Paper Group NANR 50
Hiding Images in Plain Sight: Deep Steganography. An overview of Natural Language Inference Data Collection: The way forward?. Projection-based Coreference Resolution Using Deep Syntax. QCRI Live Speech Translation System. Expressing prediction and epistemicity with Korean -(ul) kes i and Mandarin Chinese hui. Geographical Evaluation of Word Embedd …
Hiding Images in Plain Sight: Deep Steganography
| Title | Hiding Images in Plain Sight: Deep Steganography |
| Authors | Shumeet Baluja |
| Abstract | Steganography is the practice of concealing a secret message within another, ordinary, message. Commonly, steganography is used to unobtrusively hide a small message within the noisy regions of a larger image. In this study, we attempt to place a full size color image within another image of the same size. Deep neural networks are simultaneously trained to create the hiding and revealing processes and are designed to specifically work as a pair. The system is trained on images drawn randomly from the ImageNet database, and works well on natural images from a wide variety of sources. Beyond demonstrating the successful application of deep learning to hiding images, we carefully examine how the result is achieved and explore extensions. Unlike many popular steganographic methods that encode the secret message within the least significant bits of the carrier image, our approach compresses and distributes the secret image’s representation across all of the available bits. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6802-hiding-images-in-plain-sight-deep-steganography |
| http://papers.nips.cc/paper/6802-hiding-images-in-plain-sight-deep-steganography.pdf | |
| PWC | https://paperswithcode.com/paper/hiding-images-in-plain-sight-deep |
| Repo | |
| Framework | |
An overview of Natural Language Inference Data Collection: The way forward?
| Title | An overview of Natural Language Inference Data Collection: The way forward? |
| Authors | Stergios Chatzikyriakidis, Robin Cooper, Simon Dobnik, Staffan Larsson |
| Abstract | |
| Tasks | Natural Language Inference |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-7203/ |
| https://www.aclweb.org/anthology/W17-7203 | |
| PWC | https://paperswithcode.com/paper/an-overview-of-natural-language-inference |
| Repo | |
| Framework | |
Projection-based Coreference Resolution Using Deep Syntax
| Title | Projection-based Coreference Resolution Using Deep Syntax |
| Authors | Michal Nov{'a}k, Anna Nedoluzhko, Zden{\v{e}}k {\v{Z}}abokrtsk{'y} |
| Abstract | The paper describes the system for coreference resolution in German and Russian, trained exclusively on coreference relations project ed through a parallel corpus from English. The resolver operates on the level of deep syntax and makes use of multiple specialized models. It achieves 32 and 22 points in terms of CoNLL score for Russian and German, respectively. Analysis of the evaluation results show that the resolver for Russian is able to preserve 66{%} of the English resolver{'}s quality in terms of CoNLL score. The system was submitted to the Closed track of the CORBON 2017 Shared task. |
| Tasks | Coreference Resolution |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1508/ |
| https://www.aclweb.org/anthology/W17-1508 | |
| PWC | https://paperswithcode.com/paper/projection-based-coreference-resolution-using |
| Repo | |
| Framework | |
QCRI Live Speech Translation System
| Title | QCRI Live Speech Translation System |
| Authors | Fahim Dalvi, Yifan Zhang, Sameer Khurana, Nadir Durrani, Hassan Sajjad, Ahmed Abdelali, Hamdy Mubarak, Ahmed Ali, Stephan Vogel |
| Abstract | This paper presents QCRI{'}s Arabic-to-English live speech translation system. It features modern web technologies to capture live audio, and broadcasts Arabic transcriptions and English translations simultaneously. Our Kaldi-based ASR system uses the Time Delay Neural Network (TDNN) architecture, while our Machine Translation (MT) system uses both phrase-based and neural frameworks. Although our neural MT system is slower than the phrase-based system, it produces significantly better translations and is memory efficient. The demo is available at \url{https://st.qcri.org/demos/livetranslation}. |
| Tasks | Machine Translation, Speech Recognition |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-3016/ |
| https://www.aclweb.org/anthology/E17-3016 | |
| PWC | https://paperswithcode.com/paper/qcri-live-speech-translation-system |
| Repo | |
| Framework | |
Expressing prediction and epistemicity with Korean -(ul) kes i and Mandarin Chinese hui
| Title | Expressing prediction and epistemicity with Korean -(ul) kes i and Mandarin Chinese hui |
| Authors | Eunson Yoo |
| Abstract | |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/Y17-1027/ |
| https://www.aclweb.org/anthology/Y17-1027 | |
| PWC | https://paperswithcode.com/paper/expressing-prediction-and-epistemicity-with |
| Repo | |
| Framework | |
Geographical Evaluation of Word Embeddings
| Title | Geographical Evaluation of Word Embeddings |
| Authors | Michal Konkol, Tom{'a}{\v{s}} Brychc{'\i}n, Michal Nykl, Tom{'a}{\v{s}} Hercig |
| Abstract | Word embeddings are commonly compared either with human-annotated word similarities or through improvements in natural language processing tasks. We propose a novel principle which compares the information from word embeddings with reality. We implement this principle by comparing the information in the word embeddings with geographical positions of cities. Our evaluation linearly transforms the semantic space to optimally fit the real positions of cities and measures the deviation between the position given by word embeddings and the real position. A set of well-known word embeddings with state-of-the-art results were evaluated. We also introduce a visualization that helps with error analysis. |
| Tasks | Machine Translation, Named Entity Recognition, Sentiment Analysis, Word Embeddings |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-1023/ |
| https://www.aclweb.org/anthology/I17-1023 | |
| PWC | https://paperswithcode.com/paper/geographical-evaluation-of-word-embeddings |
| Repo | |
| Framework | |
Parsing transcripts of speech
| Title | Parsing transcripts of speech |
| Authors | Andrew Caines, Michael McCarthy, Paula Buttery |
| Abstract | We present an analysis of parser performance on speech data, comparing word type and token frequency distributions with written data, and evaluating parse accuracy by length of input string. We find that parser performance tends to deteriorate with increasing length of string, more so for spoken than for written texts. We train an alternative parsing model with added speech data and demonstrate improvements in accuracy on speech-units, with no deterioration in performance on written text. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4604/ |
| https://www.aclweb.org/anthology/W17-4604 | |
| PWC | https://paperswithcode.com/paper/parsing-transcripts-of-speech |
| Repo | |
| Framework | |
The ATILF-LLF System for Parseme Shared Task: a Transition-based Verbal Multiword Expression Tagger
| Title | The ATILF-LLF System for Parseme Shared Task: a Transition-based Verbal Multiword Expression Tagger |
| Authors | Hazem Al Saied, Matthieu Constant, C, Marie ito |
| Abstract | We describe the ATILF-LLF system built for the MWE 2017 Shared Task on automatic identification of verbal multiword expressions. We participated in the closed track only, for all the 18 available languages. Our system is a robust greedy transition-based system, in which MWE are identified through a MERGE transition. The system was meant to accommodate the variety of linguistic resources provided for each language, in terms of accompanying morphological and syntactic information. Using per-MWE Fscore, the system was ranked first for all but two languages (Hungarian and Romanian). |
| Tasks | Feature Engineering, Lexical Analysis |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1717/ |
| https://www.aclweb.org/anthology/W17-1717 | |
| PWC | https://paperswithcode.com/paper/the-atilf-llf-system-for-parseme-shared-task |
| Repo | |
| Framework | |
Detecting Changes in Twitter Streams using Temporal Clusters of Hashtags
| Title | Detecting Changes in Twitter Streams using Temporal Clusters of Hashtags |
| Authors | Yunli Wang, Cyril Goutte |
| Abstract | Detecting events from social media data has important applications in public security, political issues, and public health. Many studies have focused on detecting specific or unspecific events from Twitter streams. However, not much attention has been paid to detecting changes, and their impact, in online conversations related to an event. We propose methods for detecting such changes, using clustering of temporal profiles of hashtags, and three change point detection algorithms. The methods were tested on two Twitter datasets: one covering the 2014 Ottawa shooting event, and one covering the Sochi winter Olympics. We compare our approach to a baseline consisting of detecting change from raw counts in the conversation. We show that our method produces large gains in change detection accuracy on both datasets. |
| Tasks | Change Point Detection, Time Series |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2702/ |
| https://www.aclweb.org/anthology/W17-2702 | |
| PWC | https://paperswithcode.com/paper/detecting-changes-in-twitter-streams-using |
| Repo | |
| Framework | |
Question Generation for Question Answering
| Title | Question Generation for Question Answering |
| Authors | Nan Duan, Duyu Tang, Peng Chen, Ming Zhou |
| Abstract | This paper presents how to generate questions from given passages using neural networks, where large scale QA pairs are automatically crawled and processed from Community-QA website, and used as training data. The contribution of the paper is 2-fold: First, two types of question generation approaches are proposed, one is a retrieval-based method using convolution neural network (CNN), the other is a generation-based method using recurrent neural network (RNN); Second, we show how to leverage the generated questions to improve existing question answering systems. We evaluate our question generation method for the answer sentence selection task on three benchmark datasets, including SQuAD, MS MARCO, and WikiQA. Experimental results show that, by using generated questions as an extra signal, significant QA improvement can be achieved. |
| Tasks | Chatbot, Question Answering, Question Generation, Reading Comprehension |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1090/ |
| https://www.aclweb.org/anthology/D17-1090 | |
| PWC | https://paperswithcode.com/paper/question-generation-for-question-answering |
| Repo | |
| Framework | |
Attentive listening system with backchanneling, response generation and flexible turn-taking
| Title | Attentive listening system with backchanneling, response generation and flexible turn-taking |
| Authors | Divesh Lala, Pierrick Milhorat, Koji Inoue, Masanari Ishida, Katsuya Takanashi, Tatsuya Kawahara |
| Abstract | Attentive listening systems are designed to let people, especially senior people, keep talking to maintain communication ability and mental health. This paper addresses key components of an attentive listening system which encourages users to talk smoothly. First, we introduce continuous prediction of end-of-utterances and generation of backchannels, rather than generating backchannels after end-point detection of utterances. This improves subjective evaluations of backchannels. Second, we propose an effective statement response mechanism which detects focus words and responds in the form of a question or partial repeat. This can be applied to any statement. Moreover, a flexible turn-taking mechanism is designed which uses backchannels or fillers when the turn-switch is ambiguous. These techniques are integrated into a humanoid robot to conduct attentive listening. We test the feasibility of the system in a pilot experiment and show that it can produce coherent dialogues during conversation. |
| Tasks | Speech Recognition, Spoken Dialogue Systems |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-5516/ |
| https://www.aclweb.org/anthology/W17-5516 | |
| PWC | https://paperswithcode.com/paper/attentive-listening-system-with |
| Repo | |
| Framework | |
Renyi Differential Privacy Mechanisms for Posterior Sampling
| Title | Renyi Differential Privacy Mechanisms for Posterior Sampling |
| Authors | Joseph Geumlek, Shuang Song, Kamalika Chaudhuri |
| Abstract | With the newly proposed privacy definition of Rényi Differential Privacy (RDP) in (Mironov, 2017), we re-examine the inherent privacy of releasing a single sample from a posterior distribution. We exploit the impact of the prior distribution in mitigating the influence of individual data points. In particular, we focus on sampling from an exponential family and specific generalized linear models, such as logistic regression. We propose novel RDP mechanisms as well as offering a new RDP analysis for an existing method in order to add value to the RDP framework. Each method is capable of achieving arbitrary RDP privacy guarantees, and we offer experimental results of their efficacy. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7113-renyi-differential-privacy-mechanisms-for-posterior-sampling |
| http://papers.nips.cc/paper/7113-renyi-differential-privacy-mechanisms-for-posterior-sampling.pdf | |
| PWC | https://paperswithcode.com/paper/renyi-differential-privacy-mechanisms-for-1 |
| Repo | |
| Framework | |
Towards a lexicon of event-selecting predicates for a French FactBank
| Title | Towards a lexicon of event-selecting predicates for a French FactBank |
| Authors | Ingrid Falk, Fabienne Martin |
| Abstract | This paper presents ongoing work for the construction of a French FactBank and a lexicon of French event-selecting predicates (ESPs), by applying the factuality detection algorithm introduced in (Saur{'\i} and Pustejovsky, 2012). This algorithm relies on a lexicon of ESPs, specifying how these predicates influence the polarity of their embedded events. For this pilot study, we focused on French factive and implicative verbs, and capitalised on a lexical resource for the English counterparts of these verbs provided by the CLSI Group (Nairn et al., 2006; Karttunen, 2012). |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1803/ |
| https://www.aclweb.org/anthology/W17-1803 | |
| PWC | https://paperswithcode.com/paper/towards-a-lexicon-of-event-selecting |
| Repo | |
| Framework | |
Improving Clinical Diagnosis Inference through Integration of Structured and Unstructured Knowledge
| Title | Improving Clinical Diagnosis Inference through Integration of Structured and Unstructured Knowledge |
| Authors | Yuan Ling, Yuan An, Sadid Hasan |
| Abstract | This paper presents a novel approach to the task of automatically inferring the most probable diagnosis from a given clinical narrative. Structured Knowledge Bases (KBs) can be useful for such complex tasks but not sufficient. Hence, we leverage a vast amount of unstructured free text to integrate with structured KBs. The key innovative ideas include building a concept graph from both structured and unstructured knowledge sources and ranking the diagnosis concepts using the enhanced word embedding vectors learned from integrated sources. Experiments on the TREC CDS and HumanDx datasets showed that our methods improved the results of clinical diagnosis inference. |
| Tasks | Information Retrieval, Question Answering |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1904/ |
| https://www.aclweb.org/anthology/W17-1904 | |
| PWC | https://paperswithcode.com/paper/improving-clinical-diagnosis-inference |
| Repo | |
| Framework | |
Extended Named Entity Recognition API and Its Applications in Language Education
| Title | Extended Named Entity Recognition API and Its Applications in Language Education |
| Authors | Tuan Duc Nguyen, Khai Mai, Thai-Hoang Pham, Minh Trung Nguyen, Truc-Vien T. Nguyen, Takashi Eguchi, Ryohei Sasano, Satoshi Sekine |
| Abstract | |
| Tasks | Dialogue Generation, Information Retrieval, Named Entity Recognition, Question Answering |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-4007/ |
| https://www.aclweb.org/anthology/P17-4007 | |
| PWC | https://paperswithcode.com/paper/extended-named-entity-recognition-api-and-its |
| Repo | |
| Framework | |
