Paper Group NANR 13
Producing Unseen Morphological Variants in Statistical Machine Translation. FuRongWang at SemEval-2017 Task 3: Deep Neural Networks for Selecting Relevant Answers in Community Question Answering. Decoding with Value Networks for Neural Machine Translation. Improving Native Language Identification by Using Spelling Errors. Neural Automatic Post-Edit …
Producing Unseen Morphological Variants in Statistical Machine Translation
| Title | Producing Unseen Morphological Variants in Statistical Machine Translation |
| Authors | Matthias Huck, Ale{\v{s}} Tamchyna, Ond{\v{r}}ej Bojar, Alex Fraser, er |
| Abstract | Translating into morphologically rich languages is difficult. Although the coverage of lemmas may be reasonable, many morphological variants cannot be learned from the training data. We present a statistical translation system that is able to produce these inflected word forms. Different from most previous work, we do not separate morphological prediction from lexical choice into two consecutive steps. Our approach is novel in that it is integrated in decoding and takes advantage of context information from both the source language and the target language sides. |
| Tasks | Machine Translation |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2059/ |
| https://www.aclweb.org/anthology/E17-2059 | |
| PWC | https://paperswithcode.com/paper/producing-unseen-morphological-variants-in |
| Repo | |
| Framework | |
FuRongWang at SemEval-2017 Task 3: Deep Neural Networks for Selecting Relevant Answers in Community Question Answering
| Title | FuRongWang at SemEval-2017 Task 3: Deep Neural Networks for Selecting Relevant Answers in Community Question Answering |
| Authors | Sheng Zhang, Jiajun Cheng, Hui Wang, Xin Zhang, Pei Li, Zhaoyun Ding |
| Abstract | We describes deep neural networks frameworks in this paper to address the community question answering (cQA) ranking task (SemEval-2017 task 3). Convolutional neural networks and bi-directional long-short term memory networks are applied in our methods to extract semantic information from questions and answers (comments). In addition, in order to take the full advantage of question-comment semantic relevance, we deploy interaction layer and augmented features before calculating the similarity. The results show that our methods have the great effectiveness for both subtask A and subtask C. |
| Tasks | Answer Selection, Community Question Answering, Question Answering |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2052/ |
| https://www.aclweb.org/anthology/S17-2052 | |
| PWC | https://paperswithcode.com/paper/furongwang-at-semeval-2017-task-3-deep-neural |
| Repo | |
| Framework | |
Decoding with Value Networks for Neural Machine Translation
| Title | Decoding with Value Networks for Neural Machine Translation |
| Authors | Di He, Hanqing Lu, Yingce Xia, Tao Qin, Liwei Wang, Tie-Yan Liu |
| Abstract | Neural Machine Translation (NMT) has become a popular technology in recent years, and beam search is its de facto decoding method due to the shrunk search space and reduced computational complexity. However, since it only searches for local optima at each time step through one-step forward looking, it usually cannot output the best target sentence. Inspired by the success and methodology of AlphaGo, in this paper we propose using a prediction network to improve beam search, which takes the source sentence $x$, the currently available decoding output $y_1,\cdots, y_{t-1}$ and a candidate word $w$ at step $t$ as inputs and predicts the long-term value (e.g., BLEU score) of the partial target sentence if it is completed by the NMT model. Following the practice in reinforcement learning, we call this prediction network \emph{value network}. Specifically, we propose a recurrent structure for the value network, and train its parameters from bilingual data. During the test time, when choosing a word $w$ for decoding, we consider both its conditional probability given by the NMT model and its long-term value predicted by the value network. Experiments show that such an approach can significantly improve the translation accuracy on several translation tasks. |
| Tasks | Machine Translation |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6622-decoding-with-value-networks-for-neural-machine-translation |
| http://papers.nips.cc/paper/6622-decoding-with-value-networks-for-neural-machine-translation.pdf | |
| PWC | https://paperswithcode.com/paper/decoding-with-value-networks-for-neural |
| Repo | |
| Framework | |
Improving Native Language Identification by Using Spelling Errors
| Title | Improving Native Language Identification by Using Spelling Errors |
| Authors | Lingzhen Chen, Carlo Strapparava, Vivi Nastase |
| Abstract | In this paper, we explore spelling errors as a source of information for detecting the native language of a writer, a previously under-explored area. We note that character n-grams from misspelled words are very indicative of the native language of the author. In combination with other lexical features, spelling error features lead to 1.2{%} improvement in accuracy on classifying texts in the TOEFL11 corpus by the author{'}s native language, compared to systems participating in the NLI shared task. |
| Tasks | Language Identification, Native Language Identification |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-2086/ |
| https://www.aclweb.org/anthology/P17-2086 | |
| PWC | https://paperswithcode.com/paper/improving-native-language-identification-by |
| Repo | |
| Framework | |
Neural Automatic Post-Editing Using Prior Alignment and Reranking
| Title | Neural Automatic Post-Editing Using Prior Alignment and Reranking |
| Authors | Santanu Pal, Sudip Kumar Naskar, Mihaela Vela, Qun Liu, Josef van Genabith |
| Abstract | We present a second-stage machine translation (MT) system based on a neural machine translation (NMT) approach to automatic post-editing (APE) that improves the translation quality provided by a first-stage MT system. Our APE system (APE{_}Sym) is an extended version of an attention based NMT model with bilingual symmetry employing bidirectional models, mt{–}pe and pe{–}mt. APE translations produced by our system show statistically significant improvements over the first-stage MT, phrase-based APE and the best reported score on the WMT 2016 APE dataset by a previous neural APE system. Re-ranking (APE{_}Rerank) of the n-best translations from the phrase-based APE and APE{_}Sym systems provides further substantial improvements over the symmetric neural APE model. Human evaluation confirms that the APE{_}Rerank generated PE translations improve on the previous best neural APE system at WMT 2016. |
| Tasks | Automatic Post-Editing, Machine Translation |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2056/ |
| https://www.aclweb.org/anthology/E17-2056 | |
| PWC | https://paperswithcode.com/paper/neural-automatic-post-editing-using-prior |
| Repo | |
| Framework | |
Group Sparse Additive Machine
| Title | Group Sparse Additive Machine |
| Authors | Hong Chen, Xiaoqian Wang, Cheng Deng, Heng Huang |
| Abstract | A family of learning algorithms generated from additive models have attracted much attention recently for their flexibility and interpretability in high dimensional data analysis. Among them, learning models with grouped variables have shown competitive performance for prediction and variable selection. However, the previous works mainly focus on the least squares regression problem, not the classification task. Thus, it is desired to design the new additive classification model with variable selection capability for many real-world applications which focus on high-dimensional data classification. To address this challenging problem, in this paper, we investigate the classification with group sparse additive models in reproducing kernel Hilbert spaces. A novel classification method, called as \emph{group sparse additive machine} (GroupSAM), is proposed to explore and utilize the structure information among the input variables. Generalization error bound is derived and proved by integrating the sample error analysis with empirical covering numbers and the hypothesis error estimate with the stepping stone technique. Our new bound shows that GroupSAM can achieve a satisfactory learning rate with polynomial decay. Experimental results on synthetic data and seven benchmark datasets consistently show the effectiveness of our new approach. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6624-group-sparse-additive-machine |
| http://papers.nips.cc/paper/6624-group-sparse-additive-machine.pdf | |
| PWC | https://paperswithcode.com/paper/group-sparse-additive-machine |
| Repo | |
| Framework | |
Lump at SemEval-2017 Task 1: Towards an Interlingua Semantic Similarity
| Title | Lump at SemEval-2017 Task 1: Towards an Interlingua Semantic Similarity |
| Authors | Cristina Espa{~n}a-Bonet, Alberto Barr{'o}n-Cede{~n}o |
| Abstract | This is the Lump team participation at SemEval 2017 Task 1 on Semantic Textual Similarity. Our supervised model relies on features which are multilingual or interlingual in nature. We include lexical similarities, cross-language explicit semantic analysis, internal representations of multilingual neural networks and interlingual word embeddings. Our representations allow to use large datasets in language pairs with many instances to better classify instances in smaller language pairs avoiding the necessity of translating into a single language. Hence we can deal with all the languages in the task: Arabic, English, Spanish, and Turkish. |
| Tasks | Language Identification, Machine Translation, Semantic Similarity, Semantic Textual Similarity, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2019/ |
| https://www.aclweb.org/anthology/S17-2019 | |
| PWC | https://paperswithcode.com/paper/lump-at-semeval-2017-task-1-towards-an |
| Repo | |
| Framework | |
Joint Embeddings of Chinese Words, Characters, and Fine-grained Subcharacter Components
| Title | Joint Embeddings of Chinese Words, Characters, and Fine-grained Subcharacter Components |
| Authors | Jinxing Yu, Xun Jian, Hao Xin, Yangqiu Song |
| Abstract | Word embeddings have attracted much attention recently. Different from alphabetic writing systems, Chinese characters are often composed of subcharacter components which are also semantically informative. In this work, we propose an approach to jointly embed Chinese words as well as their characters and fine-grained subcharacter components. We use three likelihoods to evaluate whether the context words, characters, and components can predict the current target word, and collected 13,253 subcharacter components to demonstrate the existing approaches of decomposing Chinese characters are not enough. Evaluation on both word similarity and word analogy tasks demonstrates the superior performance of our model. |
| Tasks | Named Entity Recognition, Question Answering, Sentiment Analysis, Text Classification, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1027/ |
| https://www.aclweb.org/anthology/D17-1027 | |
| PWC | https://paperswithcode.com/paper/joint-embeddings-of-chinese-words-characters |
| Repo | |
| Framework | |
Abstractive Multi-document Summarization by Partial Tree Extraction, Recombination and Linearization
| Title | Abstractive Multi-document Summarization by Partial Tree Extraction, Recombination and Linearization |
| Authors | Litton J Kurisinkel, Yue Zhang, Vasudeva Varma |
| Abstract | Existing work for abstractive multidocument summarization utilise existing phrase structures directly extracted from input documents to generate summary sentences. These methods can suffer from lack of consistence and coherence in merging phrases. We introduce a novel approach for abstractive multidocument summarization through partial dependency tree extraction, recombination and linearization. The method entrusts the summarizer to generate its own topically coherent sequential structures from scratch for effective communication. Results on TAC 2011, DUC-2004 and 2005 show that our system gives competitive results compared with state of the art abstractive summarization approaches in the literature. We also achieve competitive results in linguistic quality assessed by human evaluators. |
| Tasks | Abstractive Text Summarization, Document Summarization, Multi-Document Summarization |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-1082/ |
| https://www.aclweb.org/anthology/I17-1082 | |
| PWC | https://paperswithcode.com/paper/abstractive-multi-document-summarization-by |
| Repo | |
| Framework | |
Incremental Knowledge Acquisition Approach for Information Extraction on both Semi-Structured and Unstructured Text from the Open Domain Web
| Title | Incremental Knowledge Acquisition Approach for Information Extraction on both Semi-Structured and Unstructured Text from the Open Domain Web |
| Authors | Maria Myung Hee Kim |
| Abstract | |
| Tasks | Open Information Extraction |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/U17-1010/ |
| https://www.aclweb.org/anthology/U17-1010 | |
| PWC | https://paperswithcode.com/paper/incremental-knowledge-acquisition-approach |
| Repo | |
| Framework | |
Measuring the Italian-English lexical gap for action verbs and its impact on translation
| Title | Measuring the Italian-English lexical gap for action verbs and its impact on translation |
| Authors | Lorenzo Gregori, Aless Panunzi, ro |
| Abstract | This paper describes a method to measure the lexical gap of action verbs in Italian and English by using the IMAGACT ontology of action. The fine-grained categorization of action concepts of the data source allowed to have wide overview of the relation between concepts in the two languages. The calculated lexical gap for both English and Italian is about 30{%} of the action concepts, much higher than previous results. Beyond this general numbers a deeper analysis has been performed in order to evaluate the impact that lexical gaps can have on translation. In particular a distinction has been made between the cases in which the presence of a lexical gap affects translation correctness and completeness at a semantic level. The results highlight a high percentage of concepts that can be considered hard to translate (about 18{%} from English to Italian and 20{%} from Italian to English) and confirms that action verbs are a critical lexical class for translation tasks. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1913/ |
| https://www.aclweb.org/anthology/W17-1913 | |
| PWC | https://paperswithcode.com/paper/measuring-the-italian-english-lexical-gap-for |
| Repo | |
| Framework | |
Permutation-based Causal Inference Algorithms with Interventions
| Title | Permutation-based Causal Inference Algorithms with Interventions |
| Authors | Yuhao Wang, Liam Solus, Karren Yang, Caroline Uhler |
| Abstract | Learning directed acyclic graphs using both observational and interventional data is now a fundamentally important problem due to recent technological developments in genomics that generate such single-cell gene expression data at a very large scale. In order to utilize this data for learning gene regulatory networks, efficient and reliable causal inference algorithms are needed that can make use of both observational and interventional data. In this paper, we present two algorithms of this type and prove that both are consistent under the faithfulness assumption. These algorithms are interventional adaptations of the Greedy SP algorithm and are the first algorithms using both observational and interventional data with consistency guarantees. Moreover, these algorithms have the advantage that they are nonparametric, which makes them useful also for analyzing non-Gaussian data. In this paper, we present these two algorithms and their consistency guarantees, and we analyze their performance on simulated data, protein signaling data, and single-cell gene expression data. |
| Tasks | Causal Inference |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7164-permutation-based-causal-inference-algorithms-with-interventions |
| http://papers.nips.cc/paper/7164-permutation-based-causal-inference-algorithms-with-interventions.pdf | |
| PWC | https://paperswithcode.com/paper/permutation-based-causal-inference-algorithms |
| Repo | |
| Framework | |
Investigating neural architectures for short answer scoring
| Title | Investigating neural architectures for short answer scoring |
| Authors | Brian Riordan, Andrea Horbach, Aoife Cahill, Torsten Zesch, Chong Min Lee |
| Abstract | Neural approaches to automated essay scoring have recently shown state-of-the-art performance. The automated essay scoring task typically involves a broad notion of writing quality that encompasses content, grammar, organization, and conventions. This differs from the short answer content scoring task, which focuses on content accuracy. The inputs to neural essay scoring models {–} ngrams and embeddings {–} are arguably well-suited to evaluate content in short answer scoring tasks. We investigate how several basic neural approaches similar to those used for automated essay scoring perform on short answer scoring. We show that neural architectures can outperform a strong non-neural baseline, but performance and optimal parameter settings vary across the more diverse types of prompts typical of short answer scoring. |
| Tasks | Reading Comprehension, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5017/ |
| https://www.aclweb.org/anthology/W17-5017 | |
| PWC | https://paperswithcode.com/paper/investigating-neural-architectures-for-short |
| Repo | |
| Framework | |
funSentiment at SemEval-2017 Task 4: Topic-Based Message Sentiment Classification by Exploiting Word Embeddings, Text Features and Target Contexts
| Title | funSentiment at SemEval-2017 Task 4: Topic-Based Message Sentiment Classification by Exploiting Word Embeddings, Text Features and Target Contexts |
| Authors | Quanzhi Li, Armineh Nourbakhsh, Xiaomo Liu, Rui Fang, Sameena Shah |
| Abstract | This paper describes the approach we used for SemEval-2017 Task 4: Sentiment Analysis in Twitter. Topic-based (target-dependent) sentiment analysis has become attractive and been used in some applications recently, but it is still a challenging research task. In our approach, we take the left and right context of a target into consideration when generating polarity classification features. We use two types of word embeddings in our classifiers: the general word embeddings learned from 200 million tweets, and sentiment-specific word embeddings learned from 10 million tweets using distance supervision. We also incorporate a text feature model in our algorithm. This model produces features based on text negation, tf.idf weighting scheme, and a Rocchio text classification method. We participated in four subtasks (B, C, D {&} E for English), all of which are about topic-based message polarity classification. Our team is ranked {#}6 in subtask B, {#}3 by MAEu and {#}9 by MAEm in subtask C, {#}3 using RAE and {#}6 using KLD in subtask D, and {#}3 in subtask E. |
| Tasks | Sentiment Analysis, Text Classification, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2125/ |
| https://www.aclweb.org/anthology/S17-2125 | |
| PWC | https://paperswithcode.com/paper/funsentiment-at-semeval-2017-task-4-topic |
| Repo | |
| Framework | |
Lexicalization, Separation and transitivity: A comparative study of Mandarin VO compound Variations
| Title | Lexicalization, Separation and transitivity: A comparative study of Mandarin VO compound Variations |
| Authors | Menghan Jiang, Chu-Ren Huang |
| Abstract | |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/Y17-1047/ |
| https://www.aclweb.org/anthology/Y17-1047 | |
| PWC | https://paperswithcode.com/paper/lexicalization-separation-and-transitivity-a |
| Repo | |
| Framework | |
