Sciweavers

ACL
2015
9 years 11 months ago
Reducing infrequent-token perplexity via variational corpora
Recurrent neural network (RNN) is recognized as a powerful language model (LM). We investigate deeper into its performance portfolio, which performs well on frequent grammatical p...
Yusheng Xie, Pranjal Daga, Yu Cheng, Kunpeng Zhang...
ACL
2015
9 years 11 months ago
Modeling Argument Strength in Student Essays
While recent years have seen a surge of interest in automated essay grading, including work on grading essays with respect to particular dimensions such as prompt adherence, coher...
Isaac Persing, Vincent Ng
ACL
2015
9 years 11 months ago
Learning the Semantics of Manipulation Action
In this paper we present a formal computational framework for modeling manipulation actions. The introduced formalism leads to semantics of manipulation action and has application...
Yezhou Yang, Yiannis Aloimonos, Cornelia Fermü...
ACL
2015
9 years 11 months ago
NEED4Tweet: A Twitterbot for Tweets Named Entity Extraction and Disambiguation
In this demo paper, we present NEED4Tweet, a Twitterbot for named entity extraction (NEE) and disambiguation (NED) for Tweets. The straightforward application of state-of-the-art ...
Mena B. Habib, Maurice van Keulen
ACL
2015
9 years 11 months ago
Machine Comprehension with Syntax, Frames, and Semantics
We demonstrate significant improvement on the MCTest question answering task (Richardson et al., 2013) by augmenting baseline features with features based on syntax, frame semant...
Hai Wang, Mohit Bansal, Kevin Gimpel, David A. McA...
ACL
2015
9 years 11 months ago
Seed-Based Event Trigger Labeling: How far can event descriptions get us?
The task of event trigger labeling is typically addressed in the standard supervised setting: triggers for each target event type are annotated as training data, based on annotati...
Ofer Bronstein, Ido Dagan, Qi Li, Heng Ji, Anette ...
ACL
2015
9 years 11 months ago
Labeled Grammar Induction with Minimal Supervision
Nearly all work in unsupervised grammar induction aims to induce unlabeled dependency trees from gold part-of-speechtagged text. These clean linguistic classes provide a very impo...
Yonatan Bisk, Christos Christodoulopoulos, Julia H...
87
Voted
ACL
2015
9 years 11 months ago
Unsupervised Prediction of Acceptability Judgements
In this paper we present the task of unsupervised prediction of speakers’ acceptability judgements. We use a test set generated from the British National Corpus (BNC) containing...
Jey Han Lau, Alexander Clark, Shalom Lappin
ACL
2015
9 years 11 months ago
Emotion Detection in Code-switching Texts via Bilingual and Sentimental Information
Code-switching is commonly used in the free-form text environment, such as social media, and it is especially favored in emotion expressions. Emotions in codeswitching texts diffe...
Zhongqing Wang, Sophia Yat Mei Lee, Shoushan Li, G...
ACL
2015
9 years 11 months ago
User Based Aggregation for Biterm Topic Model
Biterm Topic Model (BTM) is designed to model the generative process of the word co-occurrence patterns in short texts such as tweets. However, two aspects of BTM may restrict its...
Weizheng Chen, Jinpeng Wang, Yan Zhang, Hongfei Ya...