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

Maximum Entropy, Word-Frequency, Chinese Characters, and Multiple Meanings

Mar 29, 2015
Xiao-Yong Yan, Petter Minnhagen

The word-frequency distribution of a text written by an author is well accounted for by a maximum entropy distribution, the RGF (random group formation)-prediction. The RGF-distribution is completely determined by the a priori values of the total number of words in the text (M), the number of distinct words (N) and the number of repetitions of the most common word (k_max). It is here shown that this maximum entropy prediction also describes a text written in Chinese characters. In particular it is shown that although the same Chinese text written in words and Chinese characters have quite differently shaped distributions, they are nevertheless both well predicted by their respective three a priori characteristic values. It is pointed out that this is analogous to the change in the shape of the distribution when translating a given text to another language. Another consequence of the RGF-prediction is that taking a part of a long text will change the input parameters (M, N, k_max) and consequently also the shape of the frequency distribution. This is explicitly confirmed for texts written in Chinese characters. Since the RGF-prediction has no system-specific information beyond the three a priori values (M, N, k_max), any specific language characteristic has to be sought in systematic deviations from the RGF-prediction and the measured frequencies. One such systematic deviation is identified and, through a statistical information theoretical argument and an extended RGF-model, it is proposed that this deviation is caused by multiple meanings of Chinese characters. The effect is stronger for Chinese characters than for Chinese words. The relation between Zipf's law, the Simon-model for texts and the present results are discussed.

* PLoS ONE 10(5): e0125592 (2015) 
* 15 pages, 10 figures, 2 tables 

  Access Paper or Ask Questions

BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation

Jan 27, 2021
Jwala Dhamala, Tony Sun, Varun Kumar, Satyapriya Krishna, Yada Pruksachatkun, Kai-Wei Chang, Rahul Gupta

Recent advances in deep learning techniques have enabled machines to generate cohesive open-ended text when prompted with a sequence of words as context. While these models now empower many downstream applications from conversation bots to automatic storytelling, they have been shown to generate texts that exhibit social biases. To systematically study and benchmark social biases in open-ended language generation, we introduce the Bias in Open-Ended Language Generation Dataset (BOLD), a large-scale dataset that consists of 23,679 English text generation prompts for bias benchmarking across five domains: profession, gender, race, religion, and political ideology. We also propose new automated metrics for toxicity, psycholinguistic norms, and text gender polarity to measure social biases in open-ended text generation from multiple angles. An examination of text generated from three popular language models reveals that the majority of these models exhibit a larger social bias than human-written Wikipedia text across all domains. With these results we highlight the need to benchmark biases in open-ended language generation and caution users of language generation models on downstream tasks to be cognizant of these embedded prejudices.

  Access Paper or Ask Questions

Deep Learning Approach for Enhanced Cyber Threat Indicators in Twitter Stream

Mar 31, 2020
Simran K, Prathiksha Balakrishna, Vinayakumar R, Soman KP

In recent days, the amount of Cyber Security text data shared via social media resources mainly Twitter has increased. An accurate analysis of this data can help to develop cyber threat situational awareness framework for a cyber threat. This work proposes a deep learning based approach for tweet data analysis. To convert the tweets into numerical representations, various text representations are employed. These features are feed into deep learning architecture for optimal feature extraction as well as classification. Various hyperparameter tuning approaches are used for identifying optimal text representation method as well as optimal network parameters and network structures for deep learning models. For comparative analysis, the classical text representation method with classical machine learning algorithm is employed. From the detailed analysis of experiments, we found that the deep learning architecture with advanced text representation methods performed better than the classical text representation and classical machine learning algorithms. The primary reason for this is that the advanced text representation methods have the capability to learn sequential properties which exist among the textual data and deep learning architectures learns the optimal features along with decreasing the feature size.

* 11 pages 

  Access Paper or Ask Questions

Neural Machine Translation from Simplified Translations

Dec 19, 2016
Josep Crego, Jean Senellart

Text simplification aims at reducing the lexical, grammatical and structural complexity of a text while keeping the same meaning. In the context of machine translation, we introduce the idea of simplified translations in order to boost the learning ability of deep neural translation models. We conduct preliminary experiments showing that translation complexity is actually reduced in a translation of a source bi-text compared to the target reference of the bi-text while using a neural machine translation (NMT) system learned on the exact same bi-text. Based on knowledge distillation idea, we then train an NMT system using the simplified bi-text, and show that it outperforms the initial system that was built over the reference data set. Performance is further boosted when both reference and automatic translations are used to learn the network. We perform an elementary analysis of the translated corpus and report accuracy results of the proposed approach on English-to-French and English-to-German translation tasks.

* Submitted to EACL 2017 Short paper 

  Access Paper or Ask Questions

FewshotQA: A simple framework for few-shot learning of question answering tasks using pre-trained text-to-text models

Sep 10, 2021
Rakesh Chada, Pradeep Natarajan

The task of learning from only a few examples (called a few-shot setting) is of key importance and relevance to a real-world setting. For question answering (QA), the current state-of-the-art pre-trained models typically need fine-tuning on tens of thousands of examples to obtain good results. Their performance degrades significantly in a few-shot setting (< 100 examples). To address this, we propose a simple fine-tuning framework that leverages pre-trained text-to-text models and is directly aligned with their pre-training framework. Specifically, we construct the input as a concatenation of the question, a mask token representing the answer span and a context. Given this input, the model is fine-tuned using the same objective as that of its pre-training objective. Through experimental studies on various few-shot configurations, we show that this formulation leads to significant gains on multiple QA benchmarks (an absolute gain of 34.2 F1 points on average when there are only 16 training examples). The gains extend further when used with larger models (Eg:- 72.3 F1 on SQuAD using BART-large with only 32 examples) and translate well to a multilingual setting . On the multilingual TydiQA benchmark, our model outperforms the XLM-Roberta-large by an absolute margin of upto 40 F1 points and an average of 33 F1 points in a few-shot setting (<= 64 training examples). We conduct detailed ablation studies to analyze factors contributing to these gains.

* Accepted to EMNLP 2021 Main Conference 

  Access Paper or Ask Questions

Logical Inference for Counting on Semi-structured Tables

Apr 25, 2022
Tomoya Kurosawa, Hitomi Yanaka

Recently, the Natural Language Inference (NLI) task has been studied for semi-structured tables that do not have a strict format. Although neural approaches have achieved high performance in various types of NLI, including NLI between semi-structured tables and texts, they still have difficulty in performing a numerical type of inference, such as counting. To handle a numerical type of inference, we propose a logical inference system for reasoning between semi-structured tables and texts. We use logical representations as meaning representations for tables and texts and use model checking to handle a numerical type of inference between texts and tables. To evaluate the extent to which our system can perform inference with numerical comparatives, we make an evaluation protocol that focuses on numerical understanding between semi-structured tables and texts in English. We show that our system can more robustly perform inference between tables and texts that requires numerical understanding compared with current neural approaches.

* 13 pages. To appear in the Proceedings of the Association for Computational Linguistics: Student Research Workshop (ACL-SRW 2022) 

  Access Paper or Ask Questions

Multimodal Interactions Using Pretrained Unimodal Models for SIMMC 2.0

Dec 18, 2021
Joosung Lee, Kijong Han

This paper presents our work on the Situated Interactive MultiModal Conversations 2.0 challenge held at Dialog State Tracking Challenge 10. SIMMC 2.0 includes 4 subtasks, and we introduce our multimodal approaches for the subtask \#1, \#2 and the generation of subtask \#4. SIMMC 2.0 dataset is a multimodal dataset containing image and text information, which is more challenging than the problem of only text-based conversations because it must be solved by understanding the relationship between image and text. Therefore, since there is a limit to solving only text models such as BERT or GPT2, we propose a multimodal model combining image and text. We first pretrain the multimodal model to understand the relationship between image and text, then finetune our model for each task. We achieve the 3rd best performance in subtask \#1, \#2 and a runner-up in the generation of subtask \#4. The source code is available at

* Accepted to DSTC10 challenge wokrshop at AAAI 2022 

  Access Paper or Ask Questions