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

Obfuscation for Privacy-preserving Syntactic Parsing

Apr 21, 2019
Zhifeng Hu, Serhii Havrylov, Ivan Titov, Shay B. Cohen

The goal of homomorphic encryption is to encrypt data such that another party can operate on it without being explicitly exposed to the content of the original data. We introduce an idea for a privacy-preserving transformation on natural language data, inspired by homomorphic encryption. Our primary tool is {\em obfuscation}, relying on the properties of natural language. Specifically, a given text is obfuscated using a neural model that aims to preserve the syntactic relationships of the original sentence so that the obfuscated sentence can be parsed instead of the original one. The model works at the word level, and learns to obfuscate each word separately by changing it into a new word that has a similar syntactic role. The text encrypted by our model leads to better performance on three syntactic parsers (two dependency and one constituency parsers) in comparison to a strong random baseline. The substituted words have similar syntactic properties, but different semantic content, compared to the original words.

  Access Paper or Ask Questions

Is Wasserstein all you need?

Oct 18, 2018
Sidak Pal Singh, Andreas Hug, Aymeric Dieuleveut, Martin Jaggi

We propose a unified framework for building unsupervised representations of entities and their compositions, by viewing each entity as a histogram (or distribution) over its contexts. This enables us to take advantage of optimal transport and construct representations that effectively harness the geometry of the underlying space containing the contexts. Our method captures uncertainty via modelling the entities as distributions and simultaneously provides interpretability with the optimal transport map, hence giving a novel perspective for building rich and powerful feature representations. As a guiding example, we formulate unsupervised representations for text, and demonstrate it on tasks such as sentence similarity and word entailment detection. Empirical results show strong advantages gained through the proposed framework. This approach can potentially be used for any unsupervised or supervised problem (on text or other modalities) with a co-occurrence structure, such as any sequence data. The key tools at the core of this framework are Wasserstein distances and Wasserstein barycenters, hence raising the question from our title.

  Access Paper or Ask Questions

Tree-structured multi-stage principal component analysis (TMPCA): theory and applications

Oct 07, 2018
Yuanhang Su, Ruiyuan Lin, C. -C. Jay Kuo

A PCA based sequence-to-vector (seq2vec) dimension reduction method for the text classification problem, called the tree-structured multi-stage principal component analysis (TMPCA) is presented in this paper. Theoretical analysis and applicability of TMPCA are demonstrated as an extension to our previous work (Su, Huang & Kuo). Unlike conventional word-to-vector embedding methods, the TMPCA method conducts dimension reduction at the sequence level without labeled training data. Furthermore, it can preserve the sequential structure of input sequences. We show that TMPCA is computationally efficient and able to facilitate sequence-based text classification tasks by preserving strong mutual information between its input and output mathematically. It is also demonstrated by experimental results that a dense (fully connected) network trained on the TMPCA preprocessed data achieves better performance than state-of-the-art fastText and other neural-network-based solutions.

  Access Paper or Ask Questions

Analyzing Learned Representations of a Deep ASR Performance Prediction Model

Aug 28, 2018
Zied Elloumi, Laurent Besacier, Olivier Galibert, Benjamin Lecouteux

This paper addresses a relatively new task: prediction of ASR performance on unseen broadcast programs. In a previous paper, we presented an ASR performance prediction system using CNNs that encode both text (ASR transcript) and speech, in order to predict word error rate. This work is dedicated to the analysis of speech signal embeddings and text embeddings learnt by the CNN while training our prediction model. We try to better understand which information is captured by the deep model and its relation with different conditioning factors. It is shown that hidden layers convey a clear signal about speech style, accent and broadcast type. We then try to leverage these 3 types of information at training time through multi-task learning. Our experiments show that this allows to train slightly more efficient ASR performance prediction systems that - in addition - simultaneously tag the analyzed utterances according to their speech style, accent and broadcast program origin.

* EMNLP 2018 Workshop 

  Access Paper or Ask Questions

QuAC : Question Answering in Context

Aug 28, 2018
Eunsol Choi, He He, Mohit Iyyer, Mark Yatskar, Wen-tau Yih, Yejin Choi, Percy Liang, Luke Zettlemoyer

We present QuAC, a dataset for Question Answering in Context that contains 14K information-seeking QA dialogs (100K questions in total). The dialogs involve two crowd workers: (1) a student who poses a sequence of freeform questions to learn as much as possible about a hidden Wikipedia text, and (2) a teacher who answers the questions by providing short excerpts from the text. QuAC introduces challenges not found in existing machine comprehension datasets: its questions are often more open-ended, unanswerable, or only meaningful within the dialog context, as we show in a detailed qualitative evaluation. We also report results for a number of reference models, including a recently state-of-the-art reading comprehension architecture extended to model dialog context. Our best model underperforms humans by 20 F1, suggesting that there is significant room for future work on this data. Dataset, baseline, and leaderboard available at

* EMNLP Camera Ready 

  Access Paper or Ask Questions

Visually grounded cross-lingual keyword spotting in speech

Jun 13, 2018
Herman Kamper, Michael Roth

Recent work considered how images paired with speech can be used as supervision for building speech systems when transcriptions are not available. We ask whether visual grounding can be used for cross-lingual keyword spotting: given a text keyword in one language, the task is to retrieve spoken utterances containing that keyword in another language. This could enable searching through speech in a low-resource language using text queries in a high-resource language. As a proof-of-concept, we use English speech with German queries: we use a German visual tagger to add keyword labels to each training image, and then train a neural network to map English speech to German keywords. Without seeing parallel speech-transcriptions or translations, the model achieves a precision at ten of 58%. We show that most erroneous retrievals contain equivalent or semantically relevant keywords; excluding these would improve [email protected] to 91%.

* 5 pages, 2 figures, 4 tables 

  Access Paper or Ask Questions

Localizing and Quantifying Damage in Social Media Images

Jun 09, 2018
Xukun Li, Huaiyu Zhang, Doina Caragea, Muhammad Imran

Traditional post-disaster assessment of damage heavily relies on expensive GIS data, especially remote sensing image data. In recent years, social media has become a rich source of disaster information that may be useful in assessing damage at a lower cost. Such information includes text (e.g., tweets) or images posted by eyewitnesses of a disaster. Most of the existing research explores the use of text in identifying situational awareness information useful for disaster response teams. The use of social media images to assess disaster damage is limited. In this paper, we propose a novel approach, based on convolutional neural networks and class activation maps, to locate damage in a disaster image and to quantify the degree of the damage. Our proposed approach enables the use of social network images for post-disaster damage assessment and provides an inexpensive and feasible alternative to the more expensive GIS approach.

  Access Paper or Ask Questions

QA4IE: A Question Answering based Framework for Information Extraction

Apr 10, 2018
Lin Qiu, Hao Zhou, Yanru Qu, Weinan Zhang, Suoheng Li, Shu Rong, Dongyu Ru, Lihua Qian, Kewei Tu, Yong Yu

Information Extraction (IE) refers to automatically extracting structured relation tuples from unstructured texts. Common IE solutions, including Relation Extraction (RE) and open IE systems, can hardly handle cross-sentence tuples, and are severely restricted by limited relation types as well as informal relation specifications (e.g., free-text based relation tuples). In order to overcome these weaknesses, we propose a novel IE framework named QA4IE, which leverages the flexible question answering (QA) approaches to produce high quality relation triples across sentences. Based on the framework, we develop a large IE benchmark with high quality human evaluation. This benchmark contains 293K documents, 2M golden relation triples, and 636 relation types. We compare our system with some IE baselines on our benchmark and the results show that our system achieves great improvements.

  Access Paper or Ask Questions

Meta Multi-Task Learning for Sequence Modeling

Feb 25, 2018
Junkun Chen, Xipeng Qiu, Pengfei Liu, Xuanjing Huang

Semantic composition functions have been playing a pivotal role in neural representation learning of text sequences. In spite of their success, most existing models suffer from the underfitting problem: they use the same shared compositional function on all the positions in the sequence, thereby lacking expressive power due to incapacity to capture the richness of compositionality. Besides, the composition functions of different tasks are independent and learned from scratch. In this paper, we propose a new sharing scheme of composition function across multiple tasks. Specifically, we use a shared meta-network to capture the meta-knowledge of semantic composition and generate the parameters of the task-specific semantic composition models. We conduct extensive experiments on two types of tasks, text classification and sequence tagging, which demonstrate the benefits of our approach. Besides, we show that the shared meta-knowledge learned by our proposed model can be regarded as off-the-shelf knowledge and easily transferred to new tasks.

* published in The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18), 2018 

  Access Paper or Ask Questions

Stance Detection in Turkish Tweets

Jun 21, 2017
Dilek Küçük

Stance detection is a classification problem in natural language processing where for a text and target pair, a class result from the set {Favor, Against, Neither} is expected. It is similar to the sentiment analysis problem but instead of the sentiment of the text author, the stance expressed for a particular target is investigated in stance detection. In this paper, we present a stance detection tweet data set for Turkish comprising stance annotations of these tweets for two popular sports clubs as targets. Additionally, we provide the evaluation results of SVM classifiers for each target on this data set, where the classifiers use unigram, bigram, and hashtag features. This study is significant as it presents one of the initial stance detection data sets proposed so far and the first one for Turkish language, to the best of our knowledge. The data set and the evaluation results of the corresponding SVM-based approaches will form plausible baselines for the comparison of future studies on stance detection.

* Accepted to be presented at the 3rd International Workshop on Social Media World Sensors (SIDEWAYS) of the 28th ACM Conference on Hypertext and Social Media (2017) 

  Access Paper or Ask Questions