Paper Group NANR 77
LSTM Shift-Reduce CCG Parsing. TermoPL - a Flexible Tool for Terminology Extraction. Learning Transferrable Representations for Unsupervised Domain Adaptation. Corpora for Learning the Mutual Relationship between Semantic Relatedness and Textual Entailment. Syntax-based Multi-system Machine Translation. Progressively Parsing Interactional Objects f …
LSTM Shift-Reduce CCG Parsing
| Title | LSTM Shift-Reduce CCG Parsing |
| Authors | Wenduan Xu |
| Abstract | |
| Tasks | Feature Engineering |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/papers/D16-1181/d16-1181 |
| https://www.aclweb.org/anthology/D16-1181v2 | |
| PWC | https://paperswithcode.com/paper/lstm-shift-reduce-ccg-parsing |
| Repo | |
| Framework | |
TermoPL - a Flexible Tool for Terminology Extraction
| Title | TermoPL - a Flexible Tool for Terminology Extraction |
| Authors | Malgorzata Marciniak, Agnieszka Mykowiecka, Piotr Rychlik |
| Abstract | The purpose of this paper is to introduce the TermoPL tool created to extract terminology from domain corpora in Polish. The program extracts noun phrases, term candidates, with the help of a simple grammar that can be adapted for user{'}s needs. It applies the C-value method to rank term candidates being either the longest identified nominal phrases or their nested subphrases. The method operates on simplified base forms in order to unify morphological variants of terms and to recognize their contexts. We support the recognition of nested terms by word connection strength which allows us to eliminate truncated phrases from the top part of the term list. The program has an option to convert simplified forms of phrases into correct phrases in the nominal case. TermoPL accepts as input morphologically annotated and disambiguated domain texts and creates a list of terms, the top part of which comprises domain terminology. It can also compare two candidate term lists using three different coefficients showing asymmetry of term occurrences in this data. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1361/ |
| https://www.aclweb.org/anthology/L16-1361 | |
| PWC | https://paperswithcode.com/paper/termopl-a-flexible-tool-for-terminology |
| Repo | |
| Framework | |
Learning Transferrable Representations for Unsupervised Domain Adaptation
| Title | Learning Transferrable Representations for Unsupervised Domain Adaptation |
| Authors | Ozan Sener, Hyun Oh Song, Ashutosh Saxena, Silvio Savarese |
| Abstract | Supervised learning with large scale labelled datasets and deep layered models has caused a paradigm shift in diverse areas in learning and recognition. However, this approach still suffers from generalization issues under the presence of a domain shift between the training and the test data distribution. Since unsupervised domain adaptation algorithms directly address this domain shift problem between a labelled source dataset and an unlabelled target dataset, recent papers have shown promising results by fine-tuning the networks with domain adaptation loss functions which try to align the mismatch between the training and testing data distributions. Nevertheless, these recent deep learning based domain adaptation approaches still suffer from issues such as high sensitivity to the gradient reversal hyperparameters and overfitting during the fine-tuning stage. In this paper, we propose a unified deep learning framework where the representation, cross domain transformation, and target label inference are all jointly optimized in an end-to-end fashion for unsupervised domain adaptation. Our experiments show that the proposed method significantly outperforms state-of-the-art algorithms in both object recognition and digit classification experiments by a large margin. We will make our learned models as well as the source code available immediately upon acceptance. |
| Tasks | Domain Adaptation, Object Recognition, Unsupervised Domain Adaptation |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6360-learning-transferrable-representations-for-unsupervised-domain-adaptation |
| http://papers.nips.cc/paper/6360-learning-transferrable-representations-for-unsupervised-domain-adaptation.pdf | |
| PWC | https://paperswithcode.com/paper/learning-transferrable-representations-for |
| Repo | |
| Framework | |
Corpora for Learning the Mutual Relationship between Semantic Relatedness and Textual Entailment
| Title | Corpora for Learning the Mutual Relationship between Semantic Relatedness and Textual Entailment |
| Authors | Ngoc Phuoc An Vo, Octavian Popescu |
| Abstract | In this paper we present the creation of a corpora annotated with both semantic relatedness (SR) scores and textual entailment (TE) judgments. In building this corpus we aimed at discovering, if any, the relationship between these two tasks for the mutual benefit of resolving one of them by relying on the insights gained from the other. We considered a corpora already annotated with TE judgments and we proceed to the manual annotation with SR scores. The RTE 1-4 corpora used in the PASCAL competition fit our need. The annotators worked independently of one each other and they did not have access to the TE judgment during annotation. The intuition that the two annotations are correlated received major support from this experiment and this finding led to a system that uses this information to revise the initial estimates of SR scores. As semantic relatedness is one of the most general and difficult task in natural language processing we expect that future systems will combine different sources of information in order to solve it. Our work suggests that textual entailment plays a quantifiable role in addressing it. |
| Tasks | Natural Language Inference |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1539/ |
| https://www.aclweb.org/anthology/L16-1539 | |
| PWC | https://paperswithcode.com/paper/corpora-for-learning-the-mutual-relationship |
| Repo | |
| Framework | |
Syntax-based Multi-system Machine Translation
| Title | Syntax-based Multi-system Machine Translation |
| Authors | Mat{=\i}ss Rikters, Inguna Skadi{\c{n}}a |
| Abstract | This paper describes a hybrid machine translation system that explores a parser to acquire syntactic chunks of a source sentence, translates the chunks with multiple online machine translation (MT) system application program interfaces (APIs) and creates output by combining translated chunks to obtain the best possible translation. The selection of the best translation hypothesis is performed by calculating the perplexity for each translated chunk. The goal of this approach is to enhance the baseline multi-system hybrid translation (MHyT) system that uses only a language model to select best translation from translations obtained with different APIs and to improve overall English ― Latvian machine translation quality over each of the individual MT APIs. The presented syntax-based multi-system translation (SyMHyT) system demonstrates an improvement in terms of BLEU and NIST scores compared to the baseline system. Improvements reach from 1.74 up to 2.54 BLEU points. |
| Tasks | Language Modelling, Machine Translation |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1093/ |
| https://www.aclweb.org/anthology/L16-1093 | |
| PWC | https://paperswithcode.com/paper/syntax-based-multi-system-machine-translation |
| Repo | |
| Framework | |
Progressively Parsing Interactional Objects for Fine Grained Action Detection
| Title | Progressively Parsing Interactional Objects for Fine Grained Action Detection |
| Authors | Bingbing Ni, Xiaokang Yang, Shenghua Gao |
| Abstract | Fine grained video action analysis often requires reliable detection and tracking of various interacting objects and human body parts, denoted as interactional object parsing. However, most of the previous methods based on either independent or joint object detection might suffer from high model complexity and challenging image content, e.g., illumination/pose/appearance/scale variation, motion, occlusion etc. In this work, we propose an end-to-end system based on recursive neural network to perform frame by frame interactional object parsing, which can alleviate the difficulty through a incremental manner. Our key innovation is that: instead of jointly outputting all object detections at once, for each frame, we use a set of long-short term memory (LSTM) nodes to incrementally refine the detections. After passing each LSTM node, more object detections are consolidated and thus more contextual information could be utilized to determine more difficult object detections. Extensive experiments on two benchmark fine grained activity datasets demonstrate that our proposed algorithm achieves better interacting object detection performance, which in turn boosts the action recognition performance over the state-of-the-art. |
| Tasks | Action Detection, Fine-Grained Action Detection, Object Detection, Temporal Action Localization |
| Published | 2016-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2016/html/Ni_Progressively_Parsing_Interactional_CVPR_2016_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2016/papers/Ni_Progressively_Parsing_Interactional_CVPR_2016_paper.pdf | |
| PWC | https://paperswithcode.com/paper/progressively-parsing-interactional-objects |
| Repo | |
| Framework | |
Towards Time-Aware Knowledge Graph Completion
| Title | Towards Time-Aware Knowledge Graph Completion |
| Authors | Tingsong Jiang, Tianyu Liu, Tao Ge, Lei Sha, Baobao Chang, Sujian Li, Zhifang Sui |
| Abstract | Knowledge graph (KG) completion adds new facts to a KG by making inferences from existing facts. Most existing methods ignore the time information and only learn from time-unknown fact triples. In dynamic environments that evolve over time, it is important and challenging for knowledge graph completion models to take into account the temporal aspects of facts. In this paper, we present a novel time-aware knowledge graph completion model that is able to predict links in a KG using both the existing facts and the temporal information of the facts. To incorporate the happening time of facts, we propose a time-aware KG embedding model using temporal order information among facts. To incorporate the valid time of facts, we propose a joint time-aware inference model based on Integer Linear Programming (ILP) using temporal consistencyinformationasconstraints. Wefurtherintegratetwomodelstomakefulluseofglobal temporal information. We empirically evaluate our models on time-aware KG completion task. Experimental results show that our time-aware models achieve the state-of-the-art on temporal facts consistently. |
| Tasks | Knowledge Graph Completion, Knowledge Graphs, Question Answering, Relation Extraction |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1161/ |
| https://www.aclweb.org/anthology/C16-1161 | |
| PWC | https://paperswithcode.com/paper/towards-time-aware-knowledge-graph-completion |
| Repo | |
| Framework | |
Sentiment Analysis for Low Resource Languages: A Study on Informal Indonesian Tweets
| Title | Sentiment Analysis for Low Resource Languages: A Study on Informal Indonesian Tweets |
| Authors | Tuan Anh Le, David Moeljadi, Yasuhide Miura, Tomoko Ohkuma |
| Abstract | This paper describes our attempt to build a sentiment analysis system for Indonesian tweets. With this system, we can study and identify sentiments and opinions in a text or document computationally. We used four thousand manually labeled tweets collected in February and March 2016 to build the model. Because of the variety of content in tweets, we analyze tweets into eight groups in total, including pos(itive), neg(ative), and neu(tral). Finally, we obtained 73.2{%} accuracy with Long Short Term Memory (LSTM) without normalizer. |
| Tasks | Sentiment Analysis |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-5415/ |
| https://www.aclweb.org/anthology/W16-5415 | |
| PWC | https://paperswithcode.com/paper/sentiment-analysis-for-low-resource-languages |
| Repo | |
| Framework | |
Rule Extraction for Tree-to-Tree Transducers by Cost Minimization
| Title | Rule Extraction for Tree-to-Tree Transducers by Cost Minimization |
| Authors | Pascual Mart{'\i}nez-G{'o}mez, Yusuke Miyao |
| Abstract | |
| Tasks | Machine Translation, Natural Language Inference, Question Answering, Text Summarization |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1002/ |
| https://www.aclweb.org/anthology/D16-1002 | |
| PWC | https://paperswithcode.com/paper/rule-extraction-for-tree-to-tree-transducers |
| Repo | |
| Framework | |
Multiple In-text Reference Aggregation Phenomenon
| Title | Multiple In-text Reference Aggregation Phenomenon |
| Authors | Marc Bertin, Iana Atanassova |
| Abstract | |
| Tasks | Information Retrieval |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-1502/ |
| https://www.aclweb.org/anthology/W16-1502 | |
| PWC | https://paperswithcode.com/paper/multiple-in-text-reference-aggregation |
| Repo | |
| Framework | |
Exploring the Leading Authors and Journals in Major Topics by Citation Sentences and Topic Modeling
| Title | Exploring the Leading Authors and Journals in Major Topics by Citation Sentences and Topic Modeling |
| Authors | Ha Jin Kim, Juyoung An, Yoo Kyung Jeong, Min Song |
| Abstract | |
| Tasks | Information Retrieval |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-1506/ |
| https://www.aclweb.org/anthology/W16-1506 | |
| PWC | https://paperswithcode.com/paper/exploring-the-leading-authors-and-journals-in |
| Repo | |
| Framework | |
University of Houston at CL-SciSumm 2016: SVMs with tree kernels and Sentence Similarity
| Title | University of Houston at CL-SciSumm 2016: SVMs with tree kernels and Sentence Similarity |
| Authors | Luis Moraes, Shahryar Baki, Rakesh Verma, Daniel Lee |
| Abstract | |
| Tasks | Information Retrieval, Text Summarization |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-1513/ |
| https://www.aclweb.org/anthology/W16-1513 | |
| PWC | https://paperswithcode.com/paper/university-of-houston-at-cl-scisumm-2016-svms |
| Repo | |
| Framework | |
Interactive-Predictive Machine Translation based on Syntactic Constraints of Prefix
| Title | Interactive-Predictive Machine Translation based on Syntactic Constraints of Prefix |
| Authors | Na Ye, Guiping Zhang, Dongfeng Cai |
| Abstract | Interactive-predictive machine translation (IPMT) is a translation mode which combines machine translation technology and human behaviours. In the IPMT system, the utilization of the prefix greatly affects the interaction efficiency. However, state-of-the-art methods filter translation hypotheses mainly according to their matching results with the prefix on character level, and the advantage of the prefix is not fully developed. Focusing on this problem, this paper mines the deep constraints of prefix on syntactic level to improve the performance of IPMT systems. Two syntactic subtree matching rules based on phrase structure grammar are proposed to filter the translation hypotheses more strictly. Experimental results on LDC Chinese-English corpora show that the proposed method outperforms state-of-the-art phrase-based IPMT system while keeping comparable decoding speed. |
| Tasks | Machine Translation, Question Answering |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1169/ |
| https://www.aclweb.org/anthology/C16-1169 | |
| PWC | https://paperswithcode.com/paper/interactive-predictive-machine-translation |
| Repo | |
| Framework | |
Selective Annotation of Sentence Parts: Identification of Relevant Sub-sentential Units
| Title | Selective Annotation of Sentence Parts: Identification of Relevant Sub-sentential Units |
| Authors | Ge Xu, Xiaoyan Yang, Chu-Ren Huang |
| Abstract | Many NLP tasks involve sentence-level annotation yet the relevant information is not encoded at sentence level but at some relevant parts of the sentence. Such tasks include but are not limited to: sentiment expression annotation, product feature annotation, and template annotation for Q{&}A systems. However, annotation of the full corpus sentence by sentence is resource intensive. In this paper, we propose an approach that iteratively extracts frequent parts of sentences for annotating, and compresses the set of sentences after each round of annotation. Our approach can also be used in preparing training sentences for binary classification (domain-related vs. noise, subjectivity vs. objectivity, etc.), assuming that sentence-type annotation can be predicted by annotation of the most relevant sub-sentences. Two experiments are performed to test our proposal and evaluated in terms of time saved and agreement of annotation. |
| Tasks | Opinion Mining |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-5411/ |
| https://www.aclweb.org/anthology/W16-5411 | |
| PWC | https://paperswithcode.com/paper/selective-annotation-of-sentence-parts |
| Repo | |
| Framework | |
UAlacant word-level and phrase-level machine translation quality estimation systems at WMT 2016
| Title | UAlacant word-level and phrase-level machine translation quality estimation systems at WMT 2016 |
| Authors | Miquel Espl{`a}-Gomis, Felipe S{'a}nchez-Mart{'\i}nez, Mikel Forcada |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2383/ |
| https://www.aclweb.org/anthology/W16-2383 | |
| PWC | https://paperswithcode.com/paper/ualacant-word-level-and-phrase-level-machine |
| Repo | |
| Framework | |
