Articles

We explore the near-synonym lexical choice problem using a novel representa- tion of near-synonyms and their contexts in the latent semantic space. In contrast to traditional latent semantic analysis (LSA), our model is built on the lexical level of co-occurrence, which has been empir- ically proven to be effective in …...

We propose a structure called dependency forest for statistical machine translation. A dependency forest compactly represents multiple dependency trees. We develop new algorithms for extracting string-to- dependency rules and training depen- dency language models. Our forest-based string-to-dependency system obtains sig- nificant improvements ranging from 1.36 to 1.46 BLEU points over …...

Automated conversion has allowed the de- velopment of wide-coverage corpora for a variety of grammar formalisms without the expense of manual annotation. Analysing new languages also tests formalisms, ex- posing their strengths and weaknesses. We present Chinese CCGbank, a 760,000 word corpus annotated with Combinatory Categorial Grammar (CCG) derivations, in- …...

Martins et al. (2008) presented what to the best of our knowledge still ranks as the best overall result on the CONLL- X Shared Task datasets. The paper shows how triads of stacked dependency parsers described in Martins et al. (2008) can label unlabeled data for each other in a …...

Verb classes which integrate a wide range of linguistic properties (Levin, 1993) have proved useful for natural language pro- cessing (NLP) applications. However, the real-world use of these classes has been limited because for most languages, no resources similar to VerbNet (Kipper- Schuler, 2005) are available. We apply a verb …...

We employ Maximum Entropy model to con- duct sub-tree alignment between bilingual phrasal structure trees. Various lexical and structural knowledge is explored to measure the syntactic similarity across Chinese-English bi- lingual tree pairs. In the experiment, we evalu- ate the sub-tree alignment using both gold standard tree bank and the …...

In this paper, we describe a novel ap- proach to computational modeling and understanding of social and cul- tural phenomena in multi-party dia- logues. We developed a two-tier ap- proach in which we first detect and classify certain social language uses, including topic control, disagreement, and involvement, that serve as …...

We present a novel Evaluation Metric for Morphological Analysis (EMMA) that is both linguistically appealing and empirically sound. EMMA uses a graph- based assignment algorithm, optimized via integer linear programming, to match morphemes of predicted word analyses to the analyses of a morphologically rich answer key. This is necessary especially …...

Zulu is an indigenous language of South Africa, and one of the eleven official languages of that country. It is spoken by about 11 million speakers. Although it is similar in size to some Western languages, e.g. Swedish, it is consid- erably under-resourced. This paper presents a new open-source morphologi- …...

Main approaches to corpus-based seman- tic class mining include distributional similarity (DS) and pattern-based (PB). In this paper, we perform an empirical comparison of them, based on a publicly available dataset containing 500 million web pages, using various categories of queries. We further propose a frequency- based rule to select …...

The paper describes a weakly supervised approach for decomposing words into all morphemes: stems, prefixes and suffixes, using wordforms with marked stems as training data. As we concentrate on under-resourced languages, the amount of training data is limited and we need some amount of supervision in the form of a …...

The interpretation of a multiple-domain text corpus as a single ontology leads to misconceptions. This is because some concepts may be syntactically equal; though, they are semantically lopsided in different domains. Also, the occurrences of a domain concept in a large multiple- domain corpus may not gauge correctly the concept …...

Route directions are natural language (NL) statements that specify, for a given navigational task and an automatically computed route representation, a se- quence of actions to be followed by the user to reach his or her goal. A corpus- based approach to generate route direc- tions involves (i) the selection …...

Thanks to its simplicity, social tagging system has accumulated huge amount of user contributed tags. However, user contributed tags lack explicit hierarchi- cal structure, while many tag-based ap- plications would benefit if such a struc- ture presents. In this work, we explore the structure of tags with a directed and …...

Active learning has been applied to dif- ferent NLP tasks, with the aim of limit- ing the amount of time and cost for human annotation. Most studies on active learn- ing have only simulated the annotation scenario, using prelabelled gold standard data. We present the first active learning experiment for …...

Model minimization has been shown to work well for the task of unsupervised part-of-speech tagging with a dictionary. In (Ravi and Knight, 2009), the authors in- voke an integer programming (IP) solver to do model minimization. However, solving this problem exactly using an integer programming formulation is in- tractable for …...

Multi-document summarization has been an important problem in infor- mation retrieval. It aims to dis- till the most important information from a set of documents to gener- ate a compressed summary. Given a sentence graph generated from a set of documents where vertices repre- sent sentences and edges indicate that …...

Research in named entity recognition and mention detection has typically involved a fairly small number of semantic classes, which may not be adequate if seman- tic class information is intended to sup- port natural language applications. Moti- vated by this observation, we examine the under-studied problem of semantic sub- type …...

We present a novel approach to auto- matic metaphor identification in unre- stricted text. Starting from a small seed set of manually annotated metaphorical ex- pressions, the system is capable of har- vesting a large number of metaphors of similar syntactic structure from a corpus. Our method is distinguished from …...

Emotion words have been well used as the most obvious choice as feature in the task of textual emotion recognition and auto- matic emotion lexicon construction. In this work, we explore features for rec- ognizing word emotion. Based on Ren- CECps (an annotated emotion corpus) and MaxEnt (Maximum entropy) model, …...