Articles

We propose an approach to natural lan- guage inference based on a model of nat- ural logic, which identifies valid infer- ences by their lexical and syntactic fea- tures, without full semantic interpretation. We greatly extend past work in natural logic, which has focused solely on seman- tic containment and …...

Most studies in statistical or machine learning based authorship attribution focus on two or a few authors. This leads to an overestimation of the importance of the features extracted from the training data and found to be discriminating for these small sets of authors. Most studies also use sizes of …...

Translation model size is growing at a pace that outstrips improvements in computing power, and this hinders research on many interesting models. We show how an al- gorithmic scaling technique can be used to easily handle very large models. Us- ing this technique, we explore several large model variants and …...

Community-based question answering (cQA) services have accumulated millions of questions and their answers over time. In the process of accumulation, cQA ser- vices assume that questions always have unique best answers. However, with an in- depth analysis of questions and answers on cQA services, we find that the assump- tion …...

Query-oriented update summarization is an emerging summarization task very recently. It brings new challenges to the sentence ranking algorithms that require not only to locate the important and query-relevant information, but also to capture the new information when document collections evolve. In this paper, we propose a novel graph based …...

Media reporting shapes public opinion which can in turn influence events, partic- ularly in political elections, in which can- didates both respond to and shape public perception of their campaigns. We use computational linguistics to automatically predict the impact of news on public per- ception of political candidates. Our sys- …...

Active learning is a proven method for re- ducing the cost of creating the training sets that are necessary for statistical NLP. How- ever, there has been little work on stopping criteria for active learning. An operational stopping criterion is necessary to be able to use active learning in NLP …...

In this paper, we work on extending a Chinese thesaurus with words distinctly used in various Chinese communities. The acquisition and classification of such region-specific lexical items is an impor- tant step toward the larger goal of con- structing a Pan-Chinese lexical resource. In particular, we extend a previous study …...

We conduct large-scale experiments to in- vestigate optimal features for classification of verbs in biomedical texts. We intro- duce a range of feature sets and associated extraction techniques, and evaluate them thoroughly using a robust method new to the task: cost-based framework for pair- wise clustering. Our best results compare …...

Electronic written texts used in computer- mediated interactions (e-mails, blogs, chats, etc) present major deviations from the norm of the language. This paper presents an comparative study of systems aiming at normalizing the orthography of French SMS messages: after discussing the linguistic peculiarities of these mes- sages, and possible approaches …...

Existing algorithms for the Generation of Referring Expressions tend to gen- erate distinguishing descriptions at the semantic level, disregarding the ways in which surface issues can affect their quality. This paper considers how these algorithms should deal with surface am- biguity, focussing on structural ambi- guity. We propose that not …...

This paper discusses local alignment ker- nels in the context of the relation extrac- tion task. We define a local alignment kernel based on the Smith-Waterman mea- sure as a sequence similarity metric and proceed with a range of possibilities for computing a similarity between elements of sequences. We propose …...

This paper tackles textual demand analy- sis, the task of capturing what people want or need, rather than identifying what they like or dislike, on which much conven- tional work has focused. It exploits syn- tactic patterns as clues to detect previously unknown demands, and requires domain- dependent knowledge to …...

Word clustering is a conventional and im- portant NLP task, and the literature has suggested two kinds of approaches to this problem. One is based on the distribu- tional similarity and the other relies on the co-occurrence of two words in lexico- syntactic patterns. Although the two meth- ods have …...

In this paper, we describe a new rerank- ing strategy named word lattice reranking, for the task of joint Chinese word segmen- tation and part-of-speech (POS) tagging. As a derivation of the forest reranking for parsing (Huang, 2008), this strategy reranks on the pruned word lattice, which potentially contains much …...

Part of the unique cultural heritage of China is the game of Chinese couplets (duìlián). One person challenges the oth- er person with a sentence (first sentence). The other person then replies with a sen- tence (second sentence) equal in length and word segmentation, in a way that corresponding words …...

The use of similarities has been one of the main approaches to resolve the ambigui- ties of coordinate structures. In this pa- per, we present an alternative method for coordination disambiguation, which does not use similarities. Our hypothesis is that coordinate structures are supported by surrounding dependency relations, and that …...

Classifying what-type questions into proper semantic categories is found more challenging than classifying other types in question answering systems. In this paper, we propose to classify what-type questions by head noun tagging. The ap- proach highlights the role of head nouns as the category discriminator of what- type questions. To …...

In Japanese dependency parsing, Kudo’s relative preference-based method (Kudo and Matsumoto, 2005) outperforms both deterministic and probabilistic CKY-based parsing methods. In Kudo’s method, for each dependent word (or chunk) a log- linear model estimates relative preference of all other candidate words (or chunks) for being as its head. This cannot …...

This paper describes a system for process- ing economic documents written in the an- cient Sumerian language. The system is application-oriented and takes advantage of the simplicity of ancient economy. We have developed an ontology for a selected branch of economic activities. We trans- late the documents into a meaning …...