Paper Group NANR 10
Hierarchical Word Structure-based Parsing: A Feasibility Study on UD-style Dependency Parsing in Japanese. #ActuallyDepressed: Characterization of Depressed Tumblr Users’ Online Behavior from Rules Generation Machine Learning Technique. Annotation of Clinical Narratives in Bulgarian language. A Unified Framework for Structured Prediction: From The …
Hierarchical Word Structure-based Parsing: A Feasibility Study on UD-style Dependency Parsing in Japanese
| Title | Hierarchical Word Structure-based Parsing: A Feasibility Study on UD-style Dependency Parsing in Japanese |
| Authors | Takaaki Tanaka, Katsuhiko Hayashi, Masaaki Nagata |
| Abstract | In applying word-based dependency parsing such as Universal Dependencies (UD) to Japanese, the uncertainty of word segmentation emerges for defining a word unit of the dependencies. We introduce the following hierarchical word structures to dependency parsing in Japanese: morphological units (a short unit word, SUW) and syntactic units (a long unit word, LUW). An SUW can be used to segment a sentence consistently, while it is too short to represent syntactic construction. An LUW is a unit including functional multiwords and LUW-based analysis facilitates the capturing of syntactic structure and makes parsing results more precise than SUW-based analysis. This paper describes the results of a feasibility study on the ability and the effectiveness of parsing methods based on hierarchical word structure (LUW chunking+parsing) in comparison to single layer word structure (SUW parsing). We also show joint analysis of LUW-chunking and dependency parsing improves the performance of identifying predicate-argument structures, while there is not much difference between overall results of them. not much difference between overall results of them. |
| Tasks | Chunking, Dependency Parsing, Morphological Analysis |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6308/ |
| https://www.aclweb.org/anthology/W17-6308 | |
| PWC | https://paperswithcode.com/paper/hierarchical-word-structure-based-parsing-a |
| Repo | |
| Framework | |
#ActuallyDepressed: Characterization of Depressed Tumblr Users’ Online Behavior from Rules Generation Machine Learning Technique
| Title | #ActuallyDepressed: Characterization of Depressed Tumblr Users’ Online Behavior from Rules Generation Machine Learning Technique |
| Authors | Czarina Rae Cahutay, Aileen Joan Vicente |
| Abstract | |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/Y17-1020/ |
| https://www.aclweb.org/anthology/Y17-1020 | |
| PWC | https://paperswithcode.com/paper/actuallydepressed-characterization-of |
| Repo | |
| Framework | |
Annotation of Clinical Narratives in Bulgarian language
| Title | Annotation of Clinical Narratives in Bulgarian language |
| Authors | Ivajlo Radev, Kiril Simov, Galia Angelova, Svetla Boytcheva |
| Abstract | In this paper we describe annotation process of clinical texts with morphosyntactic and semantic information. The corpus contains 1,300 discharge letters in Bulgarian language for patients with Endocrinology and Metabolic disorders. The annotated corpus will be used as a Gold standard for information extraction evaluation of test corpus of 6,200 discharge letters. The annotation is performed within Clark system {—} an XML Based System For Corpora Development. It provides mechanism for semi-automatic annotation first running a pipeline for Bulgarian morphosyntactic annotation and a cascaded regular grammar for semantic annotation is run, then rules for cleaning of frequent errors are applied. At the end the result is manually checked. At the end we hope also to be able to adapted the morphosyntactic tagger to the domain of clinical narratives as well. |
| Tasks | Chunking, Dependency Parsing, Information Retrieval, Tokenization |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-8011/ |
| https://doi.org/10.26615/978-954-452-044-1_011 | |
| PWC | https://paperswithcode.com/paper/annotation-of-clinical-narratives-in |
| Repo | |
| Framework | |
A Unified Framework for Structured Prediction: From Theory to Practice
| Title | A Unified Framework for Structured Prediction: From Theory to Practice |
| Authors | Wei Lu |
| Abstract | Structured prediction is one of the most important topics in various fields, including machine learning, computer vision, natural language processing (NLP) and bioinformatics. In this tutorial, we present a novel framework that unifies various structured prediction models.The hidden Markov model (HMM) and the probabilistic context-free grammars (PCFGs) are two classic generative models used for predicting outputs with linear-chain and tree structures, respectively. As HMM{'}s discriminative counterpart, the linear-chain conditional random fields (CRFs) (Lafferty et al., 2001) model was later proposed. Such a model was shown to yield good performance on standard NLP tasks such as information extraction. Several extensions to such a model were then proposed afterward, including the semi-Markov CRFs (Sarawagi and Cohen, 2004), tree CRFs (Cohn and Blunsom, 2005), as well as discriminative parsing models and their latent variable variants (Petrov and Klein, 2007). On the other hand, utilizing a slightly different loss function, one could arrive at the structured support vector machines (Tsochantaridis et al., 2004) and its latent variable variant (Yu and Joachims, 2009) as well. Furthermore, new models that integrate neural networks and graphical models, such as neural CRFs (Do et al., 2010) were also proposed.In this tutorial, we will be discussing how such a wide spectrum of existing structured prediction models can all be implemented under a unified framework (available at here) that involves some basic building blocks. Based on such a framework, we show how some seemingly complicated structured prediction models such as a semantic parsing model (Lu et al., 2008; Lu, 2014) can be implemented conveniently and quickly. Furthermore, we also show that the framework can be used to solve certain structured prediction problems that otherwise cannot be easily handled by conventional structured prediction models. Specifically, we show how to use such a framework to construct models that are capable of predicting non-conventional structures, such as overlapping structures (Lu and Roth, 2015; Muis and Lu, 2016a). We will also discuss how to make use of the framework to build other related models such as topic models and highlight its potential applications in some recent popular tasks (e.g., AMR parsing (Flanigan et al., 2014)).The framework has been extensively used by our research group for developing various structured prediction models, including models for information extraction (Lu and Roth, 2015; Muis and Lu, 2016a; Jie et al., 2017), noun phrase chunking (Muis and Lu, 2016b), semantic parsing (Lu, 2015; Susanto and Lu, 2017), and sentiment analysis (Li and Lu, 2017). It is our hope that this tutorial will be helpful for many natural language processing researchers who are interested in designing their own structured prediction models rapidly. We also hope this tutorial allows researchers to strengthen their understandings on the connections between various structured prediction models, and that the open release of the framework will bring value to the NLP research community and enhance its overall productivity.The material associated with this tutorial will be available at the tutorial web site: https://web.archive.org/web/20180427113151/http://statnlp.org/tutorials/. |
| Tasks | Amr Parsing, Chunking, Semantic Parsing, Sentiment Analysis, Structured Prediction, Topic Models |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-3006/ |
| https://www.aclweb.org/anthology/D17-3006 | |
| PWC | https://paperswithcode.com/paper/a-unified-framework-for-structured-prediction |
| Repo | |
| Framework | |
PKU_ICL at SemEval-2017 Task 10: Keyphrase Extraction with Model Ensemble and External Knowledge
| Title | PKU_ICL at SemEval-2017 Task 10: Keyphrase Extraction with Model Ensemble and External Knowledge |
| Authors | Liang Wang, Sujian Li |
| Abstract | This paper presents a system that participated in SemEval 2017 Task 10 (subtask A and subtask B): Extracting Keyphrases and Relations from Scientific Publications (Augenstein et al., 2017). Our proposed approach utilizes external knowledge to enrich feature representation of candidate keyphrase, including Wikipedia, IEEE taxonomy and pre-trained word embeddings etc. Ensemble of unsupervised models, random forest and linear models are used for candidate keyphrase ranking and keyphrase type classification. Our system achieves the 3rd place in subtask A and 4th place in subtask B. |
| Tasks | Chunking, Feature Engineering, Information Retrieval, Text Classification, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2161/ |
| https://www.aclweb.org/anthology/S17-2161 | |
| PWC | https://paperswithcode.com/paper/pku_icl-at-semeval-2017-task-10-keyphrase |
| Repo | |
| Framework | |
What are the limitations on the flux of syntactic dependencies? Evidence from UD treebanks
| Title | What are the limitations on the flux of syntactic dependencies? Evidence from UD treebanks |
| Authors | Sylvain Kahane, Chunxiao Yan, Marie-Am{'e}lie Botalla |
| Abstract | |
| Tasks | Language Modelling |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6510/ |
| https://www.aclweb.org/anthology/W17-6510 | |
| PWC | https://paperswithcode.com/paper/what-are-the-limitations-on-the-flux-of |
| Repo | |
| Framework | |
Neural Paraphrase Generation using Transfer Learning
| Title | Neural Paraphrase Generation using Transfer Learning |
| Authors | Florin Brad, Traian Rebedea |
| Abstract | Progress in statistical paraphrase generation has been hindered for a long time by the lack of large monolingual parallel corpora. In this paper, we adapt the neural machine translation approach to paraphrase generation and perform transfer learning from the closely related task of entailment generation. We evaluate the model on the Microsoft Research Paraphrase (MSRP) corpus and show that the model is able to generate sentences that capture part of the original meaning, but fails to pick up on important words or to show large lexical variation. |
| Tasks | Machine Translation, Natural Language Inference, Paraphrase Generation, Question Answering, Text Generation, Transfer Learning |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3542/ |
| https://www.aclweb.org/anthology/W17-3542 | |
| PWC | https://paperswithcode.com/paper/neural-paraphrase-generation-using-transfer |
| Repo | |
| Framework | |
Quantitative Comparative Syntax on the Cantonese-Mandarin Parallel Dependency Treebank
| Title | Quantitative Comparative Syntax on the Cantonese-Mandarin Parallel Dependency Treebank |
| Authors | Tak-sum Wong, Kim Gerdes, Herman Leung, John Lee |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6530/ |
| https://www.aclweb.org/anthology/W17-6530 | |
| PWC | https://paperswithcode.com/paper/quantitative-comparative-syntax-on-the |
| Repo | |
| Framework | |
Adaptive RNN Tree for Large-Scale Human Action Recognition
| Title | Adaptive RNN Tree for Large-Scale Human Action Recognition |
| Authors | Wenbo Li, Longyin Wen, Ming-Ching Chang, Ser Nam Lim, Siwei Lyu |
| Abstract | In this work, we present the RNN Tree (RNN-T), an adaptive learning framework for skeleton based human action recognition. Our method categorizes action classes and uses multiple Recurrent Neural Networks (RNNs) in a tree-like hierarchy. The RNNs in RNN-T are co-trained with the action category hierarchy, which determines the structure of RNN-T. Actions in skeletal representations are recognized via a hierarchical inference process, during which individual RNNs differentiate finer-grained action classes with increasing confidence. Inference in RNN-T ends when any RNN in the tree recognizes the action with high confidence, or a leaf node is reached. RNN-T effectively addresses two main challenges of large-scale action recognition: (i) able to distinguish fine-grained action classes that are intractable using a single network, and (ii) adaptive to new action classes by augmenting an existing model. We demonstrate the effectiveness of RNN-T/ACH method and compare it with the state-of-the-art methods on a large-scale dataset and several existing benchmarks. |
| Tasks | Skeleton Based Action Recognition, Temporal Action Localization |
| Published | 2017-10-22 |
| URL | https://ieeexplore.ieee.org/document/8237423 |
| https://ieeexplore.ieee.org/document/8237423 | |
| PWC | https://paperswithcode.com/paper/adaptive-rnn-tree-for-large-scale-human-1 |
| Repo | |
| Framework | |
Refer-iTTS: A System for Referring in Spoken Installments to Objects in Real-World Images
| Title | Refer-iTTS: A System for Referring in Spoken Installments to Objects in Real-World Images |
| Authors | Sina Zarrie{\ss}, M. Soledad L{'o}pez Gambino, David Schlangen |
| Abstract | Current referring expression generation systems mostly deliver their output as one-shot, written expressions. We present on-going work on incremental generation of spoken expressions referring to objects in real-world images. This approach extends upon previous work using the words-as-classifier model for generation. We implement this generator in an incremental dialogue processing framework such that we can exploit an existing interface to incremental text-to-speech synthesis. Our system generates and synthesizes referring expressions while continuously observing non-verbal user reactions. |
| Tasks | Speech Synthesis, Text Generation, Text-To-Speech Synthesis |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3509/ |
| https://www.aclweb.org/anthology/W17-3509 | |
| PWC | https://paperswithcode.com/paper/refer-itts-a-system-for-referring-in-spoken |
| Repo | |
| Framework | |
Using hyperlinks to improve multilingual partial parsers
| Title | Using hyperlinks to improve multilingual partial parsers |
| Authors | Anders S{\o}gaard |
| Abstract | Syntactic annotation is costly and not available for the vast majority of the world{'}s languages. We show that sometimes we can do away with less labeled data by exploiting more readily available forms of mark-up. Specifically, we revisit an idea from Valentin Spitkovsky{'}s work (2010), namely that hyperlinks typically bracket syntactic constituents or chunks. We strengthen his results by showing that not only can hyperlinks help in low resource scenarios, exemplified here by Quechua, but learning from hyperlinks can also improve state-of-the-art NLP models for English newswire. We also present out-of-domain evaluation on English Ontonotes 4.0. |
| Tasks | Machine Translation, Speech Synthesis |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6310/ |
| https://www.aclweb.org/anthology/W17-6310 | |
| PWC | https://paperswithcode.com/paper/using-hyperlinks-to-improve-multilingual |
| Repo | |
| Framework | |
EmoNet: Fine-Grained Emotion Detection with Gated Recurrent Neural Networks
| Title | EmoNet: Fine-Grained Emotion Detection with Gated Recurrent Neural Networks |
| Authors | Muhammad Abdul-Mageed, Lyle Ungar |
| Abstract | Accurate detection of emotion from natural language has applications ranging from building emotional chatbots to better understanding individuals and their lives. However, progress on emotion detection has been hampered by the absence of large labeled datasets. In this work, we build a very large dataset for fine-grained emotions and develop deep learning models on it. We achieve a new state-of-the-art on 24 fine-grained types of emotions (with an average accuracy of 87.58{%}). We also extend the task beyond emotion types to model Robert Plutick{'}s 8 primary emotion dimensions, acquiring a superior accuracy of 95.68{%}. |
| Tasks | Decision Making |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1067/ |
| https://www.aclweb.org/anthology/P17-1067 | |
| PWC | https://paperswithcode.com/paper/emonet-fine-grained-emotion-detection-with |
| Repo | |
| Framework | |
Fast and Accurate Decision Trees for Natural Language Processing Tasks
| Title | Fast and Accurate Decision Trees for Natural Language Processing Tasks |
| Authors | Tiberiu Boros, Stefan Daniel Dumitrescu, Sonia Pipa |
| Abstract | Decision trees have been previously employed in many machine-learning tasks such as part-of-speech tagging, lemmatization, morphological-attribute resolution, letter-to-sound conversion and statistical-parametric speech synthesis. In this paper we introduce an optimized tree-computation algorithm, which is based on the original ID3 algorithm. We also introduce a tree-pruning method that uses a development set to delete nodes from over-fitted models. The later mentioned algorithm also uses a results caching method for speed-up. Our algorithm is almost 200 times faster than a naive implementation and yields accurate results on our test datasets. |
| Tasks | Feature Engineering, Lemmatization, Named Entity Recognition, Part-Of-Speech Tagging, Speech Synthesis, Text Categorization |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1016/ |
| https://doi.org/10.26615/978-954-452-049-6_016 | |
| PWC | https://paperswithcode.com/paper/fast-and-accurate-decision-trees-for-natural |
| Repo | |
| Framework | |
Enrichment of French Biomedical Ontologies with UMLS Concepts and Semantic Types for Biomedical Named Entity Recognition Though Ontological Semantic Annotation
| Title | Enrichment of French Biomedical Ontologies with UMLS Concepts and Semantic Types for Biomedical Named Entity Recognition Though Ontological Semantic Annotation |
| Authors | Andon Tchechmedjiev, Cl{'e}ment Jonquet |
| Abstract | |
| Tasks | Information Retrieval, Named Entity Recognition |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-7007/ |
| https://www.aclweb.org/anthology/W17-7007 | |
| PWC | https://paperswithcode.com/paper/enrichment-of-french-biomedical-ontologies |
| Repo | |
| Framework | |
Forma\cc~ao de gent'\ilicos a partir de top^onimos: descri\cc~ao lingu'\istica e aprendizado autom'atico (Formation of Demonyms from Toponyms: Linguistic Description and Machine Learning)[In Portuguese]
| Title | Forma\cc~ao de gent'\ilicos a partir de top^onimos: descri\cc~ao lingu'\istica e aprendizado autom'atico (Formation of Demonyms from Toponyms: Linguistic Description and Machine Learning)[In Portuguese] |
| Authors | Roger Alfredo Marci Rodrigues Antunes, Thiago Pardo, Gladis Maria Barcelos Almeida |
| Abstract | |
| Tasks | |
| Published | 2017-10-01 |
| URL | https://www.aclweb.org/anthology/W17-6610/ |
| https://www.aclweb.org/anthology/W17-6610 | |
| PWC | https://paperswithcode.com/paper/formaaao-de-gentalicos-a-partir-de-topa-nimos |
| Repo | |
| Framework | |
