Articles

This paper reports on an implementation of a multimodal grammar of speech and co-speech gesture within the LKB/PET grammar engi- neering environment. The implementation ex- tends the English Resource Grammar (ERG, Flickinger (2000)) with HPSG types and rules that capture the form of the linguistic signal, the form of the …...

We investigate models for unsupervised learn- ing with concave log-likelihood functions. We begin with the most well-known example, IBM Model 1 for word alignment (Brown et al., 1993) and analyze its properties, dis- cussing why other models for unsupervised learning are so seldom concave. We then present concave models for …...

We present a novel method for evaluating grammatical error correction. The core of our method, which we call MaxMatch (M2), is an algorithm for efficiently computing the sequence of phrase-level edits between a source sentence and a system hypothesis that achieves the highest overlap with the gold- standard annotation. This …...

We describe and evaluate several methods for estimating the confidence in the per-edge cor- rectness of a predicted dependency parse. We show empirically that the confidence is asso- ciated with the probability that an edge is se- lected correctly and that it can be used to de- tect incorrect edges …...

This paper describes a user study where hu- mans interactively train automatic text clas- sifiers. We attempt to replicate previous re- sults using multiple “average” Internet users instead of a few domain experts as annotators. We also analyze user annotation behaviors to find that certain labeling actions have an im- …...

Parallel corpora have applications in many ar- eas of Natural Language Processing, but are very expensive to produce. Much information can be gained from comparable texts, and we present an algorithm which, given any bod- ies of text in multiple languages, uses ex- isting named entity recognition software and topic …...

This paper introduces a general method to in- corporate the LDA Topic Model into text seg- mentation algorithms. We show that seman- tic information added by Topic Models signifi- cantly improves the performance of two word- based algorithms, namely TextTiling and C99. Additionally, we introduce the new TopicTil- ing algorithm …...

Determining the reading level of children’s lit- erature is an important task for providing edu- cators and parents with an appropriate reading trajectory through a curriculum. Automating this process has been a challenge addressed before in the computational linguistics litera- ture, with most studies attempting to predict the particular grade …...

We present a novel method to detect parallel fragments within noisy parallel corpora. Isolat- ing these parallel fragments from the noisy data in which they are contained frees us from noisy alignments and stray links that can severely constrain translation-rule extraction. We do this with existing machinery, making use of …...

Shallow-n grammars (de Gispert et al., 2010) were introduced to reduce over-generation in the Hiero translation model (Chiang, 2005) re- sulting in much faster decoding and restricting reordering to a desired level for specific lan- guage pairs. However, Shallow-n grammars require parameters which cannot be directly optimized using minimum error-rate …...

We propose a tuning method for statistical ma- chine translation, based on the pairwise rank- ing approach. Hopkins and May (2011) pre- sented a method that uses a binary classifier. In this work, we use linear regression and show that our approach is as effective as us- ing a binary …...

In the area of machine translation (MT) sys- tem combination, previous work on generat- ing input hypotheses has focused on varying a core aspect of the MT system, such as the de- coding algorithm or alignment algorithm. In this paper, we propose a new method for gen- erating diverse hypotheses …...

This paper describes our ongoing work on resolving third person pronouns and deictic words in a multi-modal corpus. We show that about two thirds of these referring expressions have antecedents that are introduced by point- ing gestures or by haptic-ostensive actions (actions that involve manipulating an object). After describing our …...

We analyze overt displays of power (ODPs) in written dialogs. We present an email cor- pus with utterances annotated for ODP and present a supervised learning system to predict it. We obtain a best cross validation F-measure of 65.8 using gold dialog act features and 55.6 without using them. 1...

Recent exploratory efforts in discourse-level language modeling have relied heavily on cal- culating Pointwise Mutual Information (PMI), which involves significant computation when done over large collections. Prior work has required aggressive pruning or independence assumptions to compute scores on large col- lections. We show the method of Condi- tional Random …...

We present an active learning method for coreference resolution that is novel in three re- spects. (i) It uses bootstrapped neighborhood pooling, which ensures a class-balanced pool even though gold labels are not available. (ii) It employs neighborhood selection, a selection strategy that ensures coverage of both posi- tive and …...

Coarse-to-fine inference has been shown to be a robust approximate method for improving the efficiency of structured prediction models while preserving their accuracy. We propose a multi-pass coarse-to-fine architecture for de- pendency parsing using linear-time vine prun- ing and structured prediction cascades. Our first-, second-, and third-order models achieve accuracies …...

We introduce lightly supervised learning for dependency parsing. In this paradigm, the al- gorithm is initiated with a parser, such as one that was built based on a very limited amount of fully annotated training data. Then, the al- gorithm iterates over unlabeled sentences and asks only for a single …...

It has been established that incorporating word cluster features derived from large unlabeled corpora can significantly improve prediction of linguistic structure. While previous work has focused primarily on English, we extend these results to other languages along two dimen- sions. First, we show that these results hold true for a …...

Negated statements often carry positive im- plicit meaning. Regardless of the seman- tic representation one adopts, pinpointing the positive concepts within a negated statement is needed in order to encode the statement’s meaning. In this paper, novel ideas to reveal positive implicit meaning using focus of nega- tion are presented. …...