October 16, 2019

1815 words 9 mins read

Paper Group NANR 40

Paper Group NANR 40

THU_NGN at SemEval-2018 Task 2: Residual CNN-LSTM Network with Attention for English Emoji Prediction. MMQA: A Multi-domain Multi-lingual Question-Answering Framework for English and Hindi. IPSL: A Database of Iconicity Patterns in Sign Languages. Creation and Use. Determining Event Durations: Models and Error Analysis. Using Lexical Alignment and …

THU_NGN at SemEval-2018 Task 2: Residual CNN-LSTM Network with Attention for English Emoji Prediction

Title THU_NGN at SemEval-2018 Task 2: Residual CNN-LSTM Network with Attention for English Emoji Prediction
Authors Chuhan Wu, Fangzhao Wu, Sixing Wu, Zhigang Yuan, Junxin Liu, Yongfeng Huang
Abstract Emojis are widely used by social media and social network users when posting their messages. It is important to study the relationships between messages and emojis. Thus, in SemEval-2018 Task 2 an interesting and challenging task is proposed, i.e., predicting which emojis are evoked by text-based tweets. We propose a residual CNN-LSTM with attention (\textbf{RCLA}) model for this task. Our model combines CNN and LSTM layers to capture both local and long-range contextual information for tweet representation. In addition, attention mechanism is used to select important components. Besides, residual connection is applied to CNN layers to facilitate the training of neural networks. We also incorporated additional features such as POS tags and sentiment features extracted from lexicons. Our model achieved 30.25{%} macro-averaged F-score in the first subtask (i.e., emoji prediction in English), ranking 7th out of 48 participants.
Tasks Sentiment Analysis
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1063/
PDF https://www.aclweb.org/anthology/S18-1063
PWC https://paperswithcode.com/paper/thu_ngn-at-semeval-2018-task-2-residual-cnn
Repo
Framework

MMQA: A Multi-domain Multi-lingual Question-Answering Framework for English and Hindi

Title MMQA: A Multi-domain Multi-lingual Question-Answering Framework for English and Hindi
Authors Deepak Gupta, Surabhi Kumari, Asif Ekbal, Pushpak Bhattacharyya
Abstract
Tasks Information Retrieval, Machine Translation, Question Answering
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1440/
PDF https://www.aclweb.org/anthology/L18-1440
PWC https://paperswithcode.com/paper/mmqa-a-multi-domain-multi-lingual-question
Repo
Framework

IPSL: A Database of Iconicity Patterns in Sign Languages. Creation and Use

Title IPSL: A Database of Iconicity Patterns in Sign Languages. Creation and Use
Authors Vadim Kimmelman, Anna Klezovich, George Moroz
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1667/
PDF https://www.aclweb.org/anthology/L18-1667
PWC https://paperswithcode.com/paper/ipsl-a-database-of-iconicity-patterns-in-sign
Repo
Framework

Determining Event Durations: Models and Error Analysis

Title Determining Event Durations: Models and Error Analysis
Authors Alakan Vempala, a, Eduardo Blanco, Alexis Palmer
Abstract This paper presents models to predict event durations. We introduce aspectual features that capture deeper linguistic information than previous work, and experiment with neural networks. Our analysis shows that tense, aspect and temporal structure of the clause provide useful clues, and that an LSTM ensemble captures relevant context around the event.
Tasks Question Answering
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-2026/
PDF https://www.aclweb.org/anthology/N18-2026
PWC https://paperswithcode.com/paper/determining-event-durations-models-and-error
Repo
Framework

Using Lexical Alignment and Referring Ability to Address Data Sparsity in Situated Dialog Reference Resolution

Title Using Lexical Alignment and Referring Ability to Address Data Sparsity in Situated Dialog Reference Resolution
Authors Todd Shore, Gabriel Skantze
Abstract Referring to entities in situated dialog is a collaborative process, whereby interlocutors often expand, repair and/or replace referring expressions in an iterative process, converging on conceptual pacts of referring language use in doing so. Nevertheless, much work on exophoric reference resolution (i.e. resolution of references to entities outside of a given text) follows a literary model, whereby individual referring expressions are interpreted as unique identifiers of their referents given the state of the dialog the referring expression is initiated. In this paper, we address this collaborative nature to improve dialogic reference resolution in two ways: First, we trained a words-as-classifiers logistic regression model of word semantics and incrementally adapt the model to idiosyncratic language between dyad partners during evaluation of the dialog. We then used these semantic models to learn the general referring ability of each word, which is independent of referent features. These methods facilitate accurate automatic reference resolution in situated dialog without annotation of referring expressions, even with little background data.
Tasks
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1252/
PDF https://www.aclweb.org/anthology/D18-1252
PWC https://paperswithcode.com/paper/using-lexical-alignment-and-referring-ability
Repo
Framework

VAST: A Corpus of Video Annotation for Speech Technologies

Title VAST: A Corpus of Video Annotation for Speech Technologies
Authors Jennifer Tracey, Stephanie Strassel
Abstract
Tasks Action Detection, Language Identification, Speaker Identification, Speech Recognition
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1682/
PDF https://www.aclweb.org/anthology/L18-1682
PWC https://paperswithcode.com/paper/vast-a-corpus-of-video-annotation-for-speech
Repo
Framework

The brWaC Corpus: A New Open Resource for Brazilian Portuguese

Title The brWaC Corpus: A New Open Resource for Brazilian Portuguese
Authors Jorge A. Wagner Filho, Rodrigo Wilkens, Marco Idiart, Aline Villavicencio
Abstract
Tasks Word Sense Induction
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1686/
PDF https://www.aclweb.org/anthology/L18-1686
PWC https://paperswithcode.com/paper/the-brwac-corpus-a-new-open-resource-for
Repo
Framework

Construction of a Multilingual Corpus Annotated with Translation Relations

Title Construction of a Multilingual Corpus Annotated with Translation Relations
Authors Yuming Zhai, Aur{'e}lien Max, Anne Vilnat
Abstract Translation relations, which distinguish literal translation from other translation techniques, constitute an important subject of study for human translators (Chuquet and Paillard, 1989). However, automatic processing techniques based on interlingual relations, such as machine translation or paraphrase generation exploiting translational equivalence, have not exploited these relations explicitly until now. In this work, we present a categorisation of translation relations and annotate them in a parallel multilingual (English, French, Chinese) corpus of oral presentations, the TED Talks. Our long term objective will be to automatically detect these relations in order to integrate them as important characteristics for the search of monolingual segments in relation of equivalence (paraphrases) or of entailment. The annotated corpus resulting from our work will be made available to the community.
Tasks Machine Translation, Paraphrase Generation
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-3814/
PDF https://www.aclweb.org/anthology/W18-3814
PWC https://paperswithcode.com/paper/construction-of-a-multilingual-corpus
Repo
Framework

Learning a face space for experiments on human identity

Title Learning a face space for experiments on human identity
Authors Joshua Peterson, Jordan Suchow, Thomas Griffiths
Abstract Generative models of human identity and appearance have broad applicability to behavioral science and technology, but the exquisite sensitivity of human face perception means that their utility hinges on alignment of the latent representation to human psychological representations and the photorealism of the generated images. Meeting these requirements is an exacting task, and existing models of human identity and appearance are often unworkably abstract, artificial, uncanny, or heavily biased. Here, we use a variational autoencoder with an autoregressive decoder to learn a latent face space from a uniquely diverse dataset of portraits that control much of the variation irrelevant to human identity and appearance. Our method generates photorealistic portraits of fictive identities with a smooth, navigable latent space. We validate our model’s alignment with human sensitivities by introducing a psychophysical Turing test for images, which humans mostly fail, a rare occurrence with any interesting generative image model. Lastly, we demonstrate an initial application of our model to the problem of fast search in mental space to obtain detailed police sketches in a small number of trials.
Tasks
Published 2018-01-01
URL https://openreview.net/forum?id=HyiS6k-CW
PDF https://openreview.net/pdf?id=HyiS6k-CW
PWC https://paperswithcode.com/paper/learning-a-face-space-for-experiments-on
Repo
Framework

Exploratory Neural Relation Classification for Domain Knowledge Acquisition

Title Exploratory Neural Relation Classification for Domain Knowledge Acquisition
Authors Yan Fan, Chengyu Wang, Xiaofeng He
Abstract The state-of-the-art methods for relation classification are primarily based on deep neural net- works. This kind of supervised learning method suffers from not only limited training data, but also the large number of low-frequency relations in specific domains. In this paper, we propose the task of exploratory relation classification for domain knowledge harvesting. The goal is to learn a classifier on pre-defined relations and discover new relations expressed in texts. A dynamically structured neural network is introduced to classify entity pairs to a continuously expanded relation set. We further propose the similarity sensitive Chinese restaurant process to discover new relations. Experiments conducted on a large corpus show the effectiveness of our neural network, while new relations are discovered with high precision and recall.
Tasks Knowledge Graphs, Relation Classification
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1192/
PDF https://www.aclweb.org/anthology/C18-1192
PWC https://paperswithcode.com/paper/exploratory-neural-relation-classification
Repo
Framework

Using Morphemes from Agglutinative Languages like Quechua and Finnish to Aid in Low-Resource Translation

Title Using Morphemes from Agglutinative Languages like Quechua and Finnish to Aid in Low-Resource Translation
Authors John Ortega, Krishnan Pillaipakkamnatt
Abstract
Tasks Machine Translation, Word Alignment
Published 2018-03-01
URL https://www.aclweb.org/anthology/W18-2201/
PDF https://www.aclweb.org/anthology/W18-2201
PWC https://paperswithcode.com/paper/using-morphemes-from-agglutinative-languages
Repo
Framework

Retrieving Information from the French Lexical Network in RDF/OWL Format

Title Retrieving Information from the French Lexical Network in RDF/OWL Format
Authors Alexs Fonseca, ro, Fatiha Sadat, Fran{\c{c}}ois Lareau
Abstract
Tasks Knowledge Graphs
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1698/
PDF https://www.aclweb.org/anthology/L18-1698
PWC https://paperswithcode.com/paper/retrieving-information-from-the-french
Repo
Framework

Portuguese Named Entity Recognition using Conditional Random Fields and Local Grammars

Title Portuguese Named Entity Recognition using Conditional Random Fields and Local Grammars
Authors Juliana Pirovani, Elias Oliveira
Abstract
Tasks Named Entity Recognition, Question Answering, Structured Prediction
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1705/
PDF https://www.aclweb.org/anthology/L18-1705
PWC https://paperswithcode.com/paper/portuguese-named-entity-recognition-using
Repo
Framework

attr2vec: Jointly Learning Word and Contextual Attribute Embeddings with Factorization Machines

Title attr2vec: Jointly Learning Word and Contextual Attribute Embeddings with Factorization Machines
Authors Fabio Petroni, Vassilis Plachouras, Timothy Nugent, Jochen L. Leidner
Abstract The widespread use of word embeddings is associated with the recent successes of many natural language processing (NLP) systems. The key approach of popular models such as word2vec and GloVe is to learn dense vector representations from the context of words. More recently, other approaches have been proposed that incorporate different types of contextual information, including topics, dependency relations, n-grams, and sentiment. However, these models typically integrate only limited additional contextual information, and often in ad hoc ways. In this work, we introduce attr2vec, a novel framework for jointly learning embeddings for words and contextual attributes based on factorization machines. We perform experiments with different types of contextual information. Our experimental results on a text classification task demonstrate that using attr2vec to jointly learn embeddings for words and Part-of-Speech (POS) tags improves results compared to learning the embeddings independently. Moreover, we use attr2vec to train dependency-based embeddings and we show that they exhibit higher similarity between functionally related words compared to traditional approaches.
Tasks Dependency Parsing, Information Retrieval, Machine Translation, Sentence Classification, Text Classification, Word Embeddings
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-1042/
PDF https://www.aclweb.org/anthology/N18-1042
PWC https://paperswithcode.com/paper/attr2vec-jointly-learning-word-and-contextual
Repo
Framework

LSTMs Can Learn Syntax-Sensitive Dependencies Well, But Modeling Structure Makes Them Better

Title LSTMs Can Learn Syntax-Sensitive Dependencies Well, But Modeling Structure Makes Them Better
Authors Adhiguna Kuncoro, Chris Dyer, John Hale, Dani Yogatama, Stephen Clark, Phil Blunsom
Abstract Language exhibits hierarchical structure, but recent work using a subject-verb agreement diagnostic argued that state-of-the-art language models, LSTMs, fail to learn long-range syntax sensitive dependencies. Using the same diagnostic, we show that, in fact, LSTMs do succeed in learning such dependencies{—}provided they have enough capacity. We then explore whether models that have access to explicit syntactic information learn agreement more effectively, and how the way in which this structural information is incorporated into the model impacts performance. We find that the mere presence of syntactic information does not improve accuracy, but when model architecture is determined by syntax, number agreement is improved. Further, we find that the choice of how syntactic structure is built affects how well number agreement is learned: top-down construction outperforms left-corner and bottom-up variants in capturing non-local structural dependencies.
Tasks Language Modelling, Machine Translation, Text Summarization
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-1132/
PDF https://www.aclweb.org/anthology/P18-1132
PWC https://paperswithcode.com/paper/lstms-can-learn-syntax-sensitive-dependencies
Repo
Framework
comments powered by Disqus