
    Izhak Shafran; Nan Du; Linh Tran; Amanda Perry; Lauren Keyes; Mark Knichel; Ashley Domin; Lei Huang; Yuhui Chen; Gang Li; Mingqiu Wang; Laurent El Shafey; Hagen Soltau; Justin S. Paul

    There is a growing interest in creating tools to assist in clinical note generation using the audio of provider-patient encounters. Motivated by this goal and with the help of providers and medical scribes, we developed an annotation scheme to extract relevant clinical concepts. We used this annotation scheme to label a corpus of about 6k clinical encounters. This was used to train a state-of-the-art

    更新日期:2020-03-26
  • Iterative Answer Prediction with Pointer-Augmented Multimodal Transformers for TextVQA
    arXiv.cs.CL Pub Date : 2019-11-14
    Ronghang Hu; Amanpreet Singh; Trevor Darrell; Marcus Rohrbach

    Many visual scenes contain text that carries crucial information, and it is thus essential to understand text in images for downstream reasoning tasks. For example, a deep water label on a warning sign warns people about the danger in the scene. Recent work has explored the TextVQA task that requires reading and understanding text in images to answer a question. However, existing approaches for TextVQA

    更新日期:2020-03-26
  • Early Detection of Social Media Hoaxes at Scale
    arXiv.cs.CL Pub Date : 2018-01-22
    Arkaitz Zubiaga; Aiqi Jiang

    The unmoderated nature of social media enables the diffusion of hoaxes, which in turn jeopardises the credibility of information gathered from social media platforms. Existing research on automated detection of hoaxes has the limitation of using relatively small datasets, owing to the difficulty of getting labelled data. This in turn has limited research exploring early detection of hoaxes as well

    更新日期:2020-03-26
  • FedNER: Privacy-preserving Medical Named Entity Recognition with Federated Learning
    arXiv.cs.CL Pub Date : 2020-03-20
    Suyu Ge; Fangzhao Wu; Chuhan Wu; Tao Qi; Yongfeng Huang; Xing Xie

    Medical named entity recognition (NER) has wide applications in intelligent healthcare. Sufficient labeled data is critical for training accurate medical NER model. However, the labeled data in a single medical platform is usually limited. Although labeled datasets may exist in many different medical platforms, they cannot be directly shared since medical data is highly privacy-sensitive. In this paper

    更新日期:2020-03-26
  • TArC: Incrementally and Semi-Automatically Collecting a Tunisian Arabish Corpus
    arXiv.cs.CL Pub Date : 2020-03-20
    Elisa Gugliotta; Marco Dinarelli

    This article describes the constitution process of the first morpho-syntactically annotated Tunisian Arabish Corpus (TArC). Arabish, also known as Arabizi, is a spontaneous coding of Arabic dialects in Latin characters and arithmographs (numbers used as letters). This code-system was developed by Arabic-speaking users of social media in order to facilitate the writing in the Computer-Mediated Communication

    更新日期:2020-03-24
  • A Framework for Generating Explanations from Temporal Personal Health Data
    arXiv.cs.CL Pub Date : 2020-03-20
    Jonathan J. Harris; Ching-Hua Chen; Mohammed J. Zaki

    Whereas it has become easier for individuals to track their personal health data (e.g., heart rate, step count, food log), there is still a wide chasm between the collection of data and the generation of meaningful explanations to help users better understand what their data means to them. With an increased comprehension of their data, users will be able to act upon the newfound information and work

    更新日期:2020-03-24
  • Analyzing Word Translation of Transformer Layers
    arXiv.cs.CL Pub Date : 2020-03-21
    Hongfei Xu; Josef van Genabith; Deyi Xiong; Qiuhui Liu

    The Transformer translation model is popular for its effective parallelization and performance. Though a wide range of analysis about the Transformer has been conducted recently, the role of each Transformer layer in translation has not been studied to our knowledge. In this paper, we propose approaches to analyze the translation performed in encoder / decoder layers of the Transformer. Our approaches

    更新日期:2020-03-24
  • A Joint Approach to Compound Splitting and Idiomatic Compound Detection
    arXiv.cs.CL Pub Date : 2020-03-21
    Irina Krotova; Sergey Aksenov; Ekaterina Artemova

    Applications such as machine translation, speech recognition, and information retrieval require efficient handling of noun compounds as they are one of the possible sources for out-of-vocabulary (OOV) words. In-depth processing of noun compounds requires not only splitting them into smaller components (or even roots) but also the identification of instances that should remain unsplitted as they are

    更新日期:2020-03-24
  • Invariant Rationalization
    arXiv.cs.CL Pub Date : 2020-03-22
    Shiyu Chang; Yang Zhang; Mo Yu; Tommi S. Jaakkola

    Selective rationalization improves neural network interpretability by identifying a small subset of input features -- the rationale -- that best explains or supports the prediction. A typical rationalization criterion, i.e. maximum mutual information (MMI), finds the rationale that maximizes the prediction performance based only on the rationale. However, MMI can be problematic because it picks up

    更新日期:2020-03-24
  • Prior Knowledge Driven Label Embedding for Slot Filling in Natural Language Understanding
    arXiv.cs.CL Pub Date : 2020-03-22
    Su Zhu; Zijian Zhao; Rao Ma; Kai Yu

    Traditional slot filling in natural language understanding (NLU) predicts a one-hot vector for each word. This form of label representation lacks semantic correlation modelling, which leads to severe data sparsity problem, especially when adapting an NLU model to a new domain. To address this issue, a novel label embedding based slot filling framework is proposed in this paper. Here, distributed label

    更新日期:2020-03-24
  • SAC: Accelerating and Structuring Self-Attention via Sparse Adaptive Connection
    arXiv.cs.CL Pub Date : 2020-03-22
    Xiaoya Li; Yuxian Meng; Qinghong Han; Fei Wu; Jiwei Li

    While the self-attention mechanism has been widely used in a wide variety of tasks, it has the unfortunate property of a quadratic cost with respect to the input length, which makes it difficult to deal with long inputs. In this paper, we present a method for accelerating and structuring self-attentions: Sparse Adaptive Connection (SAC). In SAC, we regard the input sequence as a graph and attention

    更新日期:2020-03-24
  • Visual Question Answering for Cultural Heritage
    arXiv.cs.CL Pub Date : 2020-03-22
    Pietro Bongini; Federico Becattini; Andrew D. Bagdanov; Alberto Del Bimbo

    Technology and the fruition of cultural heritage are becoming increasingly more entwined, especially with the advent of smart audio guides, virtual and augmented reality, and interactive installations. Machine learning and computer vision are important components of this ongoing integration, enabling new interaction modalities between user and museum. Nonetheless, the most frequent way of interacting

    更新日期:2020-03-24
  • Pairwise Multi-Class Document Classification for Semantic Relations between Wikipedia Articles
    arXiv.cs.CL Pub Date : 2020-03-22
    Malte Ostendorff; Terry Ruas; Moritz Schubotz; Georg Rehm; Bela Gipp

    Many digital libraries recommend literature to their users considering the similarity between a query document and their repository. However, they often fail to distinguish what is the relationship that makes two documents alike. In this paper, we model the problem of finding the relationship between two documents as a pairwise document classification task. To find the semantic relation between documents

    更新日期:2020-03-24
  • A Better Variant of Self-Critical Sequence Training
    arXiv.cs.CL Pub Date : 2020-03-22
    Ruotian Luo

    In this work, we present a simple yet better variant of Self-Critical Sequence Training. We make a simple change in the choice of baseline function in REINFORCE algorithm. The new baseline can bring better performance with no extra cost, compared to the greedy decoding baseline.

    更新日期:2020-03-24
  • Toward Tag-free Aspect Based Sentiment Analysis: A Multiple Attention Network Approach
    arXiv.cs.CL Pub Date : 2020-03-22
    Yao Qiang; Xin Li; Dongxiao Zhu

    Existing aspect based sentiment analysis (ABSA) approaches leverage various neural network models to extract the aspect sentiments via learning aspect-specific feature representations. However, these approaches heavily rely on manual tagging of user reviews according to the predefined aspects as the input, a laborious and time-consuming process. Moreover, the underlying methods do not explain how and

    更新日期:2020-03-24
  • 365 Dots in 2019: Quantifying Attention of News Sources
    arXiv.cs.CL Pub Date : 2020-03-22
    Alexander C. Nwala; Michele C. Weigle; Michael L. Nelson

    We investigate the overlap of topics of online news articles from a variety of sources. To do this, we provide a platform for studying the news by measuring this overlap and scoring news stories according to the degree of attention in near-real time. This can enable multiple studies, including identifying topics that receive the most attention from news organizations and identifying slow news days

    更新日期:2020-03-24
  • Caption Generation of Robot Behaviors based on Unsupervised Learning of Action Segments
    arXiv.cs.CL Pub Date : 2020-03-23
    Koichiro Yoshino; Kohei Wakimoto; Yuta Nishimura; Satoshi Nakamura

    Bridging robot action sequences and their natural language captions is an important task to increase explainability of human assisting robots in their recently evolving field. In this paper, we propose a system for generating natural language captions that describe behaviors of human assisting robots. The system describes robot actions by using robot observations; histories from actuator systems and

    更新日期:2020-03-24
  • E2EET: From Pipeline to End-to-end Entity Typing via Transformer-Based Embeddings
    arXiv.cs.CL Pub Date : 2020-03-23
    Michael Stewart; Wei Liu

    Entity Typing (ET) is the process of identifying the semantic types of every entity within a corpus. In contrast to Named Entity Recognition, where each token in a sentence is labelled with zero or one class label, ET involves labelling each entity mention with one or more class labels. Existing entity typing models, which operate at the mention level, are limited by two key factors: they do not make

    更新日期:2020-03-24
  • Unsupervised Word Polysemy Quantification with Multiresolution Grids of Contextual Embeddings
    arXiv.cs.CL Pub Date : 2020-03-23
    Christos Xypolopoulos; Antoine J. -P. Tixier; Michalis Vazirgiannis

    The number of senses of a given word, or polysemy, is a very subjective notion, which varies widely across annotators and resources. We propose a novel method to estimate polysemy, based on simple geometry in the contextual embedding space. Our approach is fully unsupervised and purely data-driven. We show through rigorous experiments that our rankings are well correlated (with strong statistical significance)

    更新日期:2020-03-24
  • Fast Cross-domain Data Augmentation through Neural Sentence Editing
    arXiv.cs.CL Pub Date : 2020-03-23
    Guillaume Raille; Sandra Djambazovska; Claudiu Musat

    Data augmentation promises to alleviate data scarcity. This is most important in cases where the initial data is in short supply. This is, for existing methods, also where augmenting is the most difficult, as learning the full data distribution is impossible. For natural language, sentence editing offers a solution - relying on small but meaningful changes to the original ones. Learning which changes

    更新日期:2020-03-24
  • PathVQA: 30000+ Questions for Medical Visual Question Answering
    arXiv.cs.CL Pub Date : 2020-03-07
    Xuehai He; Yichen Zhang; Luntian Mou; Eric Xing; Pengtao Xie

    Is it possible to develop an "AI Pathologist" to pass the board-certified examination of the American Board of Pathology? To achieve this goal, the first step is to create a visual question answering (VQA) dataset where the AI agent is presented with a pathology image together with a question and is asked to give the correct answer. Our work makes the first attempt to build such a dataset. Different

    更新日期:2020-03-24
  • Adaptive Name Entity Recognition under Highly Unbalanced Data
    arXiv.cs.CL Pub Date : 2020-03-10
    Thong Nguyen; Duy Nguyen; Pramod Rao

    For several purposes in Natural Language Processing (NLP), such as Information Extraction, Sentiment Analysis or Chatbot, Named Entity Recognition (NER) holds an important role as it helps to determine and categorize entities in text into predefined groups such as the names of persons, locations, quantities, organizations or percentages, etc. In this report, we present our experiments on a neural architecture

    更新日期:2020-03-24
  • Generating Natural Language Adversarial Examples on a Large Scale with Generative Models
    arXiv.cs.CL Pub Date : 2020-03-10
    Yankun Ren; Jianbin Lin; Siliang Tang; Jun Zhou; Shuang Yang; Yuan Qi; Xiang Ren

    Today text classification models have been widely used. However, these classifiers are found to be easily fooled by adversarial examples. Fortunately, standard attacking methods generate adversarial texts in a pair-wise way, that is, an adversarial text can only be created from a real-world text by replacing a few words. In many applications, these texts are limited in numbers, therefore their corresponding

    更新日期:2020-03-24
  • Multimodal Analytics for Real-world News using Measures of Cross-modal Entity Consistency
    arXiv.cs.CL Pub Date : 2020-03-23
    Eric Müller-Budack; Jonas Theiner; Sebastian Diering; Maximilian Idahl; Ralph Ewerth

    The World Wide Web has become a popular source for gathering information and news. Multimodal information, e.g., enriching text with photos, is typically used to convey the news more effectively or to attract attention. Photo content can range from decorative, depict additional important information, or can even contain misleading information. Therefore, automatic approaches to quantify cross-modal

    更新日期:2020-03-24
  • RUBi: Reducing Unimodal Biases in Visual Question Answering
    arXiv.cs.CL Pub Date : 2019-06-24
    Remi Cadene; Corentin Dancette; Hedi Ben-younes; Matthieu Cord; Devi Parikh

    Visual Question Answering (VQA) is the task of answering questions about an image. Some VQA models often exploit unimodal biases to provide the correct answer without using the image information. As a result, they suffer from a huge drop in performance when evaluated on data outside their training set distribution. This critical issue makes them unsuitable for real-world settings. We propose RUBi,

    更新日期:2020-03-24
Contents have been reproduced by permission of the publishers.
导出
全部期刊列表>>
全球疫情及响应:BMC Medicine专题征稿
欢迎探索2019年最具下载量的化学论文
新版X-MOL期刊搜索和高级搜索功能介绍
化学材料学全球高引用
ACS材料视界
南方科技大学
x-mol收录
南方科技大学
自然科研论文编辑服务
上海交通大学彭文杰
中国科学院长春应化所于聪-4-8
武汉工程大学
课题组网站
X-MOL
深圳大学二维材料实验室张晗
中山大学化学工程与技术学院
试剂库存
天合科研
down
wechat
bug