Paper Group NANR 47
Supersense Tagging with a Combination of Character, Subword, and Word-level Representations. HistoBankVis: Detecting Language Change via Data Visualization. Improving Word Sense Disambiguation in Neural Machine Translation with Sense Embeddings. UDLex: Towards Cross-language Subcategorization Lexicons. Learning an Input Filter for Argument Structur …
Supersense Tagging with a Combination of Character, Subword, and Word-level Representations
| Title | Supersense Tagging with a Combination of Character, Subword, and Word-level Representations |
| Authors | Youhyun Shin, Sang-goo Lee |
| Abstract | Recently, there has been increased interest in utilizing characters or subwords for natural language processing (NLP) tasks. However, the effect of utilizing character, subword, and word-level information simultaneously has not been examined so far. In this paper, we propose a model to leverage various levels of input features to improve on the performance of an supersense tagging task. Detailed analysis of experimental results show that different levels of input representation offer distinct characteristics that explain performance discrepancy among different tasks. |
| Tasks | Entity Alignment, Language Modelling, Machine Translation, Named Entity Recognition, Word Sense Disambiguation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4106/ |
| https://www.aclweb.org/anthology/W17-4106 | |
| PWC | https://paperswithcode.com/paper/supersense-tagging-with-a-combination-of |
| Repo | |
| Framework | |
HistoBankVis: Detecting Language Change via Data Visualization
| Title | HistoBankVis: Detecting Language Change via Data Visualization |
| Authors | Christin Sch{"a}tzle, Michael Hund, Frederik Dennig, Miriam Butt, Daniel Keim |
| Abstract | |
| Tasks | |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0507/ |
| https://www.aclweb.org/anthology/W17-0507 | |
| PWC | https://paperswithcode.com/paper/histobankvis-detecting-language-change-via |
| Repo | |
| Framework | |
Improving Word Sense Disambiguation in Neural Machine Translation with Sense Embeddings
| Title | Improving Word Sense Disambiguation in Neural Machine Translation with Sense Embeddings |
| Authors | Annette Rios Gonzales, Laura Mascarell, Rico Sennrich |
| Abstract | |
| Tasks | Machine Translation, Word Sense Disambiguation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4702/ |
| https://www.aclweb.org/anthology/W17-4702 | |
| PWC | https://paperswithcode.com/paper/improving-word-sense-disambiguation-in-neural |
| Repo | |
| Framework | |
UDLex: Towards Cross-language Subcategorization Lexicons
| Title | UDLex: Towards Cross-language Subcategorization Lexicons |
| Authors | Giulia Rambelli, Aless Lenci, ro, Thierry Poibeau |
| Abstract | |
| Tasks | Information Retrieval, Machine Translation, Natural Language Inference, Word Sense Disambiguation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6524/ |
| https://www.aclweb.org/anthology/W17-6524 | |
| PWC | https://paperswithcode.com/paper/udlex-towards-cross-language |
| Repo | |
| Framework | |
Learning an Input Filter for Argument Structure Acquisition
| Title | Learning an Input Filter for Argument Structure Acquisition |
| Authors | Laurel Perkins, Naomi Feldman, Jeffrey Lidz |
| Abstract | How do children learn a verb{'}s argument structure when their input contains nonbasic clauses that obscure verb transitivity? Here we present a new model that infers verb transitivity by learning to filter out non-basic clauses that were likely parsed in error. In simulations with child-directed speech, we show that this model accurately categorizes the majority of 50 frequent transitive, intransitive and alternating verbs, and jointly learns appropriate parameters for filtering parsing errors. Our model is thus able to filter out problematic data for verb learning without knowing in advance which data need to be filtered. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-0702/ |
| https://www.aclweb.org/anthology/W17-0702 | |
| PWC | https://paperswithcode.com/paper/learning-an-input-filter-for-argument |
| Repo | |
| Framework | |
Oxford at SemEval-2017 Task 9: Neural AMR Parsing with Pointer-Augmented Attention
| Title | Oxford at SemEval-2017 Task 9: Neural AMR Parsing with Pointer-Augmented Attention |
| Authors | Jan Buys, Phil Blunsom |
| Abstract | We present a neural encoder-decoder AMR parser that extends an attention-based model by predicting the alignment between graph nodes and sentence tokens explicitly with a pointer mechanism. Candidate lemmas are predicted as a pre-processing step so that the lemmas of lexical concepts, as well as constant strings, are factored out of the graph linearization and recovered through the predicted alignments. The approach does not rely on syntactic parses or extensive external resources. Our parser obtained 59{%} Smatch on the SemEval test set. |
| Tasks | Amr Parsing, Lemmatization |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2157/ |
| https://www.aclweb.org/anthology/S17-2157 | |
| PWC | https://paperswithcode.com/paper/oxford-at-semeval-2017-task-9-neural-amr |
| Repo | |
| Framework | |
A Sharp Error Analysis for the Fused Lasso, with Application to Approximate Changepoint Screening
| Title | A Sharp Error Analysis for the Fused Lasso, with Application to Approximate Changepoint Screening |
| Authors | Kevin Lin, James L. Sharpnack, Alessandro Rinaldo, Ryan J. Tibshirani |
| Abstract | In the 1-dimensional multiple changepoint detection problem, we derive a new fast error rate for the fused lasso estimator, under the assumption that the mean vector has a sparse number of changepoints. This rate is seen to be suboptimal (compared to the minimax rate) by only a factor of $\log\log{n}$. Our proof technique is centered around a novel construction that we call a lower interpolant. We extend our results to misspecified models and exponential family distributions. We also describe the implications of our error analysis for the approximate screening of changepoints. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7264-a-sharp-error-analysis-for-the-fused-lasso-with-application-to-approximate-changepoint-screening |
| http://papers.nips.cc/paper/7264-a-sharp-error-analysis-for-the-fused-lasso-with-application-to-approximate-changepoint-screening.pdf | |
| PWC | https://paperswithcode.com/paper/a-sharp-error-analysis-for-the-fused-lasso |
| Repo | |
| Framework | |
A Short Survey on Taxonomy Learning from Text Corpora: Issues, Resources and Recent Advances
| Title | A Short Survey on Taxonomy Learning from Text Corpora: Issues, Resources and Recent Advances |
| Authors | Chengyu Wang, Xiaofeng He, Aoying Zhou |
| Abstract | A taxonomy is a semantic hierarchy, consisting of concepts linked by is-a relations. While a large number of taxonomies have been constructed from human-compiled resources (e.g., Wikipedia), learning taxonomies from text corpora has received a growing interest and is essential for long-tailed and domain-specific knowledge acquisition. In this paper, we overview recent advances on taxonomy construction from free texts, reorganizing relevant subtasks into a complete framework. We also overview resources for evaluation and discuss challenges for future research. |
| Tasks | Question Answering |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1123/ |
| https://www.aclweb.org/anthology/D17-1123 | |
| PWC | https://paperswithcode.com/paper/a-short-survey-on-taxonomy-learning-from-text |
| Repo | |
| Framework | |
Annotating Speech, Attitude and Perception Reports
| Title | Annotating Speech, Attitude and Perception Reports |
| Authors | Corien Bary, Leopold Hess, Kees Thijs, Peter Berck, Iris Hendrickx |
| Abstract | We present REPORTS, an annotation scheme for the annotation of speech, attitude and perception reports. Such a scheme makes it possible to annotate the various text elements involved in such reports (e.g. embedding entity, complement, complement head) and their relations in a uniform way, which in turn facilitates the automatic extraction of information on, for example, complementation and vocabulary distribution. We also present the Ancient Greek corpus RAG (Thucydides{'} History of the Peloponnesian War), to which we have applied this scheme using the annotation tool BRAT. We discuss some of the issues, both theoretical and practical, that we encountered, show how the corpus helps in answering specific questions, and conclude that REPORTS fitted in well with our needs. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-0806/ |
| https://www.aclweb.org/anthology/W17-0806 | |
| PWC | https://paperswithcode.com/paper/annotating-speech-attitude-and-perception |
| Repo | |
| Framework | |
Swedish Prepositions are not Pure Function Words
| Title | Swedish Prepositions are not Pure Function Words |
| Authors | Lars Ahrenberg |
| Abstract | |
| Tasks | |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0402/ |
| https://www.aclweb.org/anthology/W17-0402 | |
| PWC | https://paperswithcode.com/paper/swedish-prepositions-are-not-pure-function |
| Repo | |
| Framework | |
Can Syntax Help? Improving an LSTM-based Sentence Compression Model for New Domains
| Title | Can Syntax Help? Improving an LSTM-based Sentence Compression Model for New Domains |
| Authors | Liangguo Wang, Jing Jiang, Hai Leong Chieu, Chen Hui Ong, D Song, an, Lejian Liao |
| Abstract | In this paper, we study how to improve the domain adaptability of a deletion-based Long Short-Term Memory (LSTM) neural network model for sentence compression. We hypothesize that syntactic information helps in making such models more robust across domains. We propose two major changes to the model: using explicit syntactic features and introducing syntactic constraints through Integer Linear Programming (ILP). Our evaluation shows that the proposed model works better than the original model as well as a traditional non-neural-network-based model in a cross-domain setting. |
| Tasks | Sentence Compression, Text Summarization, Tokenization |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1127/ |
| https://www.aclweb.org/anthology/P17-1127 | |
| PWC | https://paperswithcode.com/paper/can-syntax-help-improving-an-lstm-based |
| Repo | |
| Framework | |
Word Similarity Datasets for Indian Languages: Annotation and Baseline Systems
| Title | Word Similarity Datasets for Indian Languages: Annotation and Baseline Systems |
| Authors | Syed Sarfaraz Akhtar, Arihant Gupta, Avijit Vajpayee, Arjit Srivastava, Manish Shrivastava |
| Abstract | With the advent of word representations, word similarity tasks are becoming increasing popular as an evaluation metric for the quality of the representations. In this paper, we present manually annotated monolingual word similarity datasets of six Indian languages - Urdu, Telugu, Marathi, Punjabi, Tamil and Gujarati. These languages are most spoken Indian languages worldwide after Hindi and Bengali. For the construction of these datasets, our approach relies on translation and re-annotation of word similarity datasets of English. We also present baseline scores for word representation models using state-of-the-art techniques for Urdu, Telugu and Marathi by evaluating them on newly created word similarity datasets. |
| Tasks | Dependency Parsing, Machine Translation, Named Entity Recognition, Question Answering, Semantic Textual Similarity, Word Sense Disambiguation |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-0811/ |
| https://www.aclweb.org/anthology/W17-0811 | |
| PWC | https://paperswithcode.com/paper/word-similarity-datasets-for-indian-languages |
| Repo | |
| Framework | |
Spatial-Semantic Image Search by Visual Feature Synthesis
| Title | Spatial-Semantic Image Search by Visual Feature Synthesis |
| Authors | Long Mai, Hailin Jin, Zhe Lin, Chen Fang, Jonathan Brandt, Feng Liu |
| Abstract | The performance of image retrieval has been improved tremendously in recent years through the use of deep feature representations. Most existing methods, however, aim to retrieve images that are visually similar or semantically relevant to the query, irrespective of spatial configuration. In this paper, we develop a spatial-semantic image search technology that enables users to search for images with both semantic and spatial constraints by manipulating concept text-boxes on a 2D query canvas. We train a convolutional neural network to synthesize appropriate visual features that captures the spatial-semantic constraints from the user canvas query. We directly optimize the retrieval performance of the visual features when training our deep neural network. These visual features then are used to retrieve images that are both spatially and semantically relevant to the user query. The experiments on large-scale datasets such as MS-COCO and Visual Genome show that our method outperforms other baseline and state-of-the-art methods in spatial-semantic image search. |
| Tasks | Image Retrieval |
| Published | 2017-07-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2017/html/Mai_Spatial-Semantic_Image_Search_CVPR_2017_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2017/papers/Mai_Spatial-Semantic_Image_Search_CVPR_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/spatial-semantic-image-search-by-visual |
| Repo | |
| Framework | |
When Conditional Logic met Connexive Logic
| Title | When Conditional Logic met Connexive Logic |
| Authors | Mathieu Vidal |
| Abstract | |
| Tasks | |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-6816/ |
| https://www.aclweb.org/anthology/W17-6816 | |
| PWC | https://paperswithcode.com/paper/when-conditional-logic-met-connexive-logic |
| Repo | |
| Framework | |
Earth Mover’s Distance Minimization for Unsupervised Bilingual Lexicon Induction
| Title | Earth Mover’s Distance Minimization for Unsupervised Bilingual Lexicon Induction |
| Authors | Meng Zhang, Yang Liu, Huanbo Luan, Maosong Sun |
| Abstract | Cross-lingual natural language processing hinges on the premise that there exists invariance across languages. At the word level, researchers have identified such invariance in the word embedding semantic spaces of different languages. However, in order to connect the separate spaces, cross-lingual supervision encoded in parallel data is typically required. In this paper, we attempt to establish the cross-lingual connection without relying on any cross-lingual supervision. By viewing word embedding spaces as distributions, we propose to minimize their earth mover{'}s distance, a measure of divergence between distributions. We demonstrate the success on the unsupervised bilingual lexicon induction task. In addition, we reveal an interesting finding that the earth mover{'}s distance shows potential as a measure of language difference. |
| Tasks | Cross-Lingual Transfer, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1207/ |
| https://www.aclweb.org/anthology/D17-1207 | |
| PWC | https://paperswithcode.com/paper/earth-movers-distance-minimization-for |
| Repo | |
| Framework | |
