Articles

A word in one language can be translated to zero, one, or several words in other languages. Using word fertility features has been shown to be useful in building word alignment mod- els for statistical machine translation. We built a fertility hidden Markov model by adding fer- tility to the …...

Minimum Error Rate Training is the algo- rithm for log-linear model parameter train- ing most used in state-of-the-art Statistical Machine Translation systems. In its original formulation, the algorithm uses N-best lists output by the decoder to grow the Transla- tion Pool that shapes the surface on which the actual optimization …...

Domain adaptation, the problem of adapting a natural language processing system trained in one domain to perform well in a differ- ent domain, has received significant attention. This paper addresses an important problem for deployed systems that has received little at- tention – detecting when such adaptation is needed by …...

Part-of-speech (POS) induction is one of the most popular tasks in research on unsuper- vised NLP. Many different methods have been proposed, yet comparisons are difficult to make since there is little consensus on eval- uation framework, and many papers evalu- ate against only one or two competitor sys- tems. …...

We present the first evaluation of the utility of automatic evaluation metrics on surface real- izations of Penn Treebank data. Using outputs of the OpenCCG and XLE realizers, along with ranked WordNet synonym substitutions, we collected a corpus of generated surface re- alizations. These outputs were then rated and post-edited …...

Hierarchical phrase-based (HPB) translation provides a powerful mechanism to capture both short and long distance phrase reorder- ings. However, the phrase reorderings lack of contextual information in conventional HPB systems. This paper proposes a context- dependent phrase reordering approach that uses the maximum entropy (MaxEnt) model to help the HPB …...

We report on investigations into hierarchi- cal phrase-based translation grammars based on rules extracted from posterior distributions over alignments of the parallel text. Rather than restrict rule extraction to a single align- ment, such as Viterbi, we instead extract rules based on posterior distributions provided by the HMM word-to-word alignment …...

We address the modeling, parameter estima- tion and search challenges that arise from the...

The task of selecting information and render- ing it appropriately appears in multiple con- texts in summarization. In this paper we present a model that simultaneously optimizes selection and rendering preferences. The model operates over a phrase-based represen- tation of the source document which we ob- tain by merging PCFG …...

We employ statistical methods to analyze, generate, and translate rhythmic poetry. We first apply unsupervised learning to reveal word-stress patterns in a corpus of raw poetry. We then use these word-stress patterns, in ad- dition to rhyme and discourse models, to gen- erate English love poetry. Finally, we trans- late …...

We present a simple, robust generation system which performs content selection and surface realization in a unified, domain-independent framework. In our approach, we break up the end-to-end generation process into a se- quence of local decisions, arranged hierar- chically and each trained discriminatively. We deployed our system in three different …...

Most coreference resolution models determine if two mentions are coreferent using a single function over a set of constraints or features. This approach can lead to incorrect decisions as lower precision features often overwhelm the smaller number of high precision ones. To overcome this problem, we propose a simple coreference …...

In this paper we address two key challenges for extractive multi-document summarization: the search problem of finding the best scoring summary and the training problem of learn- ing the best model parameters. We propose an A* search algorithm to find the best extractive summary up to a given length, which …...

In situated dialogue humans often utter lin- guistic expressions that refer to extralinguistic entities in the environment. Correctly resolv- ing these references is critical yet challeng- ing for artificial agents partly due to their lim- ited speech recognition and language under- standing capabilities. Motivated by psycholin- guistic studies demonstrating a …...

There is considerable interest in interdis- ciplinary combinations of automatic speech recognition (ASR), machine learning, natu- ral language processing, text classification and information retrieval. Many of these boxes, especially ASR, are often based on consid- erable linguistic resources. We would like to be able to process spoken documents with few …...

We describe a new approach to SMT adapta- tion that weights out-of-domain phrase pairs according to their relevance to the target do- main, determined by both how similar to it they appear to be, and whether they belong to general language or not. This extends previ- ous work on discriminative …...

This paper studies two issues, non-isomorphic structure translation and target syntactic structure usage, for statistical machine translation in the context of forest-based tree to tree sequence trans- lation. For the first issue, we propose a novel non-isomorphic translation framework to capture more non-isomorphic structure mappings than tra- ditional tree-based and …...

This paper studies the problem of mining en- tity translation, specifically, mining English and Chinese name pairs. Existing efforts can be categorized into (a) a transliteration- based approach leveraging phonetic similar- ity and (b) a corpus-based approach exploiting bilingual co-occurrences, each of which suf- fers from inaccuracy and scarcity respectively. …...

For resource-limited language pairs, coverage of the test set by the parallel corpus is an important factor that affects translation qual- ity in two respects: 1) out of vocabulary words; 2) the same information in an input sentence can be expressed in different ways, while current phrase-based SMT systems can- …...

Language is sensitive to both semantic and pragmatic effects. To capture both effects, we model language use as a cooperative game between two players: a speaker, who gener- ates an utterance, and a listener, who responds with an action. Specifically, we consider the task of generating spatial references to ob- …...