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

Crowdsourcing and Validating Event-focused Emotion Corpora for German and English

May 31, 2019
Enrica Troiano, Sebastian Pad贸, Roman Klinger

Sentiment analysis has a range of corpora available across multiple languages. For emotion analysis, the situation is more limited, which hinders potential research on cross-lingual modeling and the development of predictive models for other languages. In this paper, we fill this gap for German by constructing deISEAR, a corpus designed in analogy to the well-established English ISEAR emotion dataset. Motivated by Scherer's appraisal theory, we implement a crowdsourcing experiment which consists of two steps. In step 1, participants create descriptions of emotional events for a given emotion. In step 2, five annotators assess the emotion expressed by the texts. We show that transferring an emotion classification model from the original English ISEAR to the German crowdsourced deISEAR via machine translation does not, on average, cause a performance drop.

* 14 pages, 1 figure, accepted for publication at ACL 2019 

  Access Paper or Ask Questions

Harry Potter and the Action Prediction Challenge from Natural Language

May 27, 2019
David Vilares, Carlos G贸mez-Rodr铆guez

We explore the challenge of action prediction from textual descriptions of scenes, a testbed to approximate whether text inference can be used to predict upcoming actions. As a case of study, we consider the world of the Harry Potter fantasy novels and inferring what spell will be cast next given a fragment of a story. Spells act as keywords that abstract actions (e.g. 'Alohomora' to open a door) and denote a response to the environment. This idea is used to automatically build HPAC, a corpus containing 82,836 samples and 85 actions. We then evaluate different baselines. Among the tested models, an LSTM-based approach obtains the best performance for frequent actions and large scene descriptions, but approaches such as logistic regression behave well on infrequent actions.

* NAACL 2019 (short papers) 

  Access Paper or Ask Questions

Multi-task Learning for Japanese Predicate Argument Structure Analysis

Apr 03, 2019
Hikaru Omori, Mamoru Komachi

An event-noun is a noun that has an argument structure similar to a predicate. Recent works, including those considered state-of-the-art, ignore event-nouns or build a single model for solving both Japanese predicate argument structure analysis (PASA) and event-noun argument structure analysis (ENASA). However, because there are interactions between predicates and event-nouns, it is not sufficient to target only predicates. To address this problem, we present a multi-task learning method for PASA and ENASA. Our multi-task models improved the performance of both tasks compared to a single-task model by sharing knowledge from each task. Moreover, in PASA, our models achieved state-of-the-art results in overall F1 scores on the NAIST Text Corpus. In addition, this is the first work to employ neural networks in ENASA.

* 10 pages; NAACL 2019 

  Access Paper or Ask Questions

Identifying Computer-Translated Paragraphs using Coherence Features

Dec 28, 2018
Hoang-Quoc Nguyen-Son, Ngoc-Dung T. Tieu, Huy H. Nguyen, Junichi Yamagishi, Isao Echizen

We have developed a method for extracting the coherence features from a paragraph by matching similar words in its sentences. We conducted an experiment with a parallel German corpus containing 2000 human-created and 2000 machine-translated paragraphs. The result showed that our method achieved the best performance (accuracy = 72.3%, equal error rate = 29.8%) when it is compared with previous methods on various computer-generated text including translation and paper generation (best accuracy = 67.9%, equal error rate = 32.0%). Experiments on Dutch, another rich resource language, and a low resource one (Japanese) attained similar performances. It demonstrated the efficiency of the coherence features at distinguishing computer-translated from human-created paragraphs on diverse languages.

* 9 pages, PACLIC 2018 

  Access Paper or Ask Questions

On the Strength of Character Language Models for Multilingual Named Entity Recognition

Sep 20, 2018
Xiaodong Yu, Stephen Mayhew, Mark Sammons, Dan Roth

Character-level patterns have been widely used as features in English Named Entity Recognition (NER) systems. However, to date there has been no direct investigation of the inherent differences between name and non-name tokens in text, nor whether this property holds across multiple languages. This paper analyzes the capabilities of corpus-agnostic Character-level Language Models (CLMs) in the binary task of distinguishing name tokens from non-name tokens. We demonstrate that CLMs provide a simple and powerful model for capturing these differences, identifying named entity tokens in a diverse set of languages at close to the performance of full NER systems. Moreover, by adding very simple CLM-based features we can significantly improve the performance of an off-the-shelf NER system for multiple languages.

* EMNLP 2018 
* 5 pages, EMNLP 2018 short paper 

  Access Paper or Ask Questions

Policy Shaping and Generalized Update Equations for Semantic Parsing from Denotations

Sep 05, 2018
Dipendra Misra, Ming-Wei Chang, Xiaodong He, Wen-tau Yih

Semantic parsing from denotations faces two key challenges in model training: (1) given only the denotations (e.g., answers), search for good candidate semantic parses, and (2) choose the best model update algorithm. We propose effective and general solutions to each of them. Using policy shaping, we bias the search procedure towards semantic parses that are more compatible to the text, which provide better supervision signals for training. In addition, we propose an update equation that generalizes three different families of learning algorithms, which enables fast model exploration. When experimented on a recently proposed sequential question answering dataset, our framework leads to a new state-of-the-art model that outperforms previous work by 5.0% absolute on exact match accuracy.

* Accepted at EMNLP 2018 

  Access Paper or Ask Questions

Deep Extrofitting: Specialization and Generalization of Expansional Retrofitting Word Vectors using Semantic Lexicons

Sep 04, 2018
Hwiyeol Jo

The retrofitting techniques, which inject external resources into word representations, have compensated the weakness of distributed representations in semantic and relational knowledge between words. Implicitly retrofitting word vectors by expansional technique showed that the method outperforms retrofitting in word similarity task with generalization. In this paper, we propose deep extrofitting: in-depth stacking of extrofitting. We first stack extrofitting for word vector generalization. Next, we combine extrofitting with retrofitting, finding new vector space on specialization that prevents retrofitting from converging in a few iterations. When experimenting with GloVe, we show that our methods outperform the previous methods on most of word similarity task while requiring only synonyms as external resources. We also report further analysis on the effect of word vector specialization and word vector generalization in text classification task.

  Access Paper or Ask Questions

Semantic Relation Classification: Task Formalisation and Refinement

Jun 20, 2018
Vivian S. Silva, Manuela H眉rliman, Brian Davis, Siegfried Handschuh, Andr茅 Freitas

The identification of semantic relations between terms within texts is a fundamental task in Natural Language Processing which can support applications requiring a lightweight semantic interpretation model. Currently, semantic relation classification concentrates on relations which are evaluated over open-domain data. This work provides a critique on the set of abstract relations used for semantic relation classification with regard to their ability to express relationships between terms which are found in a domain-specific corpora. Based on this analysis, this work proposes an alternative semantic relation model based on reusing and extending the set of abstract relations present in the DOLCE ontology. The resulting set of relations is well grounded, allows to capture a wide range of relations and could thus be used as a foundation for automatic classification of semantic relations.

* Proceedings of the 5th Workshop on Cognitive Aspects of the Lexicon, Osaka, Japan, 2016, pp 30-39 
* 10 pages, presented at CogALex-V 2016 

  Access Paper or Ask Questions

SGM: Sequence Generation Model for Multi-label Classification

Jun 15, 2018
Pengcheng Yang, Xu Sun, Wei Li, Shuming Ma, Wei Wu, Houfeng Wang

Multi-label classification is an important yet challenging task in natural language processing. It is more complex than single-label classification in that the labels tend to be correlated. Existing methods tend to ignore the correlations between labels. Besides, different parts of the text can contribute differently for predicting different labels, which is not considered by existing models. In this paper, we propose to view the multi-label classification task as a sequence generation problem, and apply a sequence generation model with a novel decoder structure to solve it. Extensive experimental results show that our proposed methods outperform previous work by a substantial margin. Further analysis of experimental results demonstrates that the proposed methods not only capture the correlations between labels, but also select the most informative words automatically when predicting different labels.

* Accepted by COLING 2018 

  Access Paper or Ask Questions

MemGEN: Memory is All You Need

Mar 29, 2018
Sylvain Gelly, Karol Kurach, Marcin Michalski, Xiaohua Zhai

We propose a new learning paradigm called Deep Memory. It has the potential to completely revolutionize the Machine Learning field. Surprisingly, this paradigm has not been reinvented yet, unlike Deep Learning. At the core of this approach is the \textit{Learning By Heart} principle, well studied in primary schools all over the world. Inspired by poem recitation, or by $\pi$ decimal memorization, we propose a concrete algorithm that mimics human behavior. We implement this paradigm on the task of generative modeling, and apply to images, natural language and even the $\pi$ decimals as long as one can print them as text. The proposed algorithm even generated this paper, in a one-shot learning setting. In carefully designed experiments, we show that the generated samples are indistinguishable from the training examples, as measured by any statistical tests or metrics.

  Access Paper or Ask Questions