Sciweavers

ACL
2015
10 years 11 days ago
Synthetic Word Parsing Improves Chinese Word Segmentation
We present a novel solution to improve the performance of Chinese word segmentation (CWS) using a synthetic word parser. The parser analyses the internal structure of words, and a...
Fei Cheng, Kevin Duh, Yuji Matsumoto
ACL
2015
10 years 11 days ago
Graph parsing with s-graph grammars
A key problem in semantic parsing with graph-based semantic representations is graph parsing, i.e. computing all possible analyses of a given graph according to a grammar. This pr...
Jonas Groschwitz, Alexander Koller, Christoph Teic...
ACL
2015
10 years 11 days ago
Towards a Contextual Pragmatic Model to Detect Irony in Tweets
This paper proposes an approach to capture the pragmatic context needed to infer irony in tweets. We aim to test the validity of two main hypotheses: (1) the presence of negations...
Jihen Karoui, Farah Benamara, Véronique Mor...
ACL
2015
10 years 11 days ago
Feature Selection in Kernel Space: A Case Study on Dependency Parsing
Given a set of basic binary features, we propose a new L1 norm SVM based feature selection method that explicitly selects the features in their polynomial or tree kernel spaces. T...
Xian Qian, Yang Liu 0004
ACL
2015
10 years 11 days ago
Using Tweets to Help Sentence Compression for News Highlights Generation
We explore using relevant tweets of a given news article to help sentence compression for generating compressive news highlights. We extend an unsupervised dependency-tree based s...
Zhongyu Wei, Yang Liu 0033, Chen Li, Wei Gao
ACL
2015
10 years 11 days ago
Non-Linear Text Regression with a Deep Convolutional Neural Network
Text regression has traditionally been tackled using linear models. Here we present a non-linear method based on a deep convolutional neural network. We show that despite having m...
Zsolt Bitvai, Trevor Cohn
ACL
2015
10 years 11 days ago
Parse Imputation for Dependency Annotations
Syntactic annotation is a hard task, but it can be made easier by allowing annotators flexibility to leave aspects of a sentence underspecified. Unfortunately, partial annotatio...
Jason Mielens, Liang Sun, Jason Baldridge
ACL
2015
10 years 11 days ago
Dependency Recurrent Neural Language Models for Sentence Completion
Recent work on language modelling has shifted focus from count-based models to neural models. In these works, the words in each sentence are always considered in a left-to-right o...
Piotr Mirowski, Andreas Vlachos
ACL
2015
10 years 11 days ago
Rhetoric Map of an Answer to Compound Queries
Given a discourse tree for a text as a candidate answer to a compound query, we propose a rule system for valid and invalid occurrence of the query keywords in this tree. To be a ...
Boris Galitsky, Dmitry I. Ilvovsky, Sergei O. Kuzn...
ACL
2015
10 years 11 days ago
Language to Code: Learning Semantic Parsers for If-This-Then-That Recipes
Using natural language to write programs is a touchstone problem for computational linguistics. We present an approach that learns to map natural-language descriptions of simple ...
Chris Quirk, Raymond J. Mooney, Michel Galley