Paper Group NAWR 8
Modeling topic dependencies in semantically coherent text spans with copulas. CATENA: CAusal and TEmporal relation extraction from NAtural language texts. Syntactic realization with data-driven neural tree grammars. Weighted Neural Bag-of-n-grams Model: New Baselines for Text Classification. MDSWriter: Annotation Tool for Creating High-Quality Mult …
Modeling topic dependencies in semantically coherent text spans with copulas
| Title | Modeling topic dependencies in semantically coherent text spans with copulas |
| Authors | Georgios Balikas, Hesam Amoualian, Marianne Clausel, Eric Gaussier, Massih R. Amini |
| Abstract | The exchangeability assumption in topic models like Latent Dirichlet Allocation (LDA) often results in inferring inconsistent topics for the words of text spans like noun-phrases, which are usually expected to be topically coherent. We propose copulaLDA, that extends LDA by integrating part of the text structure to the model and relaxes the conditional independence assumption between the word-specific latent topics given the per-document topic distributions. To this end, we assume that the words of text spans like noun-phrases are topically bound and we model this dependence with copulas. We demonstrate empirically the effectiveness of copulaLDA on both intrinsic and extrinsic evaluation tasks on several publicly available corpora. |
| Tasks | Topic Models |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1166/ |
| https://www.aclweb.org/anthology/C16-1166 | |
| PWC | https://paperswithcode.com/paper/modeling-topic-dependencies-in-semantically |
| Repo | https://github.com/balikasg/topicModelling |
| Framework | none |
CATENA: CAusal and TEmporal relation extraction from NAtural language texts
| Title | CATENA: CAusal and TEmporal relation extraction from NAtural language texts |
| Authors | Paramita Mirza, Sara Tonelli |
| Abstract | We present CATENA, a sieve-based system to perform temporal and causal relation extraction and classification from English texts, exploiting the interaction between the temporal and the causal model. We evaluate the performance of each sieve, showing that the rule-based, the machine-learned and the reasoning components all contribute to achieving state-of-the-art performance on TempEval-3 and TimeBank-Dense data. Although causal relations are much sparser than temporal ones, the architecture and the selected features are mostly suitable to serve both tasks. The effects of the interaction between the temporal and the causal components, although limited, yield promising results and confirm the tight connection between the temporal and the causal dimension of texts. |
| Tasks | Question Answering, Relation Classification, Relation Extraction, Temporal Information Extraction |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1007/ |
| https://www.aclweb.org/anthology/C16-1007 | |
| PWC | https://paperswithcode.com/paper/catena-causal-and-temporal-relation |
| Repo | https://github.com/paramitamirza/CATENA |
| Framework | none |
Syntactic realization with data-driven neural tree grammars
| Title | Syntactic realization with data-driven neural tree grammars |
| Authors | Brian McMahan, Matthew Stone |
| Abstract | A key component in surface realization in natural language generation is to choose concrete syntactic relationships to express a target meaning. We develop a new method for syntactic choice based on learning a stochastic tree grammar in a neural architecture. This framework can exploit state-of-the-art methods for modeling word sequences and generalizing across vocabulary. We also induce embeddings to generalize over elementary tree structures and exploit a tree recurrence over the input structure to model long-distance influences between NLG choices. We evaluate the models on the task of linearizing unannotated dependency trees, documenting the contribution of our modeling techniques to improvements in both accuracy and run time. |
| Tasks | Language Modelling, Text Generation |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1022/ |
| https://www.aclweb.org/anthology/C16-1022 | |
| PWC | https://paperswithcode.com/paper/syntactic-realization-with-data-driven-neural |
| Repo | https://github.com/braingineer/neural_tree_grammar |
| Framework | none |
Weighted Neural Bag-of-n-grams Model: New Baselines for Text Classification
| Title | Weighted Neural Bag-of-n-grams Model: New Baselines for Text Classification |
| Authors | Bofang Li, Zhe Zhao, Tao Liu, Puwei Wang, Xiaoyong Du |
| Abstract | NBSVM is one of the most popular methods for text classification and has been widely used as baselines for various text representation approaches. It uses Naive Bayes (NB) feature to weight sparse bag-of-n-grams representation. N-gram captures word order in short context and NB feature assigns more weights to those important words. However, NBSVM suffers from sparsity problem and is reported to be exceeded by newly proposed distributed (dense) text representations learned by neural networks. In this paper, we transfer the n-grams and NB weighting to neural models. We train n-gram embeddings and use NB weighting to guide the neural models to focus on important words. In fact, our methods can be viewed as distributed (dense) counterparts of sparse bag-of-n-grams in NBSVM. We discover that n-grams and NB weighting are also effective in distributed representations. As a result, our models achieve new strong baselines on 9 text classification datasets, e.g. on IMDB dataset, we reach performance of 93.5{%} accuracy, which exceeds previous state-of-the-art results obtained by deep neural models. All source codes are publicly available at \url{https://github.com/zhezhaoa/neural_BOW_toolkit}. |
| Tasks | Text Classification, Word Embeddings |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1150/ |
| https://www.aclweb.org/anthology/C16-1150 | |
| PWC | https://paperswithcode.com/paper/weighted-neural-bag-of-n-grams-model-new |
| Repo | https://github.com/zhezhaoa/neural_BOW_toolkit |
| Framework | none |
MDSWriter: Annotation Tool for Creating High-Quality Multi-Document Summarization Corpora
| Title | MDSWriter: Annotation Tool for Creating High-Quality Multi-Document Summarization Corpora |
| Authors | Christian M. Meyer, Darina Benikova, Margot Mieskes, Iryna Gurevych |
| Abstract | |
| Tasks | Document Summarization, Multi-Document Summarization |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-4017/ |
| https://www.aclweb.org/anthology/P16-4017 | |
| PWC | https://paperswithcode.com/paper/mdswriter-annotation-tool-for-creating-high |
| Repo | https://github.com/UKPLab/mdswriter |
| Framework | none |
On the Impact of Seed Words on Sentiment Polarity Lexicon Induction
| Title | On the Impact of Seed Words on Sentiment Polarity Lexicon Induction |
| Authors | Dame Jovanoski, Veno Pachovski, Preslav Nakov |
| Abstract | Sentiment polarity lexicons are key resources for sentiment analysis, and researchers have invested a lot of efforts in their manual creation. However, there has been a recent shift towards automatically extracted lexicons, which are orders of magnitude larger and perform much better. These lexicons are typically mined using bootstrapping, starting from very few seed words whose polarity is given, e.g., 50-60 words, and sometimes even just 5-6. Here we demonstrate that much higher-quality lexicons can be built by starting with hundreds of words and phrases as seeds, especially when they are in-domain. Thus, we combine (i) mid-sized high-quality manually crafted lexicons as seeds and (ii) bootstrapping, in order to build large-scale lexicons. |
| Tasks | Sentiment Analysis, Text Classification |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1147/ |
| https://www.aclweb.org/anthology/C16-1147 | |
| PWC | https://paperswithcode.com/paper/on-the-impact-of-seed-words-on-sentiment |
| Repo | https://github.com/badc0re/sent-lex |
| Framework | none |
Bad Company—Neighborhoods in Neural Embedding Spaces Considered Harmful
| Title | Bad Company—Neighborhoods in Neural Embedding Spaces Considered Harmful |
| Authors | Johannes Hellrich, Udo Hahn |
| Abstract | We assess the reliability and accuracy of (neural) word embeddings for both modern and historical English and German. Our research provides deeper insights into the empirically justified choice of optimal training methods and parameters. The overall low reliability we observe, nevertheless, casts doubt on the suitability of word neighborhoods in embedding spaces as a basis for qualitative conclusions on synchronic and diachronic lexico-semantic matters, an issue currently high up in the agenda of Digital Humanities. |
| Tasks | Word Embeddings |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1262/ |
| https://www.aclweb.org/anthology/C16-1262 | |
| PWC | https://paperswithcode.com/paper/bad-companyaneighborhoods-in-neural-embedding |
| Repo | https://github.com/hellrich/coling2016 |
| Framework | none |
Data-Driven Morphological Analysis and Disambiguation for Morphologically Rich Languages and Universal Dependencies
| Title | Data-Driven Morphological Analysis and Disambiguation for Morphologically Rich Languages and Universal Dependencies |
| Authors | Amir More, Reut Tsarfaty |
| Abstract | Parsing texts into universal dependencies (UD) in realistic scenarios requires infrastructure for the morphological analysis and disambiguation (MA{&}D) of typologically different languages as a first tier. MA{&}D is particularly challenging in morphologically rich languages (MRLs), where the ambiguous space-delimited tokens ought to be disambiguated with respect to their constituent morphemes, each morpheme carrying its own tag and a rich set features. Here we present a novel, language-agnostic, framework for MA{&}D, based on a transition system with two variants {—} word-based and morpheme-based {—} and a dedicated transition to mitigate the biases of variable-length morpheme sequences. Our experiments on a Modern Hebrew case study show state of the art results, and we show that the morpheme-based MD consistently outperforms our word-based variant. We further illustrate the utility and multilingual coverage of our framework by morphologically analyzing and disambiguating the large set of languages in the UD treebanks. |
| Tasks | Morphological Analysis |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1033/ |
| https://www.aclweb.org/anthology/C16-1033 | |
| PWC | https://paperswithcode.com/paper/data-driven-morphological-analysis-and |
| Repo | https://github.com/habeanf/yap |
| Framework | none |
Learning principled bilingual mappings of word embeddings while preserving monolingual invariance
| Title | Learning principled bilingual mappings of word embeddings while preserving monolingual invariance |
| Authors | Mikel Artetxe, Gorka Labaka, Eneko Agirre |
| Abstract | |
| Tasks | Machine Translation, Word Embeddings |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1250/ |
| https://www.aclweb.org/anthology/D16-1250 | |
| PWC | https://paperswithcode.com/paper/learning-principled-bilingual-mappings-of |
| Repo | https://github.com/artetxem/vecmap |
| Framework | none |
BIRA: Improved Predictive Exchange Word Clustering
| Title | BIRA: Improved Predictive Exchange Word Clustering |
| Authors | Jon Dehdari, Liling Tan, Josef van Genabith |
| Abstract | |
| Tasks | Chunking, Machine Translation, Word Alignment |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1139/ |
| https://www.aclweb.org/anthology/N16-1139 | |
| PWC | https://paperswithcode.com/paper/bira-improved-predictive-exchange-word |
| Repo | https://github.com/jonsafari/clustercat |
| Framework | none |
Hierarchical Attention Networks for Document Classification
| Title | Hierarchical Attention Networks for Document Classification |
| Authors | Zichao Yang, Diyi Yang, Chris Dyer, Xiaodong He, Alex Smola, Eduard Hovy |
| Abstract | |
| Tasks | Citation Intent Classification, Document Classification, Sentiment Analysis, Text Classification |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1174/ |
| https://www.aclweb.org/anthology/N16-1174 | |
| PWC | https://paperswithcode.com/paper/hierarchical-attention-networks-for-document |
| Repo | https://github.com/ematvey/hierarchical-attention-networks |
| Framework | tf |
The Product Cut
| Title | The Product Cut |
| Authors | Thomas Laurent, James Von Brecht, Xavier Bresson, Arthur Szlam |
| Abstract | We introduce a theoretical and algorithmic framework for multi-way graph partitioning that relies on a multiplicative cut-based objective. We refer to this objective as the Product Cut. We provide a detailed investigation of the mathematical properties of this objective and an effective algorithm for its optimization. The proposed model has strong mathematical underpinnings, and the corresponding algorithm achieves state-of-the-art performance on benchmark data sets. |
| Tasks | graph partitioning |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6226-the-product-cut |
| http://papers.nips.cc/paper/6226-the-product-cut.pdf | |
| PWC | https://paperswithcode.com/paper/the-product-cut |
| Repo | https://github.com/xbresson/pcut |
| Framework | none |
Transition-Based Neural Word Segmentation
| Title | Transition-Based Neural Word Segmentation |
| Authors | Meishan Zhang, Yue Zhang, Guohong Fu |
| Abstract | |
| Tasks | Chinese Word Segmentation, Feature Engineering |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1040/ |
| https://www.aclweb.org/anthology/P16-1040 | |
| PWC | https://paperswithcode.com/paper/transition-based-neural-word-segmentation |
| Repo | https://github.com/SUTDNLP/NNTransitionSegmentor |
| Framework | none |
Sublinear Time Orthogonal Tensor Decomposition
| Title | Sublinear Time Orthogonal Tensor Decomposition |
| Authors | Zhao Song, David Woodruff, Huan Zhang |
| Abstract | A recent work (Wang et. al., NIPS 2015) gives the fastest known algorithms for orthogonal tensor decomposition with provable guarantees. Their algorithm is based on computing sketches of the input tensor, which requires reading the entire input. We show in a number of cases one can achieve the same theoretical guarantees in sublinear time, i.e., even without reading most of the input tensor. Instead of using sketches to estimate inner products in tensor decomposition algorithms, we use importance sampling. To achieve sublinear time, we need to know the norms of tensor slices, and we show how to do this in a number of important cases. For symmetric tensors $ T = \sum_{i=1}^k \lambda_i u_i^{\otimes p}$ with $\lambda_i > 0$ for all i, we estimate such norms in sublinear time whenever p is even. For the important case of p = 3 and small values of k, we can also estimate such norms. For asymmetric tensors sublinear time is not possible in general, but we show if the tensor slice norms are just slightly below $\ T _F$ then sublinear time is again possible. One of the main strengths of our work is empirical - in a number of cases our algorithm is orders of magnitude faster than existing methods with the same accuracy. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6496-sublinear-time-orthogonal-tensor-decomposition |
| http://papers.nips.cc/paper/6496-sublinear-time-orthogonal-tensor-decomposition.pdf | |
| PWC | https://paperswithcode.com/paper/sublinear-time-orthogonal-tensor |
| Repo | https://github.com/huanzhang12/sampling_tensor_decomp |
| Framework | none |
Phrasal Substitution of Idiomatic Expressions
| Title | Phrasal Substitution of Idiomatic Expressions |
| Authors | Changsheng Liu, Rebecca Hwa |
| Abstract | |
| Tasks | Automatic Post-Editing, Lexical Simplification, Machine Translation, Sentiment Analysis, Word Sense Disambiguation |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1040/ |
| https://www.aclweb.org/anthology/N16-1040 | |
| PWC | https://paperswithcode.com/paper/phrasal-substitution-of-idiomatic-expressions |
| Repo | https://github.com/liucs1986/idiom_corpus |
| Framework | none |
