Articles

Arabic Dialects present many challenges for machine translation, not least of which is the lack of data resources. We use crowdsourc- ing to cheaply and quickly build Levantine- English and Egyptian-English parallel cor- pora, consisting of 1.1M words and 380k words, respectively. The dialectal sentences are selected from a large …...

The use of conventional maximum likelihood estimates hinders the performance of existing phrase-based translation models. For lack of sufficient training data, most models only con- sider a small amount of context. As a par- tial remedy, we explore here several contin- uous space translation models, where transla- tion probabilities are …...

Modeling overlapping phrases in an align- ment model can improve alignment quality but comes with a high inference cost. For example, the model of DeNero and Klein (2010) uses an ITG constraint and beam-based Viterbi decoding for tractability, but is still slow. We first show that their model can be …...

Argumentative discourse contains not only language expressing claims and evidence, but also language used to organize these claims and pieces of evidence. Differentiating be- tween the two may be useful for many appli- cations, such as those that focus on the content (e.g., relation extraction) of arguments and those that …...

In conversation, speakers have been shown to entrain, or become more similar to each other, in various ways. We measure entrain- ment on eight acoustic features extracted from the speech of subjects playing a cooperative computer game and associate the degree of en- trainment with a number of manually-labeled social …...

Many works (of both fiction and non-fiction) span multiple, intersecting narratives, each of which constitutes a story in its own right. In this work I introduce the task of multiple nar- rative disentanglement (MND), in which the aim is to tease these narratives apart by assign- ing passages from a …...

We examine evaluation methods for systems that automatically annotate images using co- occurring text. We compare previous datasets for this task using a series of baseline mea- sures inspired by those used in information re- trieval, computer vision, and extractive sum- marization. Some of our baselines match or exceed the …...

In this paper, a new method for automatic cognate detection in multilingual wordlists will be presented. The main idea behind the method is to combine different approaches to sequence comparison in historical linguistics and evolutionary biology into a new frame- work which closely models the most impor- tant aspects of …...

This paper presents a novel method for aligning etymological data, which mod- els context-sensitive rules governing sound change, and utilizes phonetic features of the sounds. The goal is, for a given corpus of cognate sets, to find the best alignment at the sound level. We introduce an imputa- tion procedure …...

The principal goal of this paper is to illustrate various ways in which phylogenetic tools can advantageously be put to use in investigating and visualizing the relationships of creole languages to other languages, both creoles and non-creoles. After introducing a test study on the English-based creoles, the major theories seeking …...

The paper reports several studies about quantifying language similarity via pho- netic alignment of core vocabulary items (taken from Wichman’s Automated Simi- larity Judgement Program data base). turns out that weighted alignment accord-It ing to the Needleman-Wunsch algorithm yields best results. For visualization and data exploration pur- poses, we used …...

In this paper, we propose a novel approach to compare languages on the basis of par- allel texts. Instead of using word lists or abstract grammatical characteristics to infer (phylogenetic) relationships, we use mul- tilingual alignments of words in sentences to establish measures of language similar- ity. To this end, …...

A SHIBBOLETH is a pronunciation, or, more generally, a variant of speech that betrays where a speaker is from (Judges 12:6). We propose a generalization of the well-known precision and recall scores to deal with the case of detecting distinctive, characteristic variants when the analysis is based on numerical difference …...

This paper proposes a simple metric of di- alect distance, based on the ratio between identical word pairs and cognate word pairs occurring in two texts. Different variations of this metric are tested on a corpus contain- ing comparable texts from different Swiss German dialects and evaluated on the basis …...

Words are important both in historical lin- guistics and natural language processing. They are not indivisible abstract atoms; much can be gained by considering smaller units such as morphemes, phonemes, syl- lables, and letters. In this presentation, I attempt to sketch the similarity pat- terns among a number of diverse …...

We demonstrate how data-driven ap- proaches to learner corpora can support Second Language Acquisition research when integrated with visualisation tools. We present a visual user interface support- ing the investigation of a set of linguistic features discriminating between pass and fail ‘English as a Second or Other Lan- guage’ exam …...

This paper presents a novel way of vi- sualising relationships between languages. The key feature of the visualisation is that it brings geographic, phylogenetic, and linguistic data together into a single im- age, allowing a new visual perspective on linguistic typology. The data presented here is extracted from the World …...

Each expanding and developing system requires some feedback to evaluate the normal trends of the system and also the unsystematic steps. In this paper two lexical- semantic databases – Princeton WordNet (PrWN) and Estonian Wordnet (EstWN)- are being examined from the visualization point of view. The visualization method is described …...

In statistical NLP, Semantic Vector Spaces (SVS) are the standard technique for the automatic modeling of lexical semantics. However, it is largely unclear how these black-box techniques exactly capture word meaning. To explore the way an SVS struc- tures the individual occurrences of words, we use a non-parametric MDS solution …...

We present a quantitative investigation of the cross-linguistic usage of some (rel- atively) newly minted derivational mor- phemes. In particular, we examine the lexi- cal semantic content expressed by three suf- fixes originating in English: -gate, -geddon and -athon. Using data from newspa- pers, we look at the distribution and …...