Articles

Most work on language acquisition treats word segmentation—the identification of lin- guistic segments from continuous speech— and word learning—the mapping of those seg- ments to meanings—as separate problems. These two abilities develop in parallel, how- ever, raising the question of whether they might interact. To explore the question, we present …...

Although Wikipedia has emerged as a power- ful collaborative Encyclopedia on the Web, it is only partially multilingual as most of the content is in English and a small number of other languages. In real-life scenarios, non- English users in general and ESL/EFL 1 users in particular, have a need …...

This paper address the problem of entity link- ing. Specifically, given an entity mentioned in unstructured texts, the task is to link this entity with an entry stored in the existing knowledge base. This is an important task for informa- tion extraction. It can serve as a convenient gateway to …...

The goal of this work is to integrate query similarity metrics as features into a dense model that can be trained on large amounts of query log data, in order to rank query rewrites. We propose features that incorpo- rate various notions of syntactic and semantic similarity in a generalized …...

Many implementations of Latent Dirichlet Al- location (LDA), including those described in Blei et al. (2003), rely at some point on the removal of stopwords, words which are as- sumed to contribute little to the meaning of the text. This step is considered necessary be- cause otherwise high-frequency words tend …...

Perceptron training is widely applied in the natural language processing community for learning complex structured models. Like all structured prediction learning frameworks, the structured perceptron can be costly to train as training complexity is proportional to in- ference, which is frequently non-linear in ex- ample sequence length. In this paper …...

We describe a Bayesian inference algorithm that can be used to train any cascade of weighted finite-state transducers on end-to- end data. We also investigate the problem of automatically selecting from among mul- tiple training runs. Our experiments on four different tasks demonstrate the genericity of this framework, and, where …...

This paper proposes a general learning frame- work for a class of problems that require learn- ing over latent intermediate representations. Many natural language processing (NLP) de- cision problems are defined over an expressive intermediate representation that is not explicit in the input, leaving the algorithm with both the task …...

Most state of the art approaches for machine transliteration are data driven and require sig- nificant parallel names corpora between lan- guages. As a result, developing translitera- tion functionality among n languages could be a resource intensive task requiring paral- lel names corpora in the order of nC2. In this …...

A number of recent articles in computational linguistics venues called for a closer exami- nation of the type of noise present in anno- tated datasets used for benchmarking (Rei- dsma and Carletta, 2008; Beigman Klebanov and Beigman, 2009). In particular, Beigman Klebanov and Beigman articulated a type of noise they …...

This paper investigates the impact of mis- spelled words in statistical machine transla- tion and proposes an extension of the transla- tion engine for handling misspellings. The en- hanced system decodes a word-based confu- sion network representing spelling variations of the input text. We present extensive experimental results on two …...

The quality of a statistical machine transla- tion (SMT) system is heavily dependent upon the amount of parallel sentences used in train- ing. In recent years, there have been several approaches developed for obtaining parallel sentences from non-parallel, or comparable data, such as news articles published within the same time …...

Typical statistical machine translation sys- tems are trained with static parallel corpora. Here we account for scenarios with a continu- ous incoming stream of parallel training data. Such scenarios include daily governmental proceedings, sustained output from transla- tion agencies, or crowd-sourced translations. We show incorporating recent sentence pairs from the …...

Coreference resolution is governed by syntac- tic, semantic, and discourse constraints. We present a generative, model-based approach in which each of these factors is modularly en- capsulated and learned in a primarily unsu- pervised manner. Our semantic representation first hypothesizes an underlying set of latent entity types, which generate specific …...

Noun phrases (NP) in a product review are always considered as the product attribute candidates in previous work. However, this method limits the recall of the product at- tribute extraction. We therefore propose a novel approach by generalizing syntactic structures of the product attributes with two strategies: intuitive heuristics and …...

This work incorporates Selectional Prefer- ences (SP) into a Semantic Role (SR) Clas- sification system. We learn separate selec- tional preferences for noun phrases and prepo- sitional phrases and we integrate them in a state-of-the-art SR classification system both in the form of features and individual class predictors. We show …...

In the field of machine translation, automatic metrics have proven quite valuable in system development for tracking progress and meas- uring the impact of incremental changes. However, human judgment still plays a large role in the context of evaluating MT systems. For example, the GALE project uses human- targeted translation …...

We report on work in progress on extract- ing lexical simplifications (e.g., “collaborate” → “work together”), focusing on utilizing edit histories in Simple English Wikipedia for this task. We consider two main approaches: (1) deriving simplification probabilities via an edit model that accounts for a mixture of dif- ferent operations, …...

Understanding query ambiguity in web search remains an important open problem. In this paper we reexamine query ambiguity by ana- lyzing the result clickthrough data. Previously proposed clickthrough-based metrics of query ambiguity tend to conflate informational and ambiguous queries. To distinguish between these query classes, we introduce novel met- rics …...

We explore the relation between word sense subjectivity and cross-lingual lexical substitu- tion, following the intuition that good substi- tutions will transfer a word’s (contextual) sen- timent from the source language into the target language. Experiments on English-Chinese lexical substitution show that taking a word’s subjectivity into account can indeed …...