42 Hits in 5.3 sec

Attention based Anaphora Resolution for Code-Mixed Social Media Text for Hindi Language

Sandhya Singh, Kevin Patel, Pushpak Bhattacharyya
2020 Forum for Information Retrieval Evaluation  
In this paper, we investigate the problem of anaphora resolution for code-mixed (Hindi and English) Twitter data. We propose a modified encoder-decoder with attention model for anaphora resolution.  ...  Its complexity is further aggravated when applied in a social media setting, often due to inherent challenges in code-mixed data widely prevalent in such a setting.  ...  As per our knowledge, this will be the first attempt to address the problem of anaphora resolution for code-mixed social media text for Hindi language.  ... 
dblp:conf/fire/SinghPB20 fatcat:bhscyydj45c7xnqbq2n2ot6t74

Machine Reading Comprehension: Methods and Trends of Low Resource Languages

2021 jecet  
This is due to the unavailability of large-scale training datasets in low resource languages. Several studies on Machine Reading Comprehension (MRC) have proposed MRC models based on English.  ...  Nonetheless, these models provide insignificant performance on low-resource languages. However, limited research has been done using low resource languages, particularly Arabic, Urdu, and Hindi.  ...  MRC Model for Code-Mixed Hindi Language: For the sequence modeling on the code mixed the Hindi language, a lot of work has been done by different researchers.  ... 
doi:10.24214/jecet.b.10.2.05775 fatcat:fto7t3avmzexzn6nfsuu4k2emm

Natural Language Processing: State of The Art, Current Trends and Challenges [article]

Diksha Khurana, Aditya Koli, Kiran Khatter, Sukhdev Singh
2017 arXiv   pre-print
Natural language processing (NLP) has recently gained much attention for representing and analysing human language computationally.  ...  The paper distinguishes four phases by discussing different levels of NLP and components of Natural Language Generation (NLG) followed by presenting the history and evolution of NLP, state of the art presenting  ...  Emotion Detection (Shashank Sharma, 2016) [34] is similar to sentiment analysis, but it works on social media platforms on mixing of two languages (English + Any other Indian Language).  ... 
arXiv:1708.05148v1 fatcat:7dvsgmaslvddhdiy3udohgudky

Over a Decade of Social Opinion Mining [article]

Keith Cortis, Brian Davis
2020 arXiv   pre-print
Social media popularity and importance is on the increase, due to people using it for various types of social interaction across multiple channels.  ...  affect, sarcasm and irony, from user-generated content represented across multiple social media platforms and in various media formats, like text, image, video and audio.  ...  Emoticons/Emojis Social media can be seen as a sub-language that uses emoticons/emojis mixed with text to show emotions [45] .  ... 
arXiv:2012.03091v1 fatcat:bm5nydbdvbalzi33l3w2ivkdja

Automatic text summarization: What has been done and what has to be done [article]

Abdelkrime Aries, Djamel eddine Zegour, Walid Khaled Hidouci
2019 arXiv   pre-print
Most of these challenges are much more related to the nature of processed languages. These challenges are interesting for academics and developers, as a path to follow in this field.  ...  Automatic summarization and, in particular, Automatic text summarization (ATS) is not a new research field; It was known since the 50s.  ...  The test corpus contains 10 topics for French, Chinese and Hindi, and 15 topics for the remaining languages.  ... 
arXiv:1904.00688v1 fatcat:xvvjdpu3xzdsdn4piksz2s4pve

Message from the general chair

Benjamin C. Lee
2015 2015 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)  
We propose a candidate ranking model for "this-issue" anaphora resolution that explores different "issue"-specific and general abstract-anaphora features. The model is not restricted to nominal  ...  Joint Learning for Coreference Resolution with Markov Logic Resolving "This-issue" Anaphora Varada Kolhatkar and Graeme Hirst Saturday 12:00pm-12:30pm -202 A (ICC) We annotate and resolve a particular  ...  A Broad-Coverage Normalization System for Social Media Language Fei Liu, Fuliang Weng, and Xiao Jiang Monday 6:00pm-9:00pm -3F Lobby (ICC) Social media language contains huge amount and wide variety of  ... 
doi:10.1109/ispass.2015.7095776 dblp:conf/ispass/Lee15 fatcat:ehbed6nl6barfgs6pzwcvwxria

A survey on sentiment analysis in Urdu: A resource-poor language

Asad Khattak, Muhammad Zubair Asghar, Anam Saeed, Ibrahim A. Hameed, Syed Asif Hassan, Shakeel Ahmad
2020 Egyptian Informatics Journal  
Based on experimental results and proposals forwarded through this paper provides the groundwork for further studies on Urdu sentiment analysis. Ó 2020 THE AUTHORS.  ...  While the volume of studies conducted on sentiment analysis is rapidly expanding, these studies mostly address English language concerns.  ...  words reflecting code mixing based behaviour.  ... 
doi:10.1016/j.eij.2020.04.003 fatcat:qvymechpvnhypg2telxbs4wj4m

Bridging Chasms In Hindustani Music Retrieval

Joe Cheri Ross, Preeti Rao, Pushpak Bhattacharyya
2018 Zenodo  
Our investigation on extracting meta-information from natural language text focuses on coreference resolution, with the aim of improving relation extraction from textual content.  ...  This research is motivated by the importance of a music recommendation system for Hindustani music.  ...  The choice of the system was based on the code accessibility to make the modification required for mention pair pruning.  ... 
doi:10.5281/zenodo.1237568 fatcat:mrshrvhbcbb2lf4n7gys6e6plq

Syntactic and cognitive issues in investigating gendered coreference

Lauren Ackerman
2019 Glossa  
Mental models as contexts for interpreting texts: Implications from studies of anaphora. Journal of Semantics 7(4). 379–393.  ...  The problem with binaries: Coding for gender and sexuality. Language and Linguistics Compass 8(11). 529–535. DOI: Epple, Carolyn. 1998.  ... 
doi:10.5334/gjgl.721 fatcat:6h2mrpjxtzbzjlvouidkmh6fvy

Trading tongues: merchants, multilingualism, and medieval literature

2014 ChoiceReviews  
and Emily Steiner, were generous and attentive readers.  ...  I would first like to thank Malcolm Litchfield at The Ohio State University Press and Ethan Knapp for enthusiastically supporting this project and providing a venue for this work.  ...  Pratt's coinage of the "contact zone" imbues the phenomenon of language contact with an important spatializing force, drawing attention to how languages mix and commingle within particular geographical  ... 
doi:10.5860/choice.51-3666 fatcat:ows3fgm2qzaf7mnzopgrpzfsy4


T.A. Gridina, T.V. Ustinova
2016 Russian Linguistic Bulletin  
The poet's lingua-creative innovations and modifications are described in this paper as prompts for the reader's novel and unique conceptualization.  ...  The Associative Theory of Linguistic Creativity is put forward as an attempt to explain the dynamic process of meaning construction in cases of deliberate language nonconformity in poetry.  ...  The paper is prepared within the project No.15-04-00465 "National-cultural specificity of the Arctic dwellers' linguistic awareness", supported by the Russian Foundation for Humanities.  ... 
doi:10.18454/rulb.6.27 fatcat:vqglnxeamraj3ikgayebvwcove

Synchronic and Diachronic Approaches to Linguistic Variation and Change

Dieter Wanner, Thomas J. Walsh
1990 The Modern Language Journal  
These developments, in my opinion, hold great promise for a better understanding of language learning, and as a result, for the improvement of language teaching.  ...  was the ninth annual symposium for teachers and scholars on 'Languages in the schools.'  ...  In Genji texts, main characters who appear often in the story, and who are centers of attention, are more likely to be coded implicitly than are participants who play minor roles.  ... 
doi:10.2307/328159 fatcat:rqh7vaod3rc7hgi3o7xgaabxpa

Introduction [chapter]

L. Ashley Squires
2021 Emerging Writing Research from the Russian Federation  
This program included substantial funding for incentives for faculty who publish in international journals and for support services to help them do so.  ...  Pressure to publish is intense regardless of the language scholars are working in (see Chapter 3 and Chapter 4).  ...  Her works have also appeared in RELC Journal, Lingua, Metaphor, and The Social World.  ... 
doi:10.37514/int-b.2021.1428.1.3 fatcat:kvtht4ip5nfwjas347pmlk72nu

Low-Resource Adaptation of Neural NLP Models [article]

Farhad Nooralahzadeh
2020 arXiv   pre-print
These resources are often based on language data available in large quantities, such as English newswire.  ...  The objective of this thesis is to investigate methods for dealing with such low-resource scenarios in information extraction and natural language understanding.  ...  In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.  ... 
arXiv:2011.04372v1 fatcat:626mbe5ba5bkdflv755o35u5pq

The ways of referential deficiency: Impersonal on and its kin [article]

Milan Rezac, Mélanie Jouitteau
2016 Zenodo  
We end the book on the place of impersonals in the landscape of argument coding and explore the expected parameter space through on-like impersonals cross-linguistically.  ...  indefinites and definites; neutrality about content like number; systematic participation in syntactic and semantic dependencies but with unparalleled restrictions like binding of only local, number-neutral anaphora  ...  We would still need to rule out base-generating on and a non-λ-bound la on the relevant reading by MP, as in the text.  ... 
doi:10.5281/zenodo.5823634 fatcat:v4ie5x7xube2jokphozx4cvaau
« Previous Showing results 1 — 15 out of 42 results