Articles

We present a joint language and transla- tion model based on a recurrent neural net- work which predicts target words based on an unbounded history of both source and tar- get words. The weaker independence as- sumptions of this model result in a vastly larger search space compared to related …...

Domain adaptation for SMT usually adapts models to an individual specific domain. However, it often lacks some correlation among different domains where common knowledge could be shared to improve the overall translation quality. In this paper, we propose a novel multi-domain adaptation ap- proach for SMT using Multi-Task Learning (MTL), …...

Left-to-right (LR) decoding (Watanabe et al., 2006b) is a promising decoding algorithm for hierarchical phrase-based translation (Hiero). It generates the target sentence by extending the hypotheses only on the right edge. LR de- coding has complexity O(n2b) for input of n words and beam size b, compared to O(n3) for …...

When using a machine translation (MT) model trained on OLD-domain parallel data to translate NEW-domain text, one major chal- lenge is the large number of out-of-vocabulary (OOV) and new-translation-sense words. We present a method to identify new translations of both known and unknown source language words that uses NEW-domain comparable …...

This paper presents the Kazakh Language Corpus (KLC), which is one of the first attempts made within a local research community to assemble a Kazakh corpus. KLC is designed to be a large scale corpus containing over 135 million words and con- veying five stylistic genres: literary, publicistic, of- ficial, …...

Web search users frequently modify their queries in hope of receiving better results. This process is referred to as “Query Refor- mulation”. Previous research has mainly fo- cused on proposing query reformulations in the form of suggested queries for users. Some research has studied the problem of predicting whether the …...

Direct quotations are used for opinion min- ing and information extraction as they have an easy to extract span and they can be attributed to a speaker with high accuracy. However, simply focusing on direct quotations ignores around half of all reported speech, which is in the form of indirect …...

Temporal variations of text are usually ig- nored in NLP applications. However, text use changes with time, which can affect many applications. In this paper we model peri- odic distributions of words over time. Focus- ing on hashtag frequency in Twitter, we first automatically identify the periodic patterns. We use …...

Scope detection is a key task in information ex- traction. This paper proposes a new approach for tree kernel-based scope detection by using the structured syntactic parse information. In addi- tion, we have explored the way of selecting compatible features for different part-of-speech cues. Experiments on the BioScope corpus show …...

We present an approach for building multi- document event threads from a large corpus of newswire articles. An event thread is basi- cally a succession of events belonging to the same story. It helps the reader to contextual- ize the information contained in a single arti- cle, by navigating backward …...

Passage retrieval is a crucial first step of au- tomatic Question Answering (QA). While ex- isting passage retrieval algorithms are effec- tive at selecting document passages most sim- ilar to the question, or those that contain the expected answer types, they do not take into account which parts of the …...

We present a method for automatically learn- ing inflectional classes and associated lem- mas from morphologically annotated corpora. The method consists of a core language- independent algorithm, which can be opti- mized for specific languages. The method is demonstrated on Egyptian Arabic and Ger- man, two morphologically rich languages. Our …...

Natural language conversation is widely re- garded as a highly difficult problem, which is usually attacked with either rule-based or learning-based models. In this paper we propose a retrieval-based automatic response model for short-text conversation, to exploit the vast amount of short conversation in- stances available on social media. For …...

In Japanese, zero references often occur and many of them are categorized into zero ex- ophora, in which a referent is not mentioned in the document. However, previous studies have focused on only zero endophora, in which a referent explicitly appears. We present a zero reference resolution model considering zero …...

We present a classification model that predicts the presence or omission of a lexical connec- tive between two clauses, based upon linguis- tic features of the clauses and the type of dis- course relation holding between them. The model is trained on a set of high frequency relations extracted from …...

Implicit feature detection, also known as im- plicit feature identification, is an essential as- pect of feature-specific opinion mining but previous works have often ignored it. We think, based on the explicit sentences, sever- al Support Vector Machine (SVM) classifier- s can be established to do this task. Never- theless, …...

We introduce a new highly scalable approach for computing Distributional Thesauri (DTs). By employing pruning techniques and a dis- tributed framework, we make the computation for very large corpora feasible on comparably small computational resources. We demon- strate this by releasing a DT for the whole vo- cabulary of Google …...

We explore a model of stress prediction in Russian using a combination of lo- cal contextual features and linguistically- motivated features associated with the word’s stem and suffix. We frame this as a ranking problem, where the objec- tive is to rank the pronunciation with the correct stress above those …...

Explanatory sentences are employed to clarify reasons, details, facts, and so on. High quality online product reviews usually include not only positive or negative opinions, but also a variety of explanations of why these opinions were given. These explanations can help readers get easily comprehensible informa- tion of the discussed …...

This paper investigates the utility and effect of running numerous random restarts when us- ing EM to attack decipherment problems. We find that simple decipherment models are able to crack homophonic substitution ciphers with high accuracy if a large number of random restarts are used but almost completely fail with …...