Ndapandula Nakashole

Also published as: Ndapa Nakashole


2020

pdf bib
ChartDialogs: Plotting from Natural Language Instructions
Yutong Shao | Ndapa Nakashole
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

This paper presents the problem of conversational plotting agents that carry out plotting actions from natural language instructions. To facilitate the development of such agents, we introduce ChartDialogs, a new multi-turn dialog dataset, covering a popular plotting library, matplotlib. The dataset contains over 15,000 dialog turns from 3,200 dialogs covering the majority of matplotlib plot types. Extensive experiments show the best-performing method achieving 61% plotting accuracy, demonstrating that the dataset presents a non-trivial challenge for future research on this task.

pdf bib
Rethinking Self-Attention: Towards Interpretability in Neural Parsing
Khalil Mrini | Franck Dernoncourt | Quan Hung Tran | Trung Bui | Walter Chang | Ndapa Nakashole
Findings of the Association for Computational Linguistics: EMNLP 2020

Attention mechanisms have improved the performance of NLP tasks while allowing models to remain explainable. Self-attention is currently widely used, however interpretability is difficult due to the numerous attention distributions. Recent work has shown that model representations can benefit from label-specific information, while facilitating interpretation of predictions. We introduce the Label Attention Layer: a new form of self-attention where attention heads represent labels. We test our novel layer by running constituency and dependency parsing experiments and show our new model obtains new state-of-the-art results for both tasks on both the Penn Treebank (PTB) and Chinese Treebank. Additionally, our model requires fewer self-attention layers compared to existing work. Finally, we find that the Label Attention heads learn relations between syntactic categories and show pathways to analyze errors.

2019

pdf bib
Commonsense about Human Senses: Labeled Data Collection Processes
Ndapa Nakashole
Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing

We consider the problem of extracting from text commonsense knowledge pertaining to human senses such as sound and smell. First, we consider the problem of recognizing mentions of human senses in text. Our contribution is a method for acquiring labeled data. Experiments show the effectiveness of our proposed data labeling approach when used with standard machine learning models on the task of sense recognition in text. Second, we propose to extract novel, common sense relationships pertaining to sense perception concepts. Our contribution is a process for generating labeled data by leveraging large corpora and crowdsourcing questionnaires.

pdf bib
Fine-Grained Spoiler Detection from Large-Scale Review Corpora
Mengting Wan | Rishabh Misra | Ndapa Nakashole | Julian McAuley
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

This paper presents computational approaches for automatically detecting critical plot twists in reviews of media products. First, we created a large-scale book review dataset that includes fine-grained spoiler annotations at the sentence-level, as well as book and (anonymized) user information. Second, we carefully analyzed this dataset, and found that: spoiler language tends to be book-specific; spoiler distributions vary greatly across books and review authors; and spoiler sentences tend to jointly appear in the latter part of reviews. Third, inspired by these findings, we developed an end-to-end neural network architecture to detect spoiler sentences in review corpora. Quantitative and qualitative results demonstrate that the proposed method substantially outperforms existing baselines.

2018

pdf bib
NORMA: Neighborhood Sensitive Maps for Multilingual Word Embeddings
Ndapa Nakashole
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Inducing multilingual word embeddings by learning a linear map between embedding spaces of different languages achieves remarkable accuracy on related languages. However, accuracy drops substantially when translating between distant languages. Given that languages exhibit differences in vocabulary, grammar, written form, or syntax, one would expect that embedding spaces of different languages have different structures especially for distant languages. With the goal of capturing such differences, we propose a method for learning neighborhood sensitive maps, NORMA. Our experiments show that NORMA outperforms current state-of-the-art methods for word translation between distant languages.

pdf bib
Characterizing Departures from Linearity in Word Translation
Ndapa Nakashole | Raphael Flauger
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

We investigate the behavior of maps learned by machine translation methods. The maps translate words by projecting between word embedding spaces of different languages. We locally approximate these maps using linear maps, and find that they vary across the word embedding space. This demonstrates that the underlying maps are non-linear. Importantly, we show that the locally linear maps vary by an amount that is tightly correlated with the distance between the neighborhoods on which they are trained. Our results can be used to test non-linear methods, and to drive the design of more accurate maps for word translation.

2017

pdf bib
Knowledge Distillation for Bilingual Dictionary Induction
Ndapandula Nakashole | Raphael Flauger
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Leveraging zero-shot learning to learn mapping functions between vector spaces of different languages is a promising approach to bilingual dictionary induction. However, methods using this approach have not yet achieved high accuracy on the task. In this paper, we propose a bridging approach, where our main contribution is a knowledge distillation training objective. As teachers, rich resource translation paths are exploited in this role. And as learners, translation paths involving low resource languages learn from the teachers. Our training objective allows seamless addition of teacher translation paths for any given low resource pair. Since our approach relies on the quality of monolingual word embeddings, we also propose to enhance vector representations of both the source and target language with linguistic information. Our experiments on various languages show large performance gains from our distillation training objective, obtaining as high as 17% accuracy improvements.

2015

pdf bib
“A Spousal Relation Begins with a Deletion of engage and Ends with an Addition of divorce”: Learning State Changing Verbs from Wikipedia Revision History
Derry Tanti Wijaya | Ndapandula Nakashole | Tom Mitchell
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

pdf bib
A Knowledge-Intensive Model for Prepositional Phrase Attachment
Ndapandula Nakashole | Tom M. Mitchell
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

2014

pdf bib
Language-Aware Truth Assessment of Fact Candidates
Ndapandula Nakashole | Tom M. Mitchell
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf bib
CTPs: Contextual Temporal Profiles for Time Scoping Facts using State Change Detection
Derry Tanti Wijaya | Ndapandula Nakashole | Tom M. Mitchell
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

2013

pdf bib
Fine-grained Semantic Typing of Emerging Entities
Ndapandula Nakashole | Tomasz Tylenda | Gerhard Weikum
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

2012

pdf bib
Real-time Population of Knowledge Bases: Opportunities and Challenges
Ndapandula Nakashole | Gerhard Weikum
Proceedings of the Joint Workshop on Automatic Knowledge Base Construction and Web-scale Knowledge Extraction (AKBC-WEKEX)

pdf bib
PATTY: A Taxonomy of Relational Patterns with Semantic Types
Ndapandula Nakashole | Gerhard Weikum | Fabian Suchanek
Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning