Computational Linguistics

Top PDF Computational Linguistics:

Last Words: The Shrinking Horizons of Computational Linguistics

Last Words: The Shrinking Horizons of Computational Linguistics

journals other than Computational Linguistics), as there is no such category in ISI JCR. This includes journals such as Computer Speech and Language, Natural Language Engi- neering, and IEEE Transactions on Speech and Audio Processing. I did not look at citations to workshops or conference papers, partly in order to simplify the analysis task, and partly because I am not aware of an independent subject classification of conferences and workshops similar to ISI JCR’s journal classifications. I suspect that the main effect of including conference and workshop citations would be to decrease the percentage of citations to non-CS areas (psychology, linguistics, mathematics, other), because CS researchers are much more likely to publish important findings in conferences than researchers in other disciplines.
Show more

6 Read more

Computational Linguistics and Generative Linguistics: The Triumph of Hope over Experience

Computational Linguistics and Generative Linguistics: The Triumph of Hope over Experience

The theme of this workshop is the interaction be- tween computational linguistics (CL) and general linguistics. The organizers ask whether it has it been virtuous, vicious, or vacuous. They use only three of the rather extraordinary number of v -initial adjectives. Is the relationship vital, valu- able, venturesome, visionary, versatile, and vi- brant? Or vague, variable, verbose, and sometimes vexatious? Has it perhaps been merely vestigial and vicarious, with hardly any general linguists really participating? Or vain, venal, vaporous, vir- ginal, volatile, and voguish, yet vulnerable, a re- lationship at risk? Or would the best description use adjectives like vengeful, venomous, vilifica- tory, villainous, vindictive, violent, vitriolic, vo- ciferous, and vulpine?
Show more

10 Read more

Computational Linguistics  Formerly the American Journal of Computational Linguistics, Volume 10, Number1, January March 1984

Computational Linguistics Formerly the American Journal of Computational Linguistics, Volume 10, Number1, January March 1984

Manuscripts submitted to COMPUTATIONAL LINGUISTICS should be typed on letter-size paper 8.5 by 11 inch or A4, double-spaced throughout, including footnotes and refer- ences.. The full fi[r]

6 Read more

35th Annual Meeting of the Association for Computational Linguistics and 8th Conference of the European Chapter of the Association for Computational Linguistics

35th Annual Meeting of the Association for Computational Linguistics and 8th Conference of the European Chapter of the Association for Computational Linguistics

In this, the first joint meeting of the American and European chapters of the Association for Computational Linguistics, you will find a wealth of high-quality papers, tutorials, and wor[r]

16 Read more

Microsyntactic Phenomena as a Computational Linguistics Issue

Microsyntactic Phenomena as a Computational Linguistics Issue

It is well known that lexically annotated text corpora are extremely helpful in lexical ambiguity resolution, especially in computational linguistics tasks. Lexical annotation means that polysemous words occurring in the corpus (ideally, all such words) are tagged for concrete lexical senses, specified by some lexicographic resource, be it a traditional explanatory dictionary or an electronic thesaurus like WordNet. Such lexically annotated corpora play a crucial role in word sense disambiguation (WSD) tasks. These tasks are normally solved by machine learning techniques, which are rapidly developing and improving. Research work in this area performed in varied paradigms for a multitude of languages is immense; recent papers, to cite but a few, include a comprehensive review by Navigly 2009, a paper by Moro et al. 2014, and newest research involving neural networks presented by Dayu Yuan et al. 2016.
Show more

10 Read more

Proceedings of the Workshop on Computational Linguistics for Literature

Proceedings of the Workshop on Computational Linguistics for Literature

Welcome to the second edition of our young but vibrant workshop on Computational Linguistics for Literature. We are thrilled to have been able to accept a pleasantly wide range of interesting papers on the computational treatment of literature. The ACL community is certainly embracing literature! We want the workshop to bring together NLP researchers interested in literature and literary scholars on the quantitative edge of their field. We feel that those who “count words” for a living have something to offer to people who “read books” for a living, and vice versa. As Rauscher et al. (this volume) put it:
Show more

12 Read more

Proceedings of the Fifth Workshop on Computational Linguistics for Literature

Proceedings of the Fifth Workshop on Computational Linguistics for Literature

Dr. Loss Pequeño Glazier is Director of the Electronic Poetry Center/E-Poetry Festivals and Professor, Department of Media Study, SUNY Buffalo. The EPC is the world’s largest digital resource for innovative and digital poetry. Glazier is the author of two books-in-progress as well as Digital Poetics: The Making of E-Poetries (Univ. of Alabama Press, 2002), Anatman, Pumpkin Seed, Algorithm (Salt Publishing, 2003), Small Press: An Annotated Guide (Greenwood, 1992), and hundreds of poems, essays, film, visual art, sound and digital works, as well as projects for dance, music, installations, and performance, including at the Neuberger Museum (SUNY Purchase), Royal Festival Hall (London), Instituto del Libro (La Habana), Guggenheim Museum (New York), UCLA Hammer Museum, Kulturforum Potsdamer Platz (Berlin), University of London, Le Divan du Monde (Paris), Bowery Poetry Club (New York), Brown University, and the Palazzo delle Arti Napoli. Glazier’s work in digital writing focuses on code and its discontents, whether in natural language permutation, translation, computer programming, computational linguistics and aesthetic, spatial, and poetics. His author page contains numerous examples of his work.
Show more

12 Read more

TGermaCorp – A (Digital) Humanities Resource for (Computational) Linguistics

TGermaCorp – A (Digital) Humanities Resource for (Computational) Linguistics

ables and Ripley, 2002)), which consistently deals with ties for statistical significance on the distribution of all distances from the Monte Carlo simulations, we find that all pairwise distances are highly significant for the Jaccard similarities and the Euclidian distances. However, for the Mahalanobis distance between TGermaCorp and WikiMimikry, there was no significant difference. Since the distance measure determines the basis for further statistical and ultimately in- terpretative assessments, it is favorable to chose a number of different measures and/or to motivate the choice of mea- sure carefully. The question for the effect of measure has been raised with respect to various subfields various times, see for instance Cha (2007) on density functions providing a dendrogram of distance measures, Salleh et al. (2012) on geometrical shapes, Cerqueira-Silva et al. (2009) on molec- ular markers. The latter reported a highly significant Spear- man correlation of 0.58 between the Mahalanobis distance and the Euclidian distance, making them the most distant measures for their data and distance set. In computational linguistics, Rama and Kolachina (2012) worked on typo- logical distances. Jin and Barri`ere (2005) found in a pre- liminary study, that the Dice coefficient, most similar to the Jaccard index, correlated best with human similarity judg- ments. Given these considerations, the choice of the three applied measures allows for the assessment of different as- pects of the data and allows generalisability on the other hand.
Show more

7 Read more

Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics

Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics

I am honoured to write the first few words of these Proceedings, as General Chair of COLING/ACL 2006 in Sydney, Australia. As we know, this is just the third time in their history that the two traditionally major events in Computational Linguistics, COLING and ACL – organised respectively by ICCL (International Committee on Computational Linguistics) and ACL (the Association for Computational Linguistics) – are joined in one combined conference, after Stanford in 1984 and Montreal in 1998. I was lucky to attend both those wonderful events and would have never imagined to be “in charge” of the next one, the first of the new millennium!
Show more

38 Read more

Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics

Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics

The 2019 meeting of the Cognitive Modeling and Computational Linguistics (CMCL) workshop follows in the tradition of many CMCLs past. We are proud to have selected a broad spectrum of talks and topics this year, ranging from parsing models, to models of sentence comprehension, to speech production, to distributional semantics methods. We are also proud to host a poster session that is larger than in previous years, increasing the reach of our workshop and allowing us to support more junior researchers and more works in progress.

12 Read more

Proceedings of the 21st Nordic Conference on Computational Linguistics

Proceedings of the 21st Nordic Conference on Computational Linguistics

On behalf of the program committee, I am pleased to welcome you to the 21st Nordic Conference on Computational Linguistics (NoDaLiDa 2017), held at the Wallenberg Conference Center in the beautiful city of Gothenburg in Sweden, on May 22–24, 2017. The proceedings are published as part of the NEALT Proceedings Series by Link¨oping University Electronic Press and they will also be available from the ACL Anthology together with the proceedings of the co-located workshops. The NoDaLiDa conference has been organized bi-annually since 1977 and returns to this anniversary event after 40 years back to Gothenburg, where it started as a friendly gathering to discuss on-going research in the field of computational linguistics in the Nordic countries. The Northern European Association for Language Technology (NEALT) was founded later in 2006, which is now responsible for organizing NoDaLiDa among other events in the Nordic countries, the Baltic states and Northwest Russia. Since the early days, NoDaLiDa has grown into a recognized international conference and the tradition continues with the program of this year’s conference. It is a great honor for me to serve as the general chair of NoDaLiDa 2017 and I am grateful for all the support during the progress.
Show more

22 Read more

Proceedings of the 22nd Nordic Conference on Computational Linguistics

Proceedings of the 22nd Nordic Conference on Computational Linguistics

Welcome to the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa 2019) held at the University of Turku in the beautiful city of Turku in Finland, on September 30-October 2, 2019. The aim of NoDaLiDa is to bring together researchers in the Nordic countries interested in any aspect related to human language and speech technologies. It is a great honor for me to serve as the general chair of NoDaLiDa 2019.

21 Read more

Discovering Factions in the Computational Linguistics Community

Discovering Factions in the Computational Linguistics Community

We present a joint probabilistic model of who cites whom in computational linguistics, and also of the words they use to do the citing. The model reveals latent factions , or groups of in- dividuals whom we expect to collaborate more closely within their faction, cite within the fac- tion using language distinct from citation out- side the faction, and be largely understandable through the language used when cited from without. We conduct an exploratory data anal- ysis on the ACL Anthology. We extend the model to reveal changes in some authors’ fac- tion memberships over time.

11 Read more

Computational Linguistics at Universiti Sains Malaysia

Computational Linguistics at Universiti Sains Malaysia

The availability of powerful computers to store information has spurred researchers in natural language processing to set up not just databases of monolingual dictionaries and corpora, but also to pool data from various sources to set up multilingual dictionary databases. SIGLEX, a Special Interest Group of the Association for Computational Linguistics, is trying to link publicly available electronic dictionaries and corpora for studies in natural language processing (see http://www.cis.upenn.edu/~mpalmer/siglex/online.html).

5 Read more

Computational Linguistics Research at the University of Pennsylvania

Computational Linguistics Research at the University of Pennsylvania

American Journal of Computational Linguistics, Volume 9, Number 2, April-June 1983 95.. This in- volves at least the following: 1.[r]

6 Read more

Computational Linguistics Applications for Multimedia Services

Computational Linguistics Applications for Multimedia Services

Multilingual Access to Large Spoken Archives (MALACH) (Oard et al., 2002) was one of the early studies that used computational linguistics tools to build an automatic metadata extraction system. In MALACH, oral history recording data was processed through automatic speech recogni- tion (ASR) and natural language processing (NLP) pipelines that extracted relevant information for cataloging. In prototyping its World Service Archive (Raimond et al., 2014), the BBC devel- oped COMMA, an metadata extraction and linked data-based interlinking system for public radio broadcasts. Its outcome is now in use by the BBC (BBC, 2015), however it is not publicly avail- able. More recently, the EU funded Media in Con- text (MiCO) project (Aichroth et al., 2015). This project aimed at accomplishing a media analysis platform for multimodal media that supports cus- tomized workflows leveraging on assorted open and closed source content analysis tools. An in- teroperability layer, MiCO Broker, was developed based on RDF and XML structures to chain dif- ferent tools. Among the latest work, Audiovi- sual Metadata Platform (AMP) is noteworthy as it plans to design and develop a platform that ex- ploits chains of automated tools and human-in- the-loop to generate and manage metadata at in- stitutional scale (Dunn et al., 2018). We actively seek collaboration with others in order to move closer to achieving a “global laboratory” for lan- guage applications.
Show more

7 Read more

Programming of Reversible Systems in Computational Linguistics

Programming of Reversible Systems in Computational Linguistics

Programming of Reversible Systems in Computational Linguistics Programming of Reversible Systems in Computational Linguistics Gerhard Engelien, Forschungsgruppe LIMAS, Bonn ~ ~ I ~ ~ ~ ~ ~" ? In my pa[.]

5 Read more

How the Statistical Revolution Changes (Computational) Linguistics

How the Statistical Revolution Changes (Computational) Linguistics

Just to be clear: psycholinguistics and language acquisition are experimental disciplines, and I don’t expect the average researcher in those fields to start doing computational linguistics any time soon. However, I do think there are an emerging cadre of young researchers in both fields apply- ing ideas and results from computational linguis- tics in their work and using experimental results from their field to develop and improve the compu- tational models. For example, in psycholinguistics researchers such as Hale (2006) and Levy (2008) are using probabilistic models of syntactic struc- ture to make predictions about human sentence processing, and Bachrach (2008) is using predic- tions from the Roark (2001) parser to help explain the patterns of fMRI activation observed during sentence comprehension. In the field of language acquisition computational linguists such as Klein and Manning (2004) have studied the unsuper- vised acquisition of syntactic structure, while lin- guists such as Boersma and Hayes (2001), Gold- smith (2001), Pater (2008) and Albright and Hayes (2003) are developing probabilistic models of the acquisition of phonology and/or morphology, and Frank et al. (2007) experimentally tests the predic- tions of a Bayesian model of lexical acquisition. Since I have more experience with computational models of language acquisition, I’ll concentrate on this topic for the rest of this section.
Show more

9 Read more

Last Words: Computational Linguistics: What About the Linguistics?

Last Words: Computational Linguistics: What About the Linguistics?

As this historical summary implies, computational linguistics does not need mainstream, non-computational linguistics, whether to supply intellectual credibility or to ensure progress. Computational linguistics is not just linguistics with some practically useful but theoretically irrelevant and obfuscating nerdie add-ons. This is not to say that computational linguists can’t, and shouldn’t, take advantage of linguistics, or at least avoid culpable ignorance where linguists have something to offer. But the boot is now on the other foot, as Martin Kay was already claiming in 1973. He began his paper in the Rustin volume by saying that “For the most part, linguists are unaware of the importance that computers must one day have for their subject.” They still are, but that’s no skin off our noses: We have more interesting things to do. Thus while we may believe that computational linguistics continues to develop views of language that are worthwhile (whether because valid or just stimulating), as in thinking about process, and that linguistics ought to take notice, computational linguistics is solidly growing in its own right. It is also doing this the better because of the way it has its friendly neighbors, natural language processing, human language technology, and the others, that provide a rather demanding apparatus to test and evaluate its ideas.
Show more

6 Read more

Last Words: Computational Linguistics and Deep Learning

Last Words: Computational Linguistics and Deep Learning

that surely would make the world a better place.” Well, that sounds very nice! So, should computational linguistics researchers be afraid? I’d argue, no. To return to the Hitchhiker’s Guide to the Galaxy theme that Geoff Hinton introduced, we need to turn the book over and look at the back cover, which says in large, friendly letters: “Don’t panic.” 2. The Success of Deep Learning

7 Read more

Show all 4480 documents...