Paper Group NANR 46
Interactive Visualization and Manipulation of Attention-based Neural Machine Translation. International Speech Communication Association Distinguished Lecture: Principles and Design of a System for Academic Information Retrieval based on Human-Machine Dialogue. Doubt, incredulity, and particles in Japanese falling interrogatives. A Multilingual Ent …
Interactive Visualization and Manipulation of Attention-based Neural Machine Translation
| Title | Interactive Visualization and Manipulation of Attention-based Neural Machine Translation |
| Authors | Jaesong Lee, Joong-Hwi Shin, Jun-Seok Kim |
| Abstract | While neural machine translation (NMT) provides high-quality translation, it is still hard to interpret and analyze its behavior. We present an interactive interface for visualizing and intervening behavior of NMT, specifically concentrating on the behavior of beam search mechanism and attention component. The tool (1) visualizes search tree and attention and (2) provides interface to adjust search tree and attention weight (manually or automatically) at real-time. We show the tool gives various methods to understand NMT. |
| Tasks | Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-2021/ |
| https://www.aclweb.org/anthology/D17-2021 | |
| PWC | https://paperswithcode.com/paper/interactive-visualization-and-manipulation-of |
| Repo | |
| Framework | |
International Speech Communication Association Distinguished Lecture: Principles and Design of a System for Academic Information Retrieval based on Human-Machine Dialogue
| Title | International Speech Communication Association Distinguished Lecture: Principles and Design of a System for Academic Information Retrieval based on Human-Machine Dialogue |
| Authors | Hiroya Fujisaki |
| Abstract | |
| Tasks | Dialogue Management, Information Retrieval |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/Y17-1002/ |
| https://www.aclweb.org/anthology/Y17-1002 | |
| PWC | https://paperswithcode.com/paper/international-speech-communication |
| Repo | |
| Framework | |
Doubt, incredulity, and particles in Japanese falling interrogatives
| Title | Doubt, incredulity, and particles in Japanese falling interrogatives |
| Authors | Lukas Rieser |
| Abstract | |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/Y17-1007/ |
| https://www.aclweb.org/anthology/Y17-1007 | |
| PWC | https://paperswithcode.com/paper/doubt-incredulity-and-particles-in-japanese |
| Repo | |
| Framework | |
A Multilingual Entity Linker Using PageRank and Semantic Graphs
| Title | A Multilingual Entity Linker Using PageRank and Semantic Graphs |
| Authors | Anton S{"o}dergren, Pierre Nugues |
| Abstract | |
| Tasks | Entity Linking, Named Entity Recognition, Question Answering |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0211/ |
| https://www.aclweb.org/anthology/W17-0211 | |
| PWC | https://paperswithcode.com/paper/a-multilingual-entity-linker-using-pagerank |
| Repo | |
| Framework | |
Joint Prediction of Word Alignment with Alignment Types
| Title | Joint Prediction of Word Alignment with Alignment Types |
| Authors | Anahita Mansouri Bigvand, Te Bu, Anoop Sarkar |
| Abstract | |
| Tasks | Machine Translation, Word Alignment, Word Embeddings |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/papers/Q17-1035/q17-1035 |
| https://www.aclweb.org/anthology/Q17-1035 | |
| PWC | https://paperswithcode.com/paper/joint-prediction-of-word-alignment-with |
| Repo | |
| Framework | |
Generating Image Descriptions using Multilingual Data
| Title | Generating Image Descriptions using Multilingual Data |
| Authors | Alan Jaffe |
| Abstract | |
| Tasks | Image Captioning, Language Modelling, Machine Translation, Multimodal Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4750/ |
| https://www.aclweb.org/anthology/W17-4750 | |
| PWC | https://paperswithcode.com/paper/generating-image-descriptions-using |
| Repo | |
| Framework | |
Towards Bootstrapping a Polarity Shifter Lexicon using Linguistic Features
| Title | Towards Bootstrapping a Polarity Shifter Lexicon using Linguistic Features |
| Authors | Marc Schulder, Michael Wiegand, Josef Ruppenhofer, Benjamin Roth |
| Abstract | |
| Tasks | Natural Language Inference, Relation Extraction, Sentiment Analysis |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/papers/I17-1063/i17-1063 |
| https://www.aclweb.org/anthology/I17-1063 | |
| PWC | https://paperswithcode.com/paper/towards-bootstrapping-a-polarity-shifter |
| Repo | |
| Framework | |
Going out on a limb: Joint Extraction of Entity Mentions and Relations without Dependency Trees
| Title | Going out on a limb: Joint Extraction of Entity Mentions and Relations without Dependency Trees |
| Authors | Arzoo Katiyar, Claire Cardie |
| Abstract | We present a novel attention-based recurrent neural network for joint extraction of entity mentions and relations. We show that attention along with long short term memory (LSTM) network can extract semantic relations between entity mentions without having access to dependency trees. Experiments on Automatic Content Extraction (ACE) corpora show that our model significantly outperforms feature-based joint model by Li and Ji (2014). We also compare our model with an end-to-end tree-based LSTM model (SPTree) by Miwa and Bansal (2016) and show that our model performs within 1{%} on entity mentions and 2{%} on relations. Our fine-grained analysis also shows that our model performs significantly better on Agent-Artifact relations, while SPTree performs better on Physical and Part-Whole relations. |
| Tasks | Relation Extraction |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1085/ |
| https://www.aclweb.org/anthology/P17-1085 | |
| PWC | https://paperswithcode.com/paper/going-out-on-a-limb-joint-extraction-of |
| Repo | |
| Framework | |
ITNLP-AiKF at SemEval-2017 Task 1: Rich Features Based SVR for Semantic Textual Similarity Computing
| Title | ITNLP-AiKF at SemEval-2017 Task 1: Rich Features Based SVR for Semantic Textual Similarity Computing |
| Authors | Wenjie Liu, Chengjie Sun, Lei Lin, Bingquan Liu |
| Abstract | Semantic Textual Similarity (STS) devotes to measuring the degree of equivalence in the underlying semantic of the sentence pair. We proposed a new system, ITNLP-AiKF, which applies in the SemEval 2017 Task1 Semantic Textual Similarity track 5 English monolingual pairs. In our system, rich features are involved, including Ontology based, word embedding based, Corpus based, Alignment based and Literal based feature. We leveraged the features to predict sentence pair similarity by a Support Vector Regression (SVR) model. In the result, a Pearson Correlation of 0.8231 is achieved by our system, which is a competitive result in the contest of this track. |
| Tasks | Feature Engineering, Semantic Textual Similarity |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2022/ |
| https://www.aclweb.org/anthology/S17-2022 | |
| PWC | https://paperswithcode.com/paper/itnlp-aikf-at-semeval-2017-task-1-rich |
| Repo | |
| Framework | |
Does Syntactic Informativity Predict Word Length? A Cross-Linguistic Study Based on the Universal Dependencies Corpora
| Title | Does Syntactic Informativity Predict Word Length? A Cross-Linguistic Study Based on the Universal Dependencies Corpora |
| Authors | Natalia Levshina |
| Abstract | |
| Tasks | |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0409/ |
| https://www.aclweb.org/anthology/W17-0409 | |
| PWC | https://paperswithcode.com/paper/does-syntactic-informativity-predict-word |
| Repo | |
| Framework | |
Neural Machine Translation for Cross-Lingual Pronoun Prediction
| Title | Neural Machine Translation for Cross-Lingual Pronoun Prediction |
| Authors | Sebastien Jean, Stanislas Lauly, Orhan Firat, Kyunghyun Cho |
| Abstract | In this paper we present our systems for the DiscoMT 2017 cross-lingual pronoun prediction shared task. For all four language pairs, we trained a standard attention-based neural machine translation system as well as three variants that incorporate information from the preceding source sentence. We show that our systems, which are not specifically designed for pronoun prediction and may be used to generate complete sentence translations, generally achieve competitive results on this task. |
| Tasks | Language Modelling, Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4806/ |
| https://www.aclweb.org/anthology/W17-4806 | |
| PWC | https://paperswithcode.com/paper/neural-machine-translation-for-cross-lingual |
| Repo | |
| Framework | |
NileTMRG at SemEval-2017 Task 8: Determining Rumour and Veracity Support for Rumours on Twitter.
| Title | NileTMRG at SemEval-2017 Task 8: Determining Rumour and Veracity Support for Rumours on Twitter. |
| Authors | Omar Enayet, Samhaa R. El-Beltagy |
| Abstract | Final submission for NileTMRG on RumourEval 2017. |
| Tasks | Rumour Detection |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2082/ |
| https://www.aclweb.org/anthology/S17-2082 | |
| PWC | https://paperswithcode.com/paper/niletmrg-at-semeval-2017-task-8-determining |
| Repo | |
| Framework | |
Cross-Lingual Word Representations: Induction and Evaluation
| Title | Cross-Lingual Word Representations: Induction and Evaluation |
| Authors | Manaal Faruqui, Anders S{\o}gaard, Ivan Vuli{'c} |
| Abstract | In recent past, NLP as a field has seen tremendous utility of distributional word vector representations as features in downstream tasks. The fact that these word vectors can be trained on unlabeled monolingual corpora of a language makes them an inexpensive resource in NLP. With the increasing use of monolingual word vectors, there is a need for word vectors that can be used as efficiently across multiple languages as monolingually. Therefore, learning bilingual and multilingual word embeddings/vectors is currently an important research topic. These vectors offer an elegant and language-pair independent way to represent content across different languages.This tutorial aims to bring NLP researchers up to speed with the current techniques in cross-lingual word representation learning. We will first discuss how to induce cross-lingual word representations (covering both bilingual and multilingual ones) from various data types and resources (e.g., parallel data, comparable data, non-aligned monolingual data in different languages, dictionaries and theasuri, or, even, images, eye-tracking data). We will then discuss how to evaluate such representations, intrinsically and extrinsically. We will introduce researchers to state-of-the-art methods for constructing cross-lingual word representations and discuss their applicability in a broad range of downstream NLP applications.We will deliver a detailed survey of the current methods, discuss best training and evaluation practices and use-cases, and provide links to publicly available implementations, datasets, and pre-trained models. |
| Tasks | Eye Tracking, Multilingual Word Embeddings, Representation Learning, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-3007/ |
| https://www.aclweb.org/anthology/D17-3007 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-word-representations-induction |
| Repo | |
| Framework | |
Gapping Constructions in Universal Dependencies v2
| Title | Gapping Constructions in Universal Dependencies v2 |
| Authors | Sebastian Schuster, Matthew Lamm, Christopher D. Manning |
| Abstract | |
| Tasks | |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0416/ |
| https://www.aclweb.org/anthology/W17-0416 | |
| PWC | https://paperswithcode.com/paper/gapping-constructions-in-universal |
| Repo | |
| Framework | |
Mixture-Rank Matrix Approximation for Collaborative Filtering
| Title | Mixture-Rank Matrix Approximation for Collaborative Filtering |
| Authors | Dongsheng Li, Chao Chen, Wei Liu, Tun Lu, Ning Gu, Stephen Chu |
| Abstract | Low-rank matrix approximation (LRMA) methods have achieved excellent accuracy among today’s collaborative filtering (CF) methods. In existing LRMA methods, the rank of user/item feature matrices is typically fixed, i.e., the same rank is adopted to describe all users/items. However, our studies show that submatrices with different ranks could coexist in the same user-item rating matrix, so that approximations with fixed ranks cannot perfectly describe the internal structures of the rating matrix, therefore leading to inferior recommendation accuracy. In this paper, a mixture-rank matrix approximation (MRMA) method is proposed, in which user-item ratings can be characterized by a mixture of LRMA models with different ranks. Meanwhile, a learning algorithm capitalizing on iterated condition modes is proposed to tackle the non-convex optimization problem pertaining to MRMA. Experimental studies on MovieLens and Netflix datasets demonstrate that MRMA can outperform six state-of-the-art LRMA-based CF methods in terms of recommendation accuracy. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6651-mixture-rank-matrix-approximation-for-collaborative-filtering |
| http://papers.nips.cc/paper/6651-mixture-rank-matrix-approximation-for-collaborative-filtering.pdf | |
| PWC | https://paperswithcode.com/paper/mixture-rank-matrix-approximation-for |
| Repo | |
| Framework | |
