Articles

We investigate the problem of parsing the noisy language of social media. We evalu- ate four Wall-Street-Journal-trained statis- tical parsers (Berkeley, Brown, Malt and MST) on a new dataset containing 1,000 phrase structure trees for sentences from microblogs (tweets) and discussion forum posts. We compare the four parsers on their …...

This paper proposes a method for extend- ing WordNet with terms in Wikipedia. Our method identifies a WordNet synset by in- tegrating evidence derived from the struc- ture of an article in Wikipedia and distri- butional similarity of terms. Unlike previ- ous methods, utilizing the hypernym and siblings of the …...

Word lists have become available for most of the world’s languages, but only a small fraction of such lists contain cognate in- formation. We present a machine-learning approach that automatically clusters words in multilingual word lists into cognate sets. Our method incorporates a number of di- verse word similarity measures …...

* Entity linking (EL) is the task of linking a textual named entity mention to a knowledge base entry. It is a difficult task involving many challenges, but the most crucial problem is entity ambiguity. Traditional EL approaches usually employ different constraints and filtering techniques to improve performance. However, these …...

News comment is a new text genre in the Web 2.0 era. Many people often write com- ments to express their opinions about recent news events or topics after they read news articles. Because news comments are freely written without checking, they are very dif- ferent from formal news texts. …...

The representative method of using mor- phological evidence for Chinese unknown word (UW) extraction is Chinese word segmentation (CWS) model, and the method of using distributional evidence for UW extraction is accessor variety (AV) criterion. However, neither of these meth- ods has been verified on large-scale cor- pus. In this …...

We propose a Named Entity (NE) recog- nition method in which word chunks are repeatedly decomposed and concatenated. We can obtain features from word chunks, such as the first word of a word chunk and the last word of a word chunk, which can- not be obtained in word-sequence-based recognition …...

The unavailability of parallel training cor- pora in resource-poor languages is a ma- jor bottleneck in cost-effective and rapid deployment of statistical machine transla- tion (SMT) technology. This has spurred significant interest in active learning for SMT to select the most informative sam- ples from a large candidate pool. This …...

Recent research on multilingual statisti- cal machine translation focuses on the us- age of pivot languages in order to over- come resource limitations for certain lan- guage pairs. This paper provides new in- sights into what factors make a good pivot language and investigates the impact of these factors on …...

x This paper proposes a novel method to resolve the coverage problem of SMT system. The method generates paraphrases for source-side sentences of the bilingual parallel data, which are then paired with the target-side sentences to generate new parallel data. Within a statis- tical paraphrase generation framework, we employ an …...

Word sequential alignment models work well for similar language pairs, but they are quite inadequate for distant language pairs. It is difficult to align words or phrases of distant languages with high ac- curacy without structural information of the sentences. In this paper, we pro- pose a Bayesian subtree alignment …...

We introduce a maximum spanning tree (MST) dependency parser that can be trained from partially annotated corpora, allowing for effective use of available lin- guistic resources and reduction of the costs of preparing new training data. This is especially important for domain adapta- tion in a real-world situation. We use …...

Efficient data structures are necessary for searching large translation rule dictionar- ies in forest-based machine translation. We propose a breadth-first representation of tree structures that allows trees to be stored and accessed efficiently. We de- scribe an algorithm that allows incremen- tal search for trees in a forest and show …...

We compare two types of methods which deal with unknown words in the context of computational grammars. Methods of the first type are based on the idea of su- pertagging and use a tagger to predict lex- ical descriptions for unknown tokens in a given input. The second type of …...

We present a discriminative model for Japanese zero anaphora resolution that si- multaneously determines an appropriate case frame for a given predicate and its predicate-argument structure. Our model is based on a log linear framework, and exploits lexical features obtained from a large raw corpus, as well as non-lexical features …...

Supervised approaches to Relation Extrac- tion (RE) are characterized by higher ac- curacy than unsupervised models. Unfor- tunately, their applicability is limited by the need of training data for each rela- tion type. Automatic creation of such data using Distant Supervision (DS) provides a promising solution to the problem. In …...

Open information extraction (IE) is a weakly supervised IE paradigm that aims to extract relation-independent informa- tion from large-scale natural language documents without significant annotation efforts. A key challenge for Open IE is to achieve self-supervision, in which the training examples are automatically ob- tained. Although the feasibility of Open …...

In event-based Information Extraction sys- tems, a major task is the automated fill- ing from unstructured texts of a template gathering information related to a partic- ular event. Such template filling may be a hard task when the information is scattered throughout the text and mixed with similar pieces of …...

Event extraction involves the identifica- tion of instances of a type of event, along with their attributes and participants. De- veloping a training corpus by annotating events in text is very labor intensive, and so selecting informative instances to an- notate can save a great deal of manual work. We …...

Compositional Distributional Semantic methods model the distributional behav- ior of a compound word by exploiting the distributional behavior of its constituent words. In this setting, a constituent word is typically represented by a feature vec- tor conflating all the senses of that word. However, not all the senses of a …...