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

AMR Parsing using Stack-LSTMs

Aug 02, 2017
Miguel Ballesteros, Yaser Al-Onaizan

We present a transition-based AMR parser that directly generates AMR parses from plain text. We use Stack-LSTMs to represent our parser state and make decisions greedily. In our experiments, we show that our parser achieves very competitive scores on English using only AMR training data. Adding additional information, such as POS tags and dependency trees, improves the results further.

* EMNLP 2017 

  Access Paper or Ask Questions

Discourse-Based Objectives for Fast Unsupervised Sentence Representation Learning

Apr 23, 2017
Yacine Jernite, Samuel R. Bowman, David Sontag

This work presents a novel objective function for the unsupervised training of neural network sentence encoders. It exploits signals from paragraph-level discourse coherence to train these models to understand text. Our objective is purely discriminative, allowing us to train models many times faster than was possible under prior methods, and it yields models which perform well in extrinsic evaluations.

  Access Paper or Ask Questions

Combining Semantic Wikis and Controlled Natural Language

Oct 17, 2008
Tobias Kuhn

We demonstrate AceWiki that is a semantic wiki using the controlled natural language Attempto Controlled English (ACE). The goal is to enable easy creation and modification of ontologies through the web. Texts in ACE can automatically be translated into first-order logic and other languages, for example OWL. Previous evaluation showed that ordinary people are able to use AceWiki without being instructed.

* In Proceedings of the Poster and Demonstration Session at the 7th International Semantic Web Conference (ISWC2008), CEUR Workshop Proceedings, Volume 401, 2008 

  Access Paper or Ask Questions

Integrating Multiple Knowledge Sources for Robust Semantic Parsing

Sep 17, 2001
Jordi Atserias, Lluis Padro, German Rigau

This work explores a new robust approach for Semantic Parsing of unrestricted texts. Our approach considers Semantic Parsing as a Consistent Labelling Problem (CLP), allowing the integration of several knowledge types (syntactic and semantic) obtained from different sources (linguistic and statistic). The current implementation obtains 95% accuracy in model identification and 72% in case-role filling.

* Proceedings of Euroconference on Recent Advances in Natural Language Processing (RANLP'01), p.8-14. Tzigov Chark, Bulgaria. Sept. 2001 

  Access Paper or Ask Questions

Corpus Annotation for Parser Evaluation

Jul 08, 1999
John Carroll, Guido Minnen, Ted Briscoe

We describe a recently developed corpus annotation scheme for evaluating parsers that avoids shortcomings of current methods. The scheme encodes grammatical relations between heads and dependents, and has been used to mark up a new public-domain corpus of naturally occurring English text. We show how the corpus can be used to evaluate the accuracy of a robust parser, and relate the corpus to extant resources.

* Proceedings of the EACL99 workshop on Linguistically Interpreted Corpora (LINC), Bergen, Norway, June 12 
* 7 pages, LaTeX (uses eaclap.sty) 

  Access Paper or Ask Questions

A Learning Approach to Natural Language Understanding

Jun 01, 1994
Roberto Pieraccini, Esther Levin

In this paper we propose a learning paradigm for the problem of understanding spoken language. The basis of the work is in a formalization of the understanding problem as a communication problem. This results in the definition of a stochastic model of the production of speech or text starting from the meaning of a sentence. The resulting understanding algorithm consists in a Viterbi maximization procedure, analogous to that commonly used for recognizing speech. The algorithm was implemented for building

* "New Advances and Trends in Speech Recognition and Coding", NATO ASI Series, Springer-Verlag, proceedings of the 1993 NATO ASI Summer School, Bubion, Spain, June-July 1993 
* 18 pages, Latex file + compressed figures 

  Access Paper or Ask Questions

Overview of the 2021 Key Point Analysis Shared Task

Oct 20, 2021
Roni Friedman, Lena Dankin, Yufang Hou, Ranit Aharonov, Yoav Katz, Noam Slonim

We describe the 2021 Key Point Analysis (KPA-2021) shared task on key point analysis that we organized as a part of the 8th Workshop on Argument Mining (ArgMining 2021) at EMNLP 2021. We outline various approaches and discuss the results of the shared task. We expect the task and the findings reported in this paper to be relevant for researchers working on text summarization and argument mining.

  Access Paper or Ask Questions

Pseudo-labelling Enhanced Media Bias Detection

Jul 16, 2021
Qin Ruan, Brian Mac Namee, Ruihai Dong

Leveraging unlabelled data through weak or distant supervision is a compelling approach to developing more effective text classification models. This paper proposes a simple but effective data augmentation method, which leverages the idea of pseudo-labelling to select samples from noisy distant supervision annotation datasets. The result shows that the proposed method improves the accuracy of biased news detection models.

  Access Paper or Ask Questions

JNLP Team: Deep Learning Approaches for Legal Processing Tasks in COLIEE 2021

Jun 25, 2021
Ha-Thanh Nguyen, Phuong Minh Nguyen, Thi-Hai-Yen Vuong, Quan Minh Bui, Chau Minh Nguyen, Binh Tran Dang, Vu Tran, Minh Le Nguyen, Ken Satoh

COLIEE is an annual competition in automatic computerized legal text processing. Automatic legal document processing is an ambitious goal, and the structure and semantics of the law are often far more complex than everyday language. In this article, we survey and report our methods and experimental results in using deep learning in legal document processing. The results show the difficulties as well as potentials in this family of approaches.

* Also published in COLIEE 2021's proceeding 

  Access Paper or Ask Questions

The Volctrans Machine Translation System for WMT20

Oct 28, 2020
Liwei Wu, Xiao Pan, Zehui Lin, Yaoming Zhu, Mingxuan Wang, Lei Li

This paper describes our VolcTrans system on WMT20 shared news translation task. We participated in 8 translation directions. Our basic systems are based on Transformer, with several variants (wider or deeper Transformers, dynamic convolutions). The final system includes text pre-process, data selection, synthetic data generation, advanced model ensemble, and multilingual pre-training.

  Access Paper or Ask Questions