Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Text": models, code, and papers

Chasing the Ghosts of Ibsen: A computational stylistic analysis of drama in translation

Jan 05, 2015
Gerard Lynch, Carl Vogel

Research into the stylistic properties of translations is an issue which has received some attention in computational stylistics. Previous work by Rybicki (2006) on the distinguishing of character idiolects in the work of Polish author Henryk Sienkiewicz and two corresponding English translations using Burrow's Delta method concluded that idiolectal differences could be observed in the source texts and this variation was preserved to a large degree in both translations. This study also found that the two translations were also highly distinguishable from one another. Burrows (2002) examined English translations of Juvenal also using the Delta method, results of this work suggest that some translators are more adept at concealing their own style when translating the works of another author whereas other authors tend to imprint their own style to a greater extent on the work they translate. Our work examines the writing of a single author, Norwegian playwright Henrik Ibsen, and these writings translated into both German and English from Norwegian, in an attempt to investigate the preservation of characterization, defined here as the distinctiveness of textual contributions of characters.

* Digital Humanities 2009 Proceedings, University of Maryland, College Park, MD, USA, pages 192-195 
* 6 pages 

  Access Paper or Ask Questions

A machine-compiled macroevolutionary history of Phanerozoic life

Jul 19, 2014
Shanan E. Peters, Ce Zhang, Miron Livny, Christopher Ré

Many aspects of macroevolutionary theory and our understanding of biotic responses to global environmental change derive from literature-based compilations of palaeontological data. Existing manually assembled databases are, however, incomplete and difficult to assess and enhance. Here, we develop and validate the quality of a machine reading system, PaleoDeepDive, that automatically locates and extracts data from heterogeneous text, tables, and figures in publications. PaleoDeepDive performs comparably to humans in complex data extraction and inference tasks and generates congruent synthetic macroevolutionary results. Unlike traditional databases, PaleoDeepDive produces a probabilistic database that systematically improves as information is added. We also show that the system can readily accommodate sophisticated data types, such as morphological data in biological illustrations and associated textual descriptions. Our machine reading approach to scientific data integration and synthesis brings within reach many questions that are currently underdetermined and does so in ways that may stimulate entirely new modes of inquiry.

  Access Paper or Ask Questions

ATLAS: A flexible and extensible architecture for linguistic annotation

Jul 13, 2000
Steven Bird, David Day, John Garofolo, John Henderson, Christophe Laprun, Mark Liberman

We describe a formal model for annotating linguistic artifacts, from which we derive an application programming interface (API) to a suite of tools for manipulating these annotations. The abstract logical model provides for a range of storage formats and promotes the reuse of tools that interact through this API. We focus first on ``Annotation Graphs,'' a graph model for annotations on linear signals (such as text and speech) indexed by intervals, for which efficient database storage and querying techniques are applicable. We note how a wide range of existing annotated corpora can be mapped to this annotation graph model. This model is then generalized to encompass a wider variety of linguistic ``signals,'' including both naturally occuring phenomena (as recorded in images, video, multi-modal interactions, etc.), as well as the derived resources that are increasingly important to the engineering of natural language processing systems (such as word lists, dictionaries, aligned bilingual corpora, etc.). We conclude with a review of the current efforts towards implementing key pieces of this architecture.

* Proceedings of the Second International Conference on Language Resources and Evaluation, pp. 1699-1706, Paris: European Language Resources Association, 2000 
* 8 pages, 9 figures 

  Access Paper or Ask Questions

Using a Diathesis Model for Semantic Parsing

Jun 29, 2000
Jordi Atserias, Irene Castellon, Montse Civit, German Rigau

This paper presents a semantic parsing approach for unrestricted texts. Semantic parsing is one of the major bottlenecks of Natural Language Understanding (NLU) systems and usually requires building expensive resources not easily portable to other domains. Our approach obtains a case-role analysis, in which the semantic roles of the verb are identified. In order to cover all the possible syntactic realisations of a verb, our system combines their argument structure with a set of general semantic labelled diatheses models. Combining them, the system builds a set of syntactic-semantic patterns with their own role-case representation. Once the patterns are build, we use an approximate tree pattern-matching algorithm to identify the most reliable pattern for a sentence. The pattern matching is performed between the syntactic-semantic patterns and the feature-structure tree representing the morphological, syntactical and semantic information of the analysed sentence. For sentences assigned to the correct model, the semantic parsing system we are presenting identifies correctly more than 73% of possible semantic case-roles.

* Proceedins of VEXTAL.1999 pg 385-392 
* 8 pages 

  Access Paper or Ask Questions

Summary Markov Models for Event Sequences

May 06, 2022
Debarun Bhattacharjya, Saurabh Sihag, Oktie Hassanzadeh, Liza Bialik

Datasets involving sequences of different types of events without meaningful time stamps are prevalent in many applications, for instance when extracted from textual corpora. We propose a family of models for such event sequences -- summary Markov models -- where the probability of observing an event type depends only on a summary of historical occurrences of its influencing set of event types. This Markov model family is motivated by Granger causal models for time series, with the important distinction that only one event can occur in a position in an event sequence. We show that a unique minimal influencing set exists for any set of event types of interest and choice of summary function, formulate two novel models from the general family that represent specific sequence dynamics, and propose a greedy search algorithm for learning them from event sequence data. We conduct an experimental investigation comparing the proposed models with relevant baselines, and illustrate their knowledge acquisition and discovery capabilities through case studies involving sequences from text.

* In Proceedings of International Joint Conference on Artificial Intelligence (IJCAI) 2022 

  Access Paper or Ask Questions

Anti-Spoofing Using Transfer Learning with Variational Information Bottleneck

Apr 04, 2022
Youngsik Eom, Yeonghyeon Lee, Ji Sub Um, Hoirin Kim

Recent advances in sophisticated synthetic speech generated from text-to-speech (TTS) or voice conversion (VC) systems cause threats to the existing automatic speaker verification (ASV) systems. Since such synthetic speech is generated from diverse algorithms, generalization ability with using limited training data is indispensable for a robust anti-spoofing system. In this work, we propose a transfer learning scheme based on the wav2vec 2.0 pretrained model with variational information bottleneck (VIB) for speech anti-spoofing task. Evaluation on the ASVspoof 2019 logical access (LA) database shows that our method improves the performance of distinguishing unseen spoofed and genuine speech, outperforming current state-of-the-art anti-spoofing systems. Furthermore, we show that the proposed system improves performance in low-resource and cross-dataset settings of anti-spoofing task significantly, demonstrating that our system is also robust in terms of data size and data distribution.

* Submitted to Interspeech 2022 

  Access Paper or Ask Questions

StyleBabel: Artistic Style Tagging and Captioning

Mar 11, 2022
Dan Ruta, Andrew Gilbert, Pranav Aggarwal, Naveen Marri, Ajinkya Kale, Jo Briggs, Chris Speed, Hailin Jin, Baldo Faieta, Alex Filipkowski, Zhe Lin, John Collomosse

We present StyleBabel, a unique open access dataset of natural language captions and free-form tags describing the artistic style of over 135K digital artworks, collected via a novel participatory method from experts studying at specialist art and design schools. StyleBabel was collected via an iterative method, inspired by `Grounded Theory': a qualitative approach that enables annotation while co-evolving a shared language for fine-grained artistic style attribute description. We demonstrate several downstream tasks for StyleBabel, adapting the recent ALADIN architecture for fine-grained style similarity, to train cross-modal embeddings for: 1) free-form tag generation; 2) natural language description of artistic style; 3) fine-grained text search of style. To do so, we extend ALADIN with recent advances in Visual Transformer (ViT) and cross-modal representation learning, achieving a state of the art accuracy in fine-grained style retrieval.

  Access Paper or Ask Questions

Speaker Adaption with Intuitive Prosodic Features for Statistical Parametric Speech Synthesis

Mar 02, 2022
Pengyu Cheng, Zhenhua Ling

In this paper, we propose a method of speaker adaption with intuitive prosodic features for statistical parametric speech synthesis. The intuitive prosodic features employed in this method include pitch, pitch range, speech rate and energy considering that they are directly related with the overall prosodic characteristics of different speakers. The intuitive prosodic features are extracted at utterance-level or speaker-level, and are further integrated into the existing speaker-encoding-based and speaker-embedding-based adaptation frameworks respectively. The acoustic models are sequence-to-sequence ones based on Tacotron2. Intuitive prosodic features are concatenated with text encoder outputs and speaker vectors for decoding acoustic features.Experimental results have demonstrated that our proposed methods can achieve better objective and subjective performance than the baseline methods without intuitive prosodic features. Besides, the proposed speaker adaption method with utterance-level prosodic features has achieved the best similarity of synthetic speech among all compared methods.

* Accepted by ICDSP2022 

  Access Paper or Ask Questions

JARVix at SemEval-2022 Task 2: It Takes One to Know One? Idiomaticity Detection using Zero and One Shot Learning

Feb 04, 2022
Ashwin Pathak, Raj Shah, Vaibhav Kumar, Yash Jakhotiya

Large Language Models have been successful in a wide variety of Natural Language Processing tasks by capturing the compositionality of the text representations. In spite of their great success, these vector representations fail to capture meaning of idiomatic multi-word expressions (MWEs). In this paper, we focus on the detection of idiomatic expressions by using binary classification. We use a dataset consisting of the literal and idiomatic usage of MWEs in English and Portuguese. Thereafter, we perform the classification in two different settings: zero shot and one shot, to determine if a given sentence contains an idiom or not. N shot classification for this task is defined by N number of common idioms between the training and testing sets. In this paper, we train multiple Large Language Models in both the settings and achieve an F1 score (macro) of 0.73 for the zero shot setting and an F1 score (macro) of 0.85 for the one shot setting. An implementation of our work can be found at .

* Best Project Award for Georgia Tech CS 7650. Code available at 

  Access Paper or Ask Questions