Articles

We present a new translation model in- tegrating the shallow local multi bottom- up tree transducer. We perform a large- scale empirical evaluation of our obtained system, which demonstrates that we sig- nificantly beat a realistic tree-to-tree base- line on the WMT 2009 English → German translation task. As an …...

Typical statistical machine translation sys- tems are batch trained with a given train- ing data and their performances are large- ly influenced by the amount of data. With the growth of the available data across different domains, it is computationally demanding to perform batch training ev- ery time when new …...

Most statistical machine translation (SMT) systems are modeled using a log- linear framework. Although the log-linear model achieves success in SMT, it still suffers from some limitations: (1) the features are required to be linear with respect to the model itself; (2) features cannot be further interpreted to reach their …...

Modern phrase-based machine translation systems make extensive use of word- based translation models for inducing alignments from parallel corpora. This is problematic, as the systems are inca- pable of accurately modelling many trans- lation phenomena that do not decompose into word-for-word translation. This pa- per presents a novel method for …...

This paper introduces a graph-based semi- supervised joint model of Chinese word segmentation and part-of-speech tagging. The proposed approach is based on a graph-based label propagation technique. One constructs a nearest-neighbor simi- larity graph over all trigrams of labeled and unlabeled data for propagating syn- tactic information, i.e., label distribution- …...

Empty categories (EC) are artificial ele- ments in Penn Treebanks motivated by the government-binding (GB) theory to ex- plain certain language phenomena such as pro-drop. ECs are ubiquitous in languages like Chinese, but they are tacitly ignored in most machine translation (MT) work because of their elusive nature. In this …...

We address the problem of informal word recognition in Chinese microblogs. A key problem is the lack of word delimiters in Chinese. We exploit this reliance as an opportunity: recognizing the relation be- tween informal word recognition and Chi- nese word segmentation, we propose to model the two tasks jointly. …...

We introduce the novel task of automati- cally generating questions that are relevant to a text but do not appear in it. One mo- tivating example of its application is for increasing user engagement around news articles by suggesting relevant compara- ble questions, such as “is Beyonce a bet- ter …...

With the increasing amount of user gener- ated reference texts in the web, automatic quality assessment has become a key chal- lenge. However, only a small amount of annotated data is available for training quality assessment systems. Wikipedia contains a large amount of texts anno- tated with cleanup templates which …...

We describe a novel approach for automat- ically predicting the hidden demographic properties of social media users. Building on prior work in common-sense knowl- edge acquisition from third-person text, we first learn the distinguishing attributes of certain classes of people. For exam- ple, we learn that people in the Female …...

Punctuations are not available in automatic speech recognition outputs, which could cre- ate barriers to many subsequent text pro- cessing tasks. This paper proposes a novel method to predict punctuation symbols for the stream of words in transcribed speech texts. Our method jointly performs parsing and punctuation prediction by integrating …...

Standard methods for part-of-speech tagging suffer from data sparseness when used on highly inflectional languages (which require large lexical tagset inventories). For this reason, a number of alternative methods have been proposed over the years. One of the most successful methods used for this task, ����������������������������, 1999), exploits a reduced …...

Online discussion forums are a popular platform for people to voice their opinions on any subject matter and to discuss or debate any issue of interest. In forums where users discuss social, political, or religious issues, there are often heated debates among users or participants. Existing research has studied mining …...

Metaphor is an important way of convey- ing the affect of people, hence understand- ing how people use metaphors to convey affect is important for the communication between individuals and increases cohe- sion if the perceived affect of the con- crete example is the same for the two in- dividuals. …...

Structural information in web text pro- vides natural annotations for NLP prob- lems such as word segmentation and pars- ing. In this paper we propose a discrim- inative learning algorithm to take advan- tage of the linguistic knowledge in large amounts of natural annotations on the In- ternet. It utilizes …...

We propose the hypothesis that word ety- mology is useful for NLP applications as a bridge between languages. We support this hypothesis with experiments in cross- language (English-Italian) document cat- egorization. In a straightforward bag-of- words experimental set-up we add etymo- logical ancestors of the words in the docu- ments, …...

Wikipedia infoboxes are a valuable source of structured knowledge for global knowl- edge sharing. However, infobox infor- mation is very incomplete and imbal- anced among the Wikipedias in differen- t languages. It is a promising but chal- lenging problem to utilize the rich struc- tured knowledge from a source language …...

We present a novel approach to noun phrase lemmatisation where the main phase is cast as a tagging problem. The idea draws on the observation that the lemmatisation of almost all Polish noun phrases may be decomposed into trans- formation of singular words (tokens) that make up each phrase. We …...

This paper studies the problem of mining named entity translations from compara- ble corpora with some “asymmetry”. Un- like the previous approaches relying on the “symmetry” found in parallel corpora, the proposed method is tolerant to asymme- try often found in comparable corpora, by distinguishing different semantics of rela- tions …...

In this paper we show that even for the case of 1:1 substitution ciphers—which encipher plaintext symbols by exchang- ing them with a unique substitute—finding the optimal decipherment with respect to a bigram language model is NP-hard. We show that in this case the decipherment problem is equivalent to the …...